release 2017.05.07

To state that this is an internal function and people should be careful
when using it outside youtube-dl.

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.04.26*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.04.26**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.05.07*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.05.07**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2017.04.26
+[debug] youtube-dl version 2017.05.07
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

ChangeLog

@@ -1,3 +1,80 @@
+version 2017.05.07
+
+Common
+* [extractor/common] Fix typo in _extract_akamai_formats
++ [postprocessor/ffmpeg] Embed chapters into media file with --add-metadata
++ [extractor/common] Introduce chapters meta field
+
+Extractors
+* [youtube] Fix authentication (#12820, #12927, #12973, #12992, #12993, #12995,
+  #13003)
+* [bilibili] Fix video downloading (#13001)
+* [rmcdecouverte] Fix extraction (#12937)
+* [theplatform] Extract chapters
+* [bandcamp] Fix thumbnail extraction (#12980)
+* [pornhub] Extend URL regular expression (#12996)
++ [youtube] Extract chapters
++ [nrk] Extract chapters
++ [vice] Add support for ooyala embeds in article pages
++ [vice] Support vice articles (#12968)
+* [vice] Fix extraction for non en_us videos (#12967)
+* [gdcvault] Fix extraction for some videos (#12733)
+* [pbs] Improve multipart video support (#12981)
+* [laola1tv] Fix extraction (#12880)
++ [cda] Support birthday verification (#12789)
+* [leeco] Fix extraction (#12974)
++ [pbs] Extract chapters
+* [amp] Imporove thumbnail and subtitles extraction
+* [foxsports] Fix extraction (#12945)
+- [coub] Remove comment count extraction (#12941)
+
+
+version 2017.05.01
+
+Core
++ [extractor/common] Extract view count from JSON-LD
+* [utils] Improve unified_timestamp
++ [utils] Add video/mp2t to mimetype2ext
+* [downloader/external] Properly handle live stream downloading cancellation
+  (#8932)
++ [utils] Add support for unicode whitespace in clean_html on python 2 (#12906)
+
+Extractors
+* [infoq] Make audio format extraction non fatal (#12938)
+* [brightcove] Allow whitespace around attribute names in embedded code
++ [zaq1] Add support for zaq1.pl (#12693)
++ [xvideos] Extract duration (#12828)
+* [vevo] Fix extraction (#12879)
++ [noovo] Add support for noovo.ca (#12792)
++ [washingtonpost] Add support for embeds (#12699)
+* [yandexmusic:playlist] Fix extraction for python 3 (#12888)
+* [anvato] Improve extraction (#12913)
+    * Promote to regular shortcut based extractor
+    * Add mcp to access key mapping table
+    * Add support for embeds extraction
+    * Add support for anvato embeds in generic extractor
+* [xtube] Fix extraction for older FLV videos (#12734)
+* [tvplayer] Fix extraction (#12908)
+
+
+version 2017.04.28
+
+Core
++ [adobepass] Use geo verification headers for all requests
+- [downloader/fragment] Remove assert for resume_len when no fragments
+  downloaded
++ [extractor/common] Add manifest_url for explicit group rendition formats
+* [extractor/common] Fix manifest_url for m3u8 formats
+- [extractor/common] Don't list master m3u8 playlists in format list (#12832)
+
+Extractor
+* [aenetworks] Fix extraction for shows with single season
++ [go] Add support for Disney, DisneyJunior and DisneyXD show pages
+* [youtube] Recognize new locale-based player URLs (#12885)
++ [streamable] Add support for new embedded URL schema (#12844)
+* [arte:+7] Relax URL regular expression (#12837)
+
+
 version 2017.04.26
 
 Core
@@ -6,19 +83,19 @@ Core
 * [YoutubeDL] Fix output template for missing timestamp (#12796)
 * [socks] Handle cases where credentials are required but missing
 * [extractor/common] Improve HLS extraction (#12211)
-    - Extract m3u8 parsing to separate method
-    - Improve rendition groups extraction
-    - Build stream name according stream GROUP-ID
-    - Ignore reference to AUDIO group without URI when stream has no CODECS
-    - Use float for scaled tbr in _parse_m3u8_formats
+    * Extract m3u8 parsing to separate method
+    * Improve rendition groups extraction
+    * Build stream name according stream GROUP-ID
+    * Ignore reference to AUDIO group without URI when stream has no CODECS
+    * Use float for scaled tbr in _parse_m3u8_formats
 * [utils] Add support for TTML styles in dfxp2srt
 * [downloader/hls] No need to download keys for fragments that have been
   already downloaded
 * [downloader/fragment] Improve fragment downloading
-    - Resume immediately
-    - Don't concatenate fragments and decrypt them on every resume
-    - Optimize disk storage usage, don't store intermediate fragments on disk
-    - Store bookkeeping download state file
+    * Resume immediately
+    * Don't concatenate fragments and decrypt them on every resume
+    * Optimize disk storage usage, don't store intermediate fragments on disk
+    * Store bookkeeping download state file
 + [extractor/common] Add support for multiple getters in try_get
 + [extractor/common] Add support for video of WebPage context in _json_ld
   (#12778)

docs/supportedsites.md

@@ -45,6 +45,7 @@
  - **anderetijden**: npo.nl and ntr.nl
  - **AnimeOnDemand**
  - **anitube.se**
+ - **Anvato**
  - **AnySex**
  - **Aparat**
  - **AppleConnect**
@@ -529,6 +530,7 @@
  - **NJPWWorld**: 新日本プロレスワールド
  - **NobelPrize**
  - **Noco**
+ - **Noovo**
  - **Normalboots**
  - **NosVideo**
  - **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz
@@ -877,9 +879,10 @@
  - **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
  - **vh1.com**
  - **Viafree**
- - **Vice**
+ - **vice**
+ - **vice:article**
+ - **vice:show**
  - **Viceland**
- - **ViceShow**
  - **Vidbit**
  - **Viddler**
  - **Videa**
@@ -1013,6 +1016,7 @@
  - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
  - **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
  - **Zapiks**
+ - **Zaq1**
  - **ZDF**
  - **ZDFChannel**
  - **zingmp3**: mp3.zing.vn

test/test_InfoExtractor.py

@@ -184,16 +184,8 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                 'pluzz_francetv_11507',
                 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
                 [{
-                    'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
-                    'ext': 'mp4',
-                    'format_id': 'meta',
-                    'format_note': 'Quality selection URL',
-                    'protocol': 'm3u8',
-                    'preference': -100,
-                    'resolution': 'multiple'
-                }, {
                     'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_0_av.m3u8?null=0',
-                    'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_0_av.m3u8?null=0',
+                    'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
                     'ext': 'mp4',
                     'format_id': '180',
                     'protocol': 'm3u8',
@@ -204,7 +196,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 144,
                 }, {
                     'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_1_av.m3u8?null=0',
-                    'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_1_av.m3u8?null=0',
+                    'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
                     'ext': 'mp4',
                     'format_id': '303',
                     'protocol': 'm3u8',
@@ -215,7 +207,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 180,
                 }, {
                     'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_2_av.m3u8?null=0',
-                    'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_2_av.m3u8?null=0',
+                    'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
                     'ext': 'mp4',
                     'format_id': '575',
                     'protocol': 'm3u8',
@@ -226,7 +218,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 288,
                 }, {
                     'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_3_av.m3u8?null=0',
-                    'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_3_av.m3u8?null=0',
+                    'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
                     'ext': 'mp4',
                     'format_id': '831',
                     'protocol': 'm3u8',
@@ -237,7 +229,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 396,
                 }, {
                     'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_4_av.m3u8?null=0',
-                    'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_4_av.m3u8?null=0',
+                    'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
                     'ext': 'mp4',
                     'protocol': 'm3u8',
                     'format_id': '1467',
@@ -254,28 +246,22 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                 'teamcoco_11995',
                 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
                 [{
-                    'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
-                    'ext': 'mp4',
-                    'format_id': 'meta',
-                    'format_note': 'Quality selection URL',
-                    'protocol': 'm3u8',
-                    'preference': -100,
-                    'resolution': 'multiple',
-                }, {
                     'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-audio-160k_v4.m3u8',
+                    'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
                     'ext': 'mp4',
                     'format_id': 'audio-0-Default',
                     'protocol': 'm3u8',
                     'vcodec': 'none',
                 }, {
                     'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-audio-64k_v4.m3u8',
+                    'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
                     'ext': 'mp4',
                     'format_id': 'audio-1-Default',
                     'protocol': 'm3u8',
                     'vcodec': 'none',
                 }, {
                     'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-audio-64k_v4.m3u8',
-                    'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-audio-64k_v4.m3u8',
+                    'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
                     'ext': 'mp4',
                     'format_id': '71',
                     'protocol': 'm3u8',
@@ -284,7 +270,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'tbr': 71,
                 }, {
                     'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-400k_v4.m3u8',
-                    'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-400k_v4.m3u8',
+                    'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
                     'ext': 'mp4',
                     'format_id': '413',
                     'protocol': 'm3u8',
@@ -295,7 +281,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 224,
                 }, {
                     'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-400k_v4.m3u8',
-                    'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-400k_v4.m3u8',
+                    'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
                     'ext': 'mp4',
                     'format_id': '522',
                     'protocol': 'm3u8',
@@ -306,7 +292,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 224,
                 }, {
                     'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-1m_v4.m3u8',
-                    'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-1m_v4.m3u8',
+                    'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
                     'ext': 'mp4',
                     'format_id': '1205',
                     'protocol': 'm3u8',
@@ -317,7 +303,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 360,
                 }, {
                     'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-2m_v4.m3u8',
-                    'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-2m_v4.m3u8',
+                    'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
                     'ext': 'mp4',
                     'format_id': '2374',
                     'protocol': 'm3u8',
@@ -334,15 +320,8 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                 'toggle_mobile_12211',
                 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
                 [{
-                    'url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
-                    'ext': 'mp4',
-                    'format_id': 'meta',
-                    'format_note': 'Quality selection URL',
-                    'protocol': 'm3u8',
-                    'preference': -100,
-                    'resolution': 'multiple'
-                }, {
                     'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_sa2ntrdg/name/a.mp4/index.m3u8',
+                    'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
                     'ext': 'mp4',
                     'format_id': 'audio-English',
                     'protocol': 'm3u8',
@@ -350,6 +329,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'vcodec': 'none',
                 }, {
                     'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_r7y0nitg/name/a.mp4/index.m3u8',
+                    'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
                     'ext': 'mp4',
                     'format_id': 'audio-Undefined',
                     'protocol': 'm3u8',
@@ -357,7 +337,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'vcodec': 'none',
                 }, {
                     'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_qlk9hlzr/name/a.mp4/index.m3u8',
-                    'manifest_url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_qlk9hlzr/name/a.mp4/index.m3u8',
+                    'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
                     'ext': 'mp4',
                     'format_id': '155',
                     'protocol': 'm3u8',
@@ -366,7 +346,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 180,
                 }, {
                     'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_oefackmi/name/a.mp4/index.m3u8',
-                    'manifest_url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_oefackmi/name/a.mp4/index.m3u8',
+                    'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
                     'ext': 'mp4',
                     'format_id': '502',
                     'protocol': 'm3u8',
@@ -375,7 +355,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 270,
                 }, {
                     'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/12/pv/1/flavorId/0_vyg9pj7k/name/a.mp4/index.m3u8',
-                    'manifest_url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/12/pv/1/flavorId/0_vyg9pj7k/name/a.mp4/index.m3u8',
+                    'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
                     'ext': 'mp4',
                     'format_id': '827',
                     'protocol': 'm3u8',
@@ -384,7 +364,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 360,
                 }, {
                     'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/12/pv/1/flavorId/0_50n4psvx/name/a.mp4/index.m3u8',
-                    'manifest_url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/12/pv/1/flavorId/0_50n4psvx/name/a.mp4/index.m3u8',
+                    'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
                     'ext': 'mp4',
                     'format_id': '1396',
                     'protocol': 'm3u8',
@@ -398,16 +378,8 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                 'twitch_vod',
                 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
                 [{
-                    'url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
-                    'ext': 'mp4',
-                    'format_id': 'meta',
-                    'format_note': 'Quality selection URL',
-                    'protocol': 'm3u8',
-                    'preference': -100,
-                    'resolution': 'multiple'
-                }, {
                     'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/audio_only/index-muted-HM49I092CC.m3u8',
-                    'manifest_url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/audio_only/index-muted-HM49I092CC.m3u8',
+                    'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
                     'ext': 'mp4',
                     'format_id': 'Audio Only',
                     'protocol': 'm3u8',
@@ -416,7 +388,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'tbr': 182.725,
                 }, {
                     'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/mobile/index-muted-HM49I092CC.m3u8',
-                    'manifest_url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/mobile/index-muted-HM49I092CC.m3u8',
+                    'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
                     'ext': 'mp4',
                     'format_id': 'Mobile',
                     'protocol': 'm3u8',
@@ -427,7 +399,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 226,
                 }, {
                     'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/low/index-muted-HM49I092CC.m3u8',
-                    'manifest_url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/low/index-muted-HM49I092CC.m3u8',
+                    'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
                     'ext': 'mp4',
                     'format_id': 'Low',
                     'protocol': 'm3u8',
@@ -438,7 +410,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 360,
                 }, {
                     'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/medium/index-muted-HM49I092CC.m3u8',
-                    'manifest_url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/medium/index-muted-HM49I092CC.m3u8',
+                    'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
                     'ext': 'mp4',
                     'format_id': 'Medium',
                     'protocol': 'm3u8',
@@ -449,7 +421,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 480,
                 }, {
                     'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/high/index-muted-HM49I092CC.m3u8',
-                    'manifest_url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/high/index-muted-HM49I092CC.m3u8',
+                    'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
                     'ext': 'mp4',
                     'format_id': 'High',
                     'protocol': 'm3u8',
@@ -460,7 +432,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 720,
                 }, {
                     'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/chunked/index-muted-HM49I092CC.m3u8',
-                    'manifest_url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/chunked/index-muted-HM49I092CC.m3u8',
+                    'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
                     'ext': 'mp4',
                     'format_id': 'Source',
                     'protocol': 'm3u8',
@@ -478,16 +450,8 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                 'vidio',
                 'https://www.vidio.com/videos/165683/playlist.m3u8',
                 [{
-                    'url': 'https://www.vidio.com/videos/165683/playlist.m3u8',
-                    'ext': 'mp4',
-                    'format_id': 'meta',
-                    'format_note': 'Quality selection URL',
-                    'protocol': 'm3u8',
-                    'preference': -100,
-                    'resolution': 'multiple'
-                }, {
                     'url': 'https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b300.mp4.m3u8',
-                    'manifest_url': 'https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b300.mp4.m3u8',
+                    'manifest_url': 'https://www.vidio.com/videos/165683/playlist.m3u8',
                     'ext': 'mp4',
                     'format_id': '270p 3G',
                     'protocol': 'm3u8',
@@ -496,7 +460,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 270,
                 }, {
                     'url': 'https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b600.mp4.m3u8',
-                    'manifest_url': 'https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b600.mp4.m3u8',
+                    'manifest_url': 'https://www.vidio.com/videos/165683/playlist.m3u8',
                     'ext': 'mp4',
                     'format_id': '360p SD',
                     'protocol': 'm3u8',
@@ -505,7 +469,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 360,
                 }, {
                     'url': 'https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b1200.mp4.m3u8',
-                    'manifest_url': 'https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b1200.mp4.m3u8',
+                    'manifest_url': 'https://www.vidio.com/videos/165683/playlist.m3u8',
                     'ext': 'mp4',
                     'format_id': '720p HD',
                     'protocol': 'm3u8',

test/test_download.py

@@ -225,7 +225,7 @@ def generator(test_case, tname):
                                 format_bytes(got_fsize)))
                     if 'md5' in tc:
                         md5_for_file = _file_md5(tc_filename)
-                        self.assertEqual(md5_for_file, tc['md5'])
+                        self.assertEqual(tc['md5'], md5_for_file)
                 # Finally, check test cases' data again but this time against
                 # extracted data from info JSON file written during processing
                 info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'

test/test_utils.py

@@ -44,6 +44,7 @@ from youtube_dl.utils import (
     limit_length,
     mimetype2ext,
     month_by_name,
+    multipart_encode,
     ohdave_rsa_encrypt,
     OnDemandPagedList,
     orderedSet,
@@ -338,6 +339,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
         self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
         self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
+        self.assertEqual(unified_timestamp('2017-03-30T17:52:41Q'), 1490896361)
 
     def test_determine_ext(self):
         self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
@@ -619,6 +621,16 @@ class TestUtil(unittest.TestCase):
             'http://example.com/path', {'test': '第二行тест'})),
             query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
 
+    def test_multipart_encode(self):
+        self.assertEqual(
+            multipart_encode({b'field': b'value'}, boundary='AAAAAA')[0],
+            b'--AAAAAA\r\nContent-Disposition: form-data; name="field"\r\n\r\nvalue\r\n--AAAAAA--\r\n')
+        self.assertEqual(
+            multipart_encode({'欄位'.encode('utf-8'): '值'.encode('utf-8')}, boundary='AAAAAA')[0],
+            b'--AAAAAA\r\nContent-Disposition: form-data; name="\xe6\xac\x84\xe4\xbd\x8d"\r\n\r\n\xe5\x80\xbc\r\n--AAAAAA--\r\n')
+        self.assertRaises(
+            ValueError, multipart_encode, {b'field': b'value'}, boundary='value')
+
     def test_dict_get(self):
         FALSE_VALUES = {
             'none': None,
@@ -899,6 +911,7 @@ class TestUtil(unittest.TestCase):
     def test_clean_html(self):
         self.assertEqual(clean_html('a:\nb'), 'a: b')
         self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')
+        self.assertEqual(clean_html('a<br>\xa0b'), 'a\nb')
 
     def test_intlist_to_bytes(self):
         self.assertEqual(

test/test_youtube_chapters.py

@@ -0,0 +1,268 @@
+#!/usr/bin/env python
+# coding: utf-8
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from test.helper import expect_value
+from youtube_dl.extractor import YoutubeIE
+
+
+class TestYoutubeChapters(unittest.TestCase):
+
+    _TEST_CASES = [
+        (
+            # https://www.youtube.com/watch?v=A22oy8dFjqc
+            # pattern: 00:00 - <title>
+            '''This is the absolute ULTIMATE experience of Queen's set at LIVE AID, this is the best video mixed to the absolutely superior stereo radio broadcast. This vastly superior audio mix takes a huge dump on all of the official mixes. Best viewed in 1080p. ENJOY! ***MAKE SURE TO READ THE DESCRIPTION***<br /><a href="#" onclick="yt.www.watch.player.seekTo(00*60+36);return false;">00:36</a> - Bohemian Rhapsody<br /><a href="#" onclick="yt.www.watch.player.seekTo(02*60+42);return false;">02:42</a> - Radio Ga Ga<br /><a href="#" onclick="yt.www.watch.player.seekTo(06*60+53);return false;">06:53</a> - Ay Oh!<br /><a href="#" onclick="yt.www.watch.player.seekTo(07*60+34);return false;">07:34</a> - Hammer To Fall<br /><a href="#" onclick="yt.www.watch.player.seekTo(12*60+08);return false;">12:08</a> - Crazy Little Thing Called Love<br /><a href="#" onclick="yt.www.watch.player.seekTo(16*60+03);return false;">16:03</a> - We Will Rock You<br /><a href="#" onclick="yt.www.watch.player.seekTo(17*60+18);return false;">17:18</a> - We Are The Champions<br /><a href="#" onclick="yt.www.watch.player.seekTo(21*60+12);return false;">21:12</a> - Is This The World We Created...?<br /><br />Short song analysis:<br /><br />- "Bohemian Rhapsody": Although it's a short medley version, it's one of the best performances of the ballad section, with Freddie nailing the Bb4s with the correct studio phrasing (for the first time ever!).<br /><br />- "Radio Ga Ga": Although it's missing one chorus, this is one of - if not the best - the best versions ever, Freddie nails all the Bb4s and sounds very clean! Spike Edney's Roland Jupiter 8 also really shines through on this mix, compared to the DVD releases!<br /><br />- "Audience Improv": A great improv, Freddie sounds strong and confident. You gotta love when he sustains that A4 for 4 seconds!<br /><br />- "Hammer To Fall": Despite missing a verse and a chorus, it's a strong version (possibly the best ever). Freddie sings the song amazingly, and even ad-libs a C#5 and a C5! Also notice how heavy Brian's guitar sounds compared to the thin DVD mixes - it roars!<br /><br />- "Crazy Little Thing Called Love": A great version, the crowd loves the song, the jam is great as well! Only downside to this is the slight feedback issues.<br /><br />- "We Will Rock You": Although cut down to the 1st verse and chorus, Freddie sounds strong. He nails the A4, and the solo from Dr. May is brilliant!<br /><br />- "We Are the Champions": Perhaps the high-light of the performance - Freddie is very daring on this version, he sustains the pre-chorus Bb4s, nails the 1st C5, belts great A4s, but most importantly: He nails the chorus Bb4s, in all 3 choruses! This is the only time he has ever done so! It has to be said though, the last one sounds a bit rough, but that's a side effect of belting high notes for the past 18 minutes, with nodules AND laryngitis!<br /><br />- "Is This The World We Created... ?": Freddie and Brian perform a beautiful version of this, and it is one of the best versions ever. It's both sad and hilarious that a couple of BBC engineers are talking over the song, one of them being completely oblivious of the fact that he is interrupting the performance, on live television... Which was being televised to almost 2 billion homes.<br /><br /><br />All rights go to their respective owners!<br />-----Copyright Disclaimer Under Section 107 of the Copyright Act 1976, allowance is made for fair use for purposes such as criticism, comment, news reporting, teaching, scholarship, and research. Fair use is a use permitted by copyright statute that might otherwise be infringing. Non-profit, educational or personal use tips the balance in favor of fair use''',
+            1477,
+            [{
+                'start_time': 36,
+                'end_time': 162,
+                'title': 'Bohemian Rhapsody',
+            }, {
+                'start_time': 162,
+                'end_time': 413,
+                'title': 'Radio Ga Ga',
+            }, {
+                'start_time': 413,
+                'end_time': 454,
+                'title': 'Ay Oh!',
+            }, {
+                'start_time': 454,
+                'end_time': 728,
+                'title': 'Hammer To Fall',
+            }, {
+                'start_time': 728,
+                'end_time': 963,
+                'title': 'Crazy Little Thing Called Love',
+            }, {
+                'start_time': 963,
+                'end_time': 1038,
+                'title': 'We Will Rock You',
+            }, {
+                'start_time': 1038,
+                'end_time': 1272,
+                'title': 'We Are The Champions',
+            }, {
+                'start_time': 1272,
+                'end_time': 1477,
+                'title': 'Is This The World We Created...?',
+            }]
+        ),
+        (
+            # https://www.youtube.com/watch?v=ekYlRhALiRQ
+            # pattern: <num>. <title> 0:00
+            '1.  Those Beaten Paths of Confusion <a href="#" onclick="yt.www.watch.player.seekTo(0*60+00);return false;">0:00</a><br />2.  Beyond the Shadows of Emptiness & Nothingness <a href="#" onclick="yt.www.watch.player.seekTo(11*60+47);return false;">11:47</a><br />3.  Poison Yourself...With Thought <a href="#" onclick="yt.www.watch.player.seekTo(26*60+30);return false;">26:30</a><br />4.  The Agents of Transformation <a href="#" onclick="yt.www.watch.player.seekTo(35*60+57);return false;">35:57</a><br />5.  Drowning in the Pain of Consciousness <a href="#" onclick="yt.www.watch.player.seekTo(44*60+32);return false;">44:32</a><br />6.  Deny the Disease of Life <a href="#" onclick="yt.www.watch.player.seekTo(53*60+07);return false;">53:07</a><br /><br />More info/Buy: http://crepusculonegro.storenvy.com/products/257645-cn-03-arizmenda-within-the-vacuum-of-infinity<br /><br />No copyright is intended. The rights to this video are assumed by the owner and its affiliates.',
+            4009,
+            [{
+                'start_time': 0,
+                'end_time': 707,
+                'title': '1. Those Beaten Paths of Confusion',
+            }, {
+                'start_time': 707,
+                'end_time': 1590,
+                'title': '2. Beyond the Shadows of Emptiness & Nothingness',
+            }, {
+                'start_time': 1590,
+                'end_time': 2157,
+                'title': '3. Poison Yourself...With Thought',
+            }, {
+                'start_time': 2157,
+                'end_time': 2672,
+                'title': '4. The Agents of Transformation',
+            }, {
+                'start_time': 2672,
+                'end_time': 3187,
+                'title': '5. Drowning in the Pain of Consciousness',
+            }, {
+                'start_time': 3187,
+                'end_time': 4009,
+                'title': '6. Deny the Disease of Life',
+            }]
+        ),
+        (
+            # https://www.youtube.com/watch?v=WjL4pSzog9w
+            # pattern: 00:00 <title>
+            '<a href="https://arizmenda.bandcamp.com/merch/despairs-depths-descended-cd" class="yt-uix-servicelink  " data-target-new-window="True" data-servicelink="CDAQ6TgYACITCNf1raqT2dMCFdRjGAod_o0CBSj4HQ" data-url="https://arizmenda.bandcamp.com/merch/despairs-depths-descended-cd" rel="nofollow noopener" target="_blank">https://arizmenda.bandcamp.com/merch/...</a><br /><br /><a href="#" onclick="yt.www.watch.player.seekTo(00*60+00);return false;">00:00</a> Christening Unborn Deformities <br /><a href="#" onclick="yt.www.watch.player.seekTo(07*60+08);return false;">07:08</a> Taste of Purity<br /><a href="#" onclick="yt.www.watch.player.seekTo(16*60+16);return false;">16:16</a> Sculpting Sins of a Universal Tongue<br /><a href="#" onclick="yt.www.watch.player.seekTo(24*60+45);return false;">24:45</a> Birth<br /><a href="#" onclick="yt.www.watch.player.seekTo(31*60+24);return false;">31:24</a> Neves<br /><a href="#" onclick="yt.www.watch.player.seekTo(37*60+55);return false;">37:55</a> Libations in Limbo',
+            2705,
+            [{
+                'start_time': 0,
+                'end_time': 428,
+                'title': 'Christening Unborn Deformities',
+            }, {
+                'start_time': 428,
+                'end_time': 976,
+                'title': 'Taste of Purity',
+            }, {
+                'start_time': 976,
+                'end_time': 1485,
+                'title': 'Sculpting Sins of a Universal Tongue',
+            }, {
+                'start_time': 1485,
+                'end_time': 1884,
+                'title': 'Birth',
+            }, {
+                'start_time': 1884,
+                'end_time': 2275,
+                'title': 'Neves',
+            }, {
+                'start_time': 2275,
+                'end_time': 2705,
+                'title': 'Libations in Limbo',
+            }]
+        ),
+        (
+            # https://www.youtube.com/watch?v=o3r1sn-t3is
+            # pattern: <title> 00:00 <note>
+            'Download this show in MP3: <a href="http://sh.st/njZKK" class="yt-uix-servicelink  " data-url="http://sh.st/njZKK" data-target-new-window="True" data-servicelink="CDAQ6TgYACITCK3j8_6o2dMCFVDCGAoduVAKKij4HQ" rel="nofollow noopener" target="_blank">http://sh.st/njZKK</a><br /><br />Setlist:<br />I-E-A-I-A-I-O <a href="#" onclick="yt.www.watch.player.seekTo(00*60+45);return false;">00:45</a><br />Suite-Pee <a href="#" onclick="yt.www.watch.player.seekTo(4*60+26);return false;">4:26</a>  (Incomplete)<br />Attack <a href="#" onclick="yt.www.watch.player.seekTo(5*60+31);return false;">5:31</a> (First live performance since 2011)<br />Prison Song <a href="#" onclick="yt.www.watch.player.seekTo(8*60+42);return false;">8:42</a><br />Know <a href="#" onclick="yt.www.watch.player.seekTo(12*60+32);return false;">12:32</a> (First live performance since 2011)<br />Aerials <a href="#" onclick="yt.www.watch.player.seekTo(15*60+32);return false;">15:32</a><br />Soldier Side - Intro <a href="#" onclick="yt.www.watch.player.seekTo(19*60+13);return false;">19:13</a><br />B.Y.O.B. <a href="#" onclick="yt.www.watch.player.seekTo(20*60+09);return false;">20:09</a><br />Soil <a href="#" onclick="yt.www.watch.player.seekTo(24*60+32);return false;">24:32</a><br />Darts <a href="#" onclick="yt.www.watch.player.seekTo(27*60+48);return false;">27:48</a><br />Radio/Video <a href="#" onclick="yt.www.watch.player.seekTo(30*60+38);return false;">30:38</a><br />Hypnotize <a href="#" onclick="yt.www.watch.player.seekTo(35*60+05);return false;">35:05</a><br />Temper <a href="#" onclick="yt.www.watch.player.seekTo(38*60+08);return false;">38:08</a> (First live performance since 1999)<br />CUBErt <a href="#" onclick="yt.www.watch.player.seekTo(41*60+00);return false;">41:00</a><br />Needles <a href="#" onclick="yt.www.watch.player.seekTo(42*60+57);return false;">42:57</a><br />Deer Dance <a href="#" onclick="yt.www.watch.player.seekTo(46*60+27);return false;">46:27</a><br />Bounce <a href="#" onclick="yt.www.watch.player.seekTo(49*60+38);return false;">49:38</a><br />Suggestions <a href="#" onclick="yt.www.watch.player.seekTo(51*60+25);return false;">51:25</a><br />Psycho <a href="#" onclick="yt.www.watch.player.seekTo(53*60+52);return false;">53:52</a><br />Chop Suey! <a href="#" onclick="yt.www.watch.player.seekTo(58*60+13);return false;">58:13</a><br />Lonely Day <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+01*60+15);return false;">1:01:15</a><br />Question! <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+04*60+14);return false;">1:04:14</a><br />Lost in Hollywood <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+08*60+10);return false;">1:08:10</a><br />Vicinity of Obscenity  <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+13*60+40);return false;">1:13:40</a>(First live performance since 2012)<br />Forest <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+16*60+17);return false;">1:16:17</a><br />Cigaro <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+20*60+02);return false;">1:20:02</a><br />Toxicity <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+23*60+57);return false;">1:23:57</a>(with Chino Moreno)<br />Sugar <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+27*60+53);return false;">1:27:53</a>',
+            5640,
+            [{
+                'start_time': 45,
+                'end_time': 266,
+                'title': 'I-E-A-I-A-I-O',
+            }, {
+                'start_time': 266,
+                'end_time': 331,
+                'title': 'Suite-Pee (Incomplete)',
+            }, {
+                'start_time': 331,
+                'end_time': 522,
+                'title': 'Attack (First live performance since 2011)',
+            }, {
+                'start_time': 522,
+                'end_time': 752,
+                'title': 'Prison Song',
+            }, {
+                'start_time': 752,
+                'end_time': 932,
+                'title': 'Know (First live performance since 2011)',
+            }, {
+                'start_time': 932,
+                'end_time': 1153,
+                'title': 'Aerials',
+            }, {
+                'start_time': 1153,
+                'end_time': 1209,
+                'title': 'Soldier Side - Intro',
+            }, {
+                'start_time': 1209,
+                'end_time': 1472,
+                'title': 'B.Y.O.B.',
+            }, {
+                'start_time': 1472,
+                'end_time': 1668,
+                'title': 'Soil',
+            }, {
+                'start_time': 1668,
+                'end_time': 1838,
+                'title': 'Darts',
+            }, {
+                'start_time': 1838,
+                'end_time': 2105,
+                'title': 'Radio/Video',
+            }, {
+                'start_time': 2105,
+                'end_time': 2288,
+                'title': 'Hypnotize',
+            }, {
+                'start_time': 2288,
+                'end_time': 2460,
+                'title': 'Temper (First live performance since 1999)',
+            }, {
+                'start_time': 2460,
+                'end_time': 2577,
+                'title': 'CUBErt',
+            }, {
+                'start_time': 2577,
+                'end_time': 2787,
+                'title': 'Needles',
+            }, {
+                'start_time': 2787,
+                'end_time': 2978,
+                'title': 'Deer Dance',
+            }, {
+                'start_time': 2978,
+                'end_time': 3085,
+                'title': 'Bounce',
+            }, {
+                'start_time': 3085,
+                'end_time': 3232,
+                'title': 'Suggestions',
+            }, {
+                'start_time': 3232,
+                'end_time': 3493,
+                'title': 'Psycho',
+            }, {
+                'start_time': 3493,
+                'end_time': 3675,
+                'title': 'Chop Suey!',
+            }, {
+                'start_time': 3675,
+                'end_time': 3854,
+                'title': 'Lonely Day',
+            }, {
+                'start_time': 3854,
+                'end_time': 4090,
+                'title': 'Question!',
+            }, {
+                'start_time': 4090,
+                'end_time': 4420,
+                'title': 'Lost in Hollywood',
+            }, {
+                'start_time': 4420,
+                'end_time': 4577,
+                'title': 'Vicinity of Obscenity (First live performance since 2012)',
+            }, {
+                'start_time': 4577,
+                'end_time': 4802,
+                'title': 'Forest',
+            }, {
+                'start_time': 4802,
+                'end_time': 5037,
+                'title': 'Cigaro',
+            }, {
+                'start_time': 5037,
+                'end_time': 5273,
+                'title': 'Toxicity (with Chino Moreno)',
+            }, {
+                'start_time': 5273,
+                'end_time': 5640,
+                'title': 'Sugar',
+            }]
+        ),
+        (
+            # https://www.youtube.com/watch?v=PkYLQbsqCE8
+            # pattern: <num> - <title> [<latinized title>] 0:00:00
+            '''Затемно (Zatemno) is an Obscure Black Metal Band from Russia.<br /><br />"Во прах (Vo prakh)'' Into The Ashes", Debut mini-album released may 6, 2016, by Death Knell Productions<br />Released on 6 panel digipak CD, limited to 100 copies only<br />And digital format on Bandcamp<br /><br />Tracklist<br /><br />1 - Во прах [Vo prakh] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+00*60+00);return false;">0:00:00</a><br />2 - Искупление [Iskupleniye] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+08*60+10);return false;">0:08:10</a><br />3 - Из серпов луны...[Iz serpov luny] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+14*60+30);return false;">0:14:30</a><br /><br />Links:<br /><a href="https://deathknellprod.bandcamp.com/album/--2" class="yt-uix-servicelink  " data-target-new-window="True" data-url="https://deathknellprod.bandcamp.com/album/--2" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://deathknellprod.bandcamp.com/a...</a><br /><a href="https://www.facebook.com/DeathKnellProd/" class="yt-uix-servicelink  " data-target-new-window="True" data-url="https://www.facebook.com/DeathKnellProd/" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://www.facebook.com/DeathKnellProd/</a><br /><br /><br />I don't have any right about this artifact, my only intention is to spread the music of the band, all rights are reserved to the Затемно (Zatemno) and his producers, Death Knell Productions.<br /><br />------------------------------------------------------------------<br /><br />Subscribe for more videos like this.<br />My link: <a href="https://web.facebook.com/AttackOfTheDragons" class="yt-uix-servicelink  " data-target-new-window="True" data-url="https://web.facebook.com/AttackOfTheDragons" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://web.facebook.com/AttackOfTheD...</a>''',
+            1138,
+            [{
+                'start_time': 0,
+                'end_time': 490,
+                'title': '1 - Во прах [Vo prakh]',
+            }, {
+                'start_time': 490,
+                'end_time': 870,
+                'title': '2 - Искупление [Iskupleniye]',
+            }, {
+                'start_time': 870,
+                'end_time': 1138,
+                'title': '3 - Из серпов луны...[Iz serpov luny]',
+            }]
+        ),
+    ]
+
+    def test_youtube_chapters(self):
+        for description, duration, expected_chapters in self._TEST_CASES:
+            ie = YoutubeIE()
+            expect_value(
+                self, ie._extract_chapters(description, duration),
+                expected_chapters, None)
+
+
+if __name__ == '__main__':
+    unittest.main()

youtube_dl/downloader/external.py

@@ -29,7 +29,17 @@ class ExternalFD(FileDownloader):
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)
 
-        retval = self._call_downloader(tmpfilename, info_dict)
+        try:
+            retval = self._call_downloader(tmpfilename, info_dict)
+        except KeyboardInterrupt:
+            if not info_dict.get('is_live'):
+                raise
+            # Live stream downloading cancellation should be considered as
+            # correct and expected termination thus all postprocessing
+            # should take place
+            retval = 0
+            self.to_screen('[%s] Interrupted by user' % self.get_basename())
+
         if retval == 0:
             fsize = os.path.getsize(encodeFilename(tmpfilename))
             self.to_screen('\r[%s] Downloaded %s bytes' % (self.get_basename(), fsize))

youtube_dl/downloader/fragment.py

@@ -49,7 +49,7 @@ class FragmentFD(FileDownloader):
                 index:  0-based index of current fragment among all fragments
             fragment_count:
                 Total count of fragments
-                
+
     This feature is experimental and file format may change in future.
     """
 
@@ -155,8 +155,6 @@ class FragmentFD(FileDownloader):
                 self._write_ytdl_file(ctx)
             if ctx['fragment_index'] > 0:
                 assert resume_len > 0
-            else:
-                assert resume_len == 0
 
         dest_stream, tmpfilename = sanitize_open(tmpfilename, open_mode)
 

youtube_dl/extractor/adobepass.py

@@ -1308,6 +1308,12 @@ class AdobePassIE(InfoExtractor):
     _USER_AGENT = 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0'
     _MVPD_CACHE = 'ap-mvpd'
 
+    def _download_webpage_handle(self, *args, **kwargs):
+        headers = kwargs.get('headers', {})
+        headers.update(self.geo_verification_headers())
+        kwargs['headers'] = headers
+        return super(AdobePassIE, self)._download_webpage_handle(*args, **kwargs)
+
     @staticmethod
     def _get_mvpd_resource(provider_id, title, guid, rating):
         channel = etree.Element('channel')

youtube_dl/extractor/aenetworks.py

@@ -101,10 +101,14 @@ class AENetworksIE(AENetworksBaseIE):
                 for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
                     entries.append(self.url_result(
                         compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
-                return self.playlist_result(
-                    entries, self._html_search_meta('aetn:SeriesId', webpage),
-                    self._html_search_meta('aetn:SeriesTitle', webpage))
-            elif url_parts_len == 2:
+                if entries:
+                    return self.playlist_result(
+                        entries, self._html_search_meta('aetn:SeriesId', webpage),
+                        self._html_search_meta('aetn:SeriesTitle', webpage))
+                else:
+                    # single season
+                    url_parts_len = 2
+            if url_parts_len == 2:
                 entries = []
                 for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
                     episode_attributes = extract_attributes(episode_item)
@@ -112,7 +116,7 @@ class AENetworksIE(AENetworksBaseIE):
                         url, episode_attributes['data-canonical'])
                     entries.append(self.url_result(
                         episode_url, 'AENetworks',
-                        episode_attributes['data-videoid']))
+                        episode_attributes.get('data-videoid') or episode_attributes.get('data-video-id')))
                 return self.playlist_result(
                     entries, self._html_search_meta('aetn:SeasonId', webpage))
 

youtube_dl/extractor/afreecatv.py

@@ -207,11 +207,10 @@ class AfreecaTVIE(InfoExtractor):
                     file_url, video_id, 'mp4', entry_protocol='m3u8_native',
                     m3u8_id='hls',
                     note='Downloading part %d m3u8 information' % file_num)
-                title = title if one else '%s (part %d)' % (title, file_num)
                 file_info = common_entry.copy()
                 file_info.update({
                     'id': format_id,
-                    'title': title,
+                    'title': title if one else '%s (part %d)' % (title, file_num),
                     'upload_date': upload_date,
                     'duration': file_duration,
                     'formats': formats,

youtube_dl/extractor/amp.py

@@ -34,9 +34,12 @@ class AMPIE(InfoExtractor):
             if isinstance(media_thumbnail, dict):
                 media_thumbnail = [media_thumbnail]
             for thumbnail_data in media_thumbnail:
-                thumbnail = thumbnail_data['@attributes']
+                thumbnail = thumbnail_data.get('@attributes', {})
+                thumbnail_url = thumbnail.get('url')
+                if not thumbnail_url:
+                    continue
                 thumbnails.append({
-                    'url': self._proto_relative_url(thumbnail['url'], 'http:'),
+                    'url': self._proto_relative_url(thumbnail_url, 'http:'),
                     'width': int_or_none(thumbnail.get('width')),
                     'height': int_or_none(thumbnail.get('height')),
                 })
@@ -47,9 +50,14 @@ class AMPIE(InfoExtractor):
             if isinstance(media_subtitle, dict):
                 media_subtitle = [media_subtitle]
             for subtitle_data in media_subtitle:
-                subtitle = subtitle_data['@attributes']
-                lang = subtitle.get('lang') or 'en'
-                subtitles[lang] = [{'url': subtitle['href']}]
+                subtitle = subtitle_data.get('@attributes', {})
+                subtitle_href = subtitle.get('href')
+                if not subtitle_href:
+                    continue
+                subtitles.setdefault(subtitle.get('lang') or 'en', []).append({
+                    'url': subtitle_href,
+                    'ext': mimetype2ext(subtitle.get('type')) or determine_ext(subtitle_href),
+                })
 
         formats = []
         media_content = get_media_node('content')

youtube_dl/extractor/anvato.py

@@ -5,6 +5,7 @@ import base64
 import hashlib
 import json
 import random
+import re
 import time
 
 from .common import InfoExtractor
@@ -16,6 +17,7 @@ from ..utils import (
     intlist_to_bytes,
     int_or_none,
     strip_jsonp,
+    unescapeHTML,
 )
 
 
@@ -26,6 +28,8 @@ def md5_text(s):
 
 
 class AnvatoIE(InfoExtractor):
+    _VALID_URL = r'anvato:(?P<access_key_or_mcp>[^:]+):(?P<id>\d+)'
+
     # Copied from anvplayer.min.js
     _ANVACK_TABLE = {
         'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ',
@@ -114,6 +118,22 @@ class AnvatoIE(InfoExtractor):
         'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6_secure': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ'
     }
 
+    _MCP_TO_ACCESS_KEY_TABLE = {
+        'qa': 'anvato_mcpqa_demo_web_stage_18b55e00db5a13faa8d03ae6e41f6f5bcb15b922',
+        'lin': 'anvato_mcp_lin_web_prod_4c36fbfd4d8d8ecae6488656e21ac6d1ac972749',
+        'univison': 'anvato_mcp_univision_web_prod_37fe34850c99a3b5cdb71dab10a417dd5cdecafa',
+        'uni': 'anvato_mcp_univision_web_prod_37fe34850c99a3b5cdb71dab10a417dd5cdecafa',
+        'dev': 'anvato_mcp_fs2go_web_prod_c7b90a93e171469cdca00a931211a2f556370d0a',
+        'sps': 'anvato_mcp_sps_web_prod_54bdc90dd6ba21710e9f7074338365bba28da336',
+        'spsstg': 'anvato_mcp_sps_web_prod_54bdc90dd6ba21710e9f7074338365bba28da336',
+        'anv': 'anvato_mcp_anv_web_prod_791407490f4c1ef2a4bcb21103e0cb1bcb3352b3',
+        'gray': 'anvato_mcp_gray_web_prod_4c10f067c393ed8fc453d3930f8ab2b159973900',
+        'hearst': 'anvato_mcp_hearst_web_prod_5356c3de0fc7c90a3727b4863ca7fec3a4524a99',
+        'cbs': 'anvato_mcp_cbs_web_prod_02f26581ff80e5bda7aad28226a8d369037f2cbe',
+        'telemundo': 'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582'
+    }
+
+    _ANVP_RE = r'<script[^>]+\bdata-anvp\s*=\s*(["\'])(?P<anvp>(?:(?!\1).)+)\1'
     _AUTH_KEY = b'\x31\xc2\x42\x84\x9e\x73\xa0\xce'
 
     def __init__(self, *args, **kwargs):
@@ -178,12 +198,7 @@ class AnvatoIE(InfoExtractor):
             }
 
             if ext == 'm3u8' or media_format in ('m3u8', 'm3u8-variant'):
-                # Not using _extract_m3u8_formats here as individual media
-                # playlists are also included in published_urls.
-                if tbr is None:
-                    formats.append(self._m3u8_meta_format(video_url, ext='mp4', m3u8_id='hls'))
-                    continue
-                else:
+                if tbr is not None:
                     a_format.update({
                         'format_id': '-'.join(filter(None, ['hls', compat_str(tbr)])),
                         'ext': 'mp4',
@@ -222,9 +237,42 @@ class AnvatoIE(InfoExtractor):
             'subtitles': subtitles,
         }
 
+    @staticmethod
+    def _extract_urls(ie, webpage, video_id):
+        entries = []
+        for mobj in re.finditer(AnvatoIE._ANVP_RE, webpage):
+            anvplayer_data = ie._parse_json(
+                mobj.group('anvp'), video_id, transform_source=unescapeHTML,
+                fatal=False)
+            if not anvplayer_data:
+                continue
+            video = anvplayer_data.get('video')
+            if not isinstance(video, compat_str) or not video.isdigit():
+                continue
+            access_key = anvplayer_data.get('accessKey')
+            if not access_key:
+                mcp = anvplayer_data.get('mcp')
+                if mcp:
+                    access_key = AnvatoIE._MCP_TO_ACCESS_KEY_TABLE.get(
+                        mcp.lower())
+            if not access_key:
+                continue
+            entries.append(ie.url_result(
+                'anvato:%s:%s' % (access_key, video), ie=AnvatoIE.ie_key(),
+                video_id=video))
+        return entries
+
     def _extract_anvato_videos(self, webpage, video_id):
-        anvplayer_data = self._parse_json(self._html_search_regex(
-            r'<script[^>]+data-anvp=\'([^\']+)\'', webpage,
-            'Anvato player data'), video_id)
+        anvplayer_data = self._parse_json(
+            self._html_search_regex(
+                self._ANVP_RE, webpage, 'Anvato player data', group='anvp'),
+            video_id)
         return self._get_anvato_videos(
             anvplayer_data['accessKey'], anvplayer_data['video'])
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        access_key, video_id = mobj.group('access_key_or_mcp', 'id')
+        if access_key not in self._ANVACK_TABLE:
+            access_key = self._MCP_TO_ACCESS_KEY_TABLE[access_key]
+        return self._get_anvato_videos(access_key, video_id)

youtube_dl/extractor/appleconnect.py

@@ -12,13 +12,13 @@ class AppleConnectIE(InfoExtractor):
     _VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/idsa\.(?P<id>[\w-]+)'
     _TEST = {
         'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
-        'md5': '10d0f2799111df4cb1c924520ca78f98',
+        'md5': 'e7c38568a01ea45402570e6029206723',
         'info_dict': {
             'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
             'ext': 'm4v',
             'title': 'Energy',
             'uploader': 'Drake',
-            'thumbnail': 'http://is5.mzstatic.com/image/thumb/Video5/v4/78/61/c5/7861c5fa-ad6d-294b-1464-cf7605b911d6/source/1920x1080sr.jpg',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'upload_date': '20150710',
             'timestamp': 1436545535,
         },

youtube_dl/extractor/appletrailers.py

@@ -70,7 +70,8 @@ class AppleTrailersIE(InfoExtractor):
     }, {
         'url': 'http://trailers.apple.com/trailers/magnolia/blackthorn/',
         'info_dict': {
-            'id': 'blackthorn',
+            'id': '4489',
+            'title': 'Blackthorn',
         },
         'playlist_mincount': 2,
         'expected_warnings': ['Unable to download JSON metadata'],
@@ -261,7 +262,7 @@ class AppleTrailersSectionIE(InfoExtractor):
             'title': 'Most Popular',
             'id': 'mostpopular',
         },
-        'playlist_mincount': 80,
+        'playlist_mincount': 30,
     }, {
         'url': 'http://trailers.apple.com/#section=moviestudios',
         'info_dict': {

youtube_dl/extractor/archiveorg.py

@@ -24,12 +24,12 @@ class ArchiveOrgIE(InfoExtractor):
         }
     }, {
         'url': 'https://archive.org/details/Cops1922',
-        'md5': 'bc73c8ab3838b5a8fc6c6651fa7b58ba',
+        'md5': '0869000b4ce265e8ca62738b336b268a',
         'info_dict': {
             'id': 'Cops1922',
             'ext': 'mp4',
             'title': 'Buster Keaton\'s "Cops" (1922)',
-            'description': 'md5:b4544662605877edd99df22f9620d858',
+            'description': 'md5:89e7c77bf5d965dd5c0372cfb49470f6',
         }
     }, {
         'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',

youtube_dl/extractor/arte.py

@@ -180,7 +180,7 @@ class ArteTVBaseIE(InfoExtractor):
 
 class ArteTVPlus7IE(ArteTVBaseIE):
     IE_NAME = 'arte.tv:+7'
-    _VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/[^/]+/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/(?:[^/]+/)?(?P<lang>fr|de|en|es)/(?:videos/)?(?:[^/]+/)*(?P<id>[^/?#&]+)'
 
     _TESTS = [{
         'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D',
@@ -188,6 +188,9 @@ class ArteTVPlus7IE(ArteTVBaseIE):
     }, {
         'url': 'http://sites.arte.tv/karambolage/de/video/karambolage-22',
         'only_matching': True,
+    }, {
+        'url': 'http://www.arte.tv/de/videos/048696-000-A/der-kluge-bauch-unser-zweites-gehirn',
+        'only_matching': True,
     }]
 
     @classmethod

youtube_dl/extractor/atresplayer.py

@@ -36,7 +36,7 @@ class AtresPlayerIE(InfoExtractor):
         },
         {
             'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html',
-            'md5': '0d0e918533bbd4b263f2de4d197d4aac',
+            'md5': '6e52cbb513c405e403dbacb7aacf8747',
             'info_dict': {
                 'id': 'capitulo-112-david-bustamante',
                 'ext': 'flv',

youtube_dl/extractor/audioboom.py

@@ -16,7 +16,7 @@ class AudioBoomIE(InfoExtractor):
             'title': '3/09/2016 Czaban Hour 3',
             'description': 'Guest:   Nate Davis - NFL free agency,   Guest:   Stan Gans',
             'duration': 2245.72,
-            'uploader': 'Steve Czaban',
+            'uploader': 'SB Nation A.M.',
             'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio',
         }
     }, {

youtube_dl/extractor/bandcamp.py

@@ -34,12 +34,12 @@ class BandcampIE(InfoExtractor):
         '_skip': 'There is a limit of 200 free downloads / month for the test song'
     }, {
         'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
-        'md5': '73d0b3171568232574e45652f8720b5c',
+        'md5': '0369ace6b939f0927e62c67a1a8d9fa7',
         'info_dict': {
             'id': '2650410135',
-            'ext': 'mp3',
-            'title': 'Lanius (Battle)',
-            'uploader': 'Ben Prunty Music',
+            'ext': 'aiff',
+            'title': 'Ben Prunty - Lanius (Battle)',
+            'uploader': 'Ben Prunty',
         },
     }]
 
@@ -47,6 +47,7 @@ class BandcampIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         title = mobj.group('title')
         webpage = self._download_webpage(url, title)
+        thumbnail = self._html_search_meta('og:image', webpage, default=None)
         m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
         if not m_download:
             m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
@@ -75,6 +76,7 @@ class BandcampIE(InfoExtractor):
                 return {
                     'id': track_id,
                     'title': data['title'],
+                    'thumbnail': thumbnail,
                     'formats': formats,
                     'duration': float_or_none(data.get('duration')),
                 }
@@ -143,7 +145,7 @@ class BandcampIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
-            'thumbnail': info.get('thumb_url'),
+            'thumbnail': info.get('thumb_url') or thumbnail,
             'uploader': info.get('artist'),
             'artist': artist,
             'track': track,

youtube_dl/extractor/beeg.py

@@ -16,7 +16,7 @@ class BeegIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
     _TEST = {
         'url': 'http://beeg.com/5416503',
-        'md5': '46c384def73b33dbc581262e5ee67cef',
+        'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820',
         'info_dict': {
             'id': '5416503',
             'ext': 'mp4',

youtube_dl/extractor/bilibili.py

@@ -122,6 +122,11 @@ class BiliBiliIE(InfoExtractor):
                     'preference': -2 if 'hd.mp4' in backup_url else -3,
                 })
 
+            for a_format in formats:
+                a_format.setdefault('http_headers', {}).update({
+                    'Referer': url,
+                })
+
             self._sort_formats(formats)
 
             entries.append({

youtube_dl/extractor/bleacherreport.py

@@ -35,7 +35,7 @@ class BleacherReportIE(InfoExtractor):
             'title': 'Aussie Golfers Get Fright of Their Lives After Being Chased by Angry Kangaroo',
             'timestamp': 1446839961,
             'uploader': 'Sean Fay',
-            'description': 'md5:825e94e0f3521df52fa83b2ed198fa20',
+            'description': 'md5:b1601e2314c4d8eec23b6eafe086a757',
             'uploader_id': 6466954,
             'upload_date': '20151011',
         },
@@ -90,17 +90,13 @@ class BleacherReportCMSIE(AMPIE):
     _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36})'
     _TESTS = [{
         'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
-        'md5': '8c2c12e3af7805152675446c905d159b',
+        'md5': '2e4b0a997f9228ffa31fada5c53d1ed1',
         'info_dict': {
             'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
-            'ext': 'mp4',
+            'ext': 'flv',
             'title': 'Cena vs. Rollins Would Expose the Heavyweight Division',
             'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e',
         },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/br.py

@@ -77,7 +77,7 @@ class BRIE(InfoExtractor):
                 'description': 'md5:bb659990e9e59905c3d41e369db1fbe3',
                 'duration': 893,
                 'uploader': 'Eva Maria Steimle',
-                'upload_date': '20140117',
+                'upload_date': '20170208',
             }
         },
     ]

youtube_dl/extractor/brightcove.py

@@ -522,7 +522,7 @@ class BrightcoveNewIE(InfoExtractor):
         # [2] looks like:
         for video, script_tag, account_id, player_id, embed in re.findall(
                 r'''(?isx)
-                    (<video\s+[^>]*data-video-id=['"]?[^>]+>)
+                    (<video\s+[^>]*\bdata-video-id\s*=\s*['"]?[^>]+>)
                     (?:.*?
                         (<script[^>]+
                             src=["\'](?:https?:)?//players\.brightcove\.net/

youtube_dl/extractor/canalc2.py

@@ -16,13 +16,10 @@ class Canalc2IE(InfoExtractor):
         'md5': '060158428b650f896c542dfbb3d6487f',
         'info_dict': {
             'id': '12163',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Terrasses du Numérique',
             'duration': 122,
         },
-        'params': {
-            'skip_download': True,  # Requires rtmpdump
-        }
     }, {
         'url': 'http://archives-canalc2.u-strasbg.fr/video.asp?idVideo=11427&voir=oui',
         'only_matching': True,

youtube_dl/extractor/cbc.py

@@ -96,6 +96,7 @@ class CBCIE(InfoExtractor):
         'info_dict': {
             'title': 'Keep Rover active during the deep freeze with doggie pushups and other fun indoor tasks',
             'id': 'dog-indoor-exercise-winter-1.3928238',
+            'description': 'md5:c18552e41726ee95bd75210d1ca9194c',
         },
         'playlist_mincount': 6,
     }]
@@ -165,12 +166,11 @@ class CBCPlayerIE(InfoExtractor):
             'uploader': 'CBCC-NEW',
         },
     }, {
-        # available only when we add `formats=MPEG4,FLV,MP3` to theplatform url
         'url': 'http://www.cbc.ca/player/play/2164402062',
-        'md5': '17a61eb813539abea40618d6323a7f82',
+        'md5': '33fcd8f6719b9dd60a5e73adcb83b9f6',
         'info_dict': {
             'id': '2164402062',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Cancer survivor four times over',
             'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.',
             'timestamp': 1320410746,

youtube_dl/extractor/cbslocal.py

@@ -60,8 +60,8 @@ class CBSLocalIE(AnvatoIE):
             'title': 'A Very Blue Anniversary',
             'description': 'CBS2’s Cindy Hsu has more.',
             'thumbnail': 're:^https?://.*',
-            'timestamp': 1479962220,
-            'upload_date': '20161124',
+            'timestamp': int,
+            'upload_date': r're:^\d{8}$',
             'uploader': 'CBS',
             'subtitles': {
                 'en': 'mincount:5',

youtube_dl/extractor/cda.py

@@ -9,7 +9,10 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     int_or_none,
+    multipart_encode,
     parse_duration,
+    random_birthday,
+    urljoin,
 )
 
 
@@ -27,7 +30,8 @@ class CDAIE(InfoExtractor):
             'description': 'md5:269ccd135d550da90d1662651fcb9772',
             'thumbnail': r're:^https?://.*\.jpg$',
             'average_rating': float,
-            'duration': 39
+            'duration': 39,
+            'age_limit': 0,
         }
     }, {
         'url': 'http://www.cda.pl/video/57413289',
@@ -41,13 +45,41 @@ class CDAIE(InfoExtractor):
             'uploader': 'crash404',
             'view_count': int,
             'average_rating': float,
-            'duration': 137
+            'duration': 137,
+            'age_limit': 0,
         }
+    }, {
+        # Age-restricted
+        'url': 'http://www.cda.pl/video/1273454c4',
+        'info_dict': {
+            'id': '1273454c4',
+            'ext': 'mp4',
+            'title': 'Bronson (2008) napisy HD 1080p',
+            'description': 'md5:1b6cb18508daf2dc4e0fa4db77fec24c',
+            'height': 1080,
+            'uploader': 'boniek61',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 5554,
+            'age_limit': 18,
+            'view_count': int,
+            'average_rating': float,
+        },
     }, {
         'url': 'http://ebd.cda.pl/0x0/5749950c',
         'only_matching': True,
     }]
 
+    def _download_age_confirm_page(self, url, video_id, *args, **kwargs):
+        form_data = random_birthday('rok', 'miesiac', 'dzien')
+        form_data.update({'return': url, 'module': 'video', 'module_id': video_id})
+        data, content_type = multipart_encode(form_data)
+        return self._download_webpage(
+            urljoin(url, '/a/validatebirth'), video_id, *args,
+            data=data, headers={
+                'Referer': url,
+                'Content-Type': content_type,
+            }, **kwargs)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         self._set_cookie('cda.pl', 'cda.player', 'html5')
@@ -57,6 +89,13 @@ class CDAIE(InfoExtractor):
         if 'Ten film jest dostępny dla użytkowników premium' in webpage:
             raise ExtractorError('This video is only available for premium users.', expected=True)
 
+        need_confirm_age = False
+        if self._html_search_regex(r'(<form[^>]+action="/a/validatebirth")',
+                                   webpage, 'birthday validate form', default=None):
+            webpage = self._download_age_confirm_page(
+                url, video_id, note='Confirming age')
+            need_confirm_age = True
+
         formats = []
 
         uploader = self._search_regex(r'''(?x)
@@ -81,6 +120,7 @@ class CDAIE(InfoExtractor):
             'thumbnail': self._og_search_thumbnail(webpage),
             'formats': formats,
             'duration': None,
+            'age_limit': 18 if need_confirm_age else 0,
         }
 
         def extract_format(page, version):
@@ -121,7 +161,12 @@ class CDAIE(InfoExtractor):
         for href, resolution in re.findall(
                 r'<a[^>]+data-quality="[^"]+"[^>]+href="([^"]+)"[^>]+class="quality-btn"[^>]*>([0-9]+p)',
                 webpage):
-            webpage = self._download_webpage(
+            if need_confirm_age:
+                handler = self._download_age_confirm_page
+            else:
+                handler = self._download_webpage
+
+            webpage = handler(
                 self._BASE_URL + href, video_id,
                 'Downloading %s version information' % resolution, fatal=False)
             if not webpage:
@@ -129,6 +174,7 @@ class CDAIE(InfoExtractor):
                 # invalid version is requested.
                 self.report_warning('Unable to download %s version information' % resolution)
                 continue
+
             extract_format(webpage, resolution)
 
         self._sort_formats(formats)

youtube_dl/extractor/clipfish.py

@@ -12,7 +12,7 @@ class ClipfishIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?clipfish\.de/(?:[^/]+/)+video/(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.clipfish.de/special/ugly-americans/video/4343170/s01-e01-ugly-americans-date-in-der-hoelle/',
-        'md5': '720563e467b86374c194bdead08d207d',
+        'md5': 'b9a5dc46294154c1193e2d10e0c95693',
         'info_dict': {
             'id': '4343170',
             'ext': 'mp4',

youtube_dl/extractor/collegerama.py

@@ -21,7 +21,7 @@ class CollegeRamaIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Een nieuwe wereld: waarden, bewustzijn en techniek van de mensheid 2.0.',
                 'description': '',
-                'thumbnail': r're:^https?://.*\.jpg$',
+                'thumbnail': r're:^https?://.*\.jpg(?:\?.*?)?$',
                 'duration': 7713.088,
                 'timestamp': 1413309600,
                 'upload_date': '20141014',
@@ -35,6 +35,7 @@ class CollegeRamaIE(InfoExtractor):
                 'ext': 'wmv',
                 'title': '64ste Vakantiecursus: Afvalwater',
                 'description': 'md5:7fd774865cc69d972f542b157c328305',
+                'thumbnail': r're:^https?://.*\.jpg(?:\?.*?)?$',
                 'duration': 10853,
                 'timestamp': 1326446400,
                 'upload_date': '20120113',

youtube_dl/extractor/common.py

@@ -245,6 +245,10 @@ class InfoExtractor(object):
                     specified in the URL.
     end_time:       Time in seconds where the reproduction should end, as
                     specified in the URL.
+    chapters:       A list of dictionaries, with the following entries:
+                        * "start_time" - The start time of the chapter in seconds
+                        * "end_time" - The end time of the chapter in seconds
+                        * "title" (optional, string)
 
     The following fields should only be used when the video belongs to some logical
     chapter or section:
@@ -990,6 +994,7 @@ class InfoExtractor(object):
                 'tbr': int_or_none(e.get('bitrate')),
                 'width': int_or_none(e.get('width')),
                 'height': int_or_none(e.get('height')),
+                'view_count': int_or_none(e.get('interactionCount')),
             })
 
         for e in json_ld:
@@ -1334,7 +1339,7 @@ class InfoExtractor(object):
         if '#EXT-X-FAXS-CM:' in m3u8_doc:  # Adobe Flash Access
             return []
 
-        formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)]
+        formats = []
 
         format_url = lambda u: (
             u
@@ -1386,6 +1391,7 @@ class InfoExtractor(object):
                 f = {
                     'format_id': '-'.join(format_id),
                     'url': format_url(media_url),
+                    'manifest_url': m3u8_url,
                     'language': media.get('LANGUAGE'),
                     'ext': ext,
                     'protocol': entry_protocol,
@@ -1438,7 +1444,7 @@ class InfoExtractor(object):
                 f = {
                     'format_id': '-'.join(format_id),
                     'url': manifest_url,
-                    'manifest_url': manifest_url,
+                    'manifest_url': m3u8_url,
                     'tbr': tbr,
                     'ext': ext,
                     'fps': float_or_none(last_stream_inf.get('FRAME-RATE')),
@@ -2168,7 +2174,7 @@ class InfoExtractor(object):
     def _extract_akamai_formats(self, manifest_url, video_id, hosts={}):
         formats = []
         hdcore_sign = 'hdcore=3.7.0'
-        f4m_url = re.sub(r'(https?://[^/+])/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
+        f4m_url = re.sub(r'(https?://[^/]+)/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
         hds_host = hosts.get('hds')
         if hds_host:
             f4m_url = re.sub(r'(https?://)[^/]+', r'\1' + hds_host, f4m_url)

youtube_dl/extractor/coub.py

@@ -24,12 +24,11 @@ class CoubIE(InfoExtractor):
             'duration': 4.6,
             'timestamp': 1428527772,
             'upload_date': '20150408',
-            'uploader': 'Артём Лоскутников',
+            'uploader': 'Artyom Loskutnikov',
             'uploader_id': 'artyom.loskutnikov',
             'view_count': int,
             'like_count': int,
             'repost_count': int,
-            'comment_count': int,
             'age_limit': 0,
         },
     }, {
@@ -118,7 +117,6 @@ class CoubIE(InfoExtractor):
         view_count = int_or_none(coub.get('views_count') or coub.get('views_increase_count'))
         like_count = int_or_none(coub.get('likes_count'))
         repost_count = int_or_none(coub.get('recoubs_count'))
-        comment_count = int_or_none(coub.get('comments_count'))
 
         age_restricted = coub.get('age_restricted', coub.get('age_restricted_by_admin'))
         if age_restricted is not None:
@@ -137,7 +135,6 @@ class CoubIE(InfoExtractor):
             'view_count': view_count,
             'like_count': like_count,
             'repost_count': repost_count,
-            'comment_count': comment_count,
             'age_limit': age_limit,
             'formats': formats,
         }

youtube_dl/extractor/crackle.py

@@ -21,9 +21,10 @@ class CrackleIE(InfoExtractor):
             'season_number': 8,
             'episode_number': 4,
             'subtitles': {
-                'en-US': [{
-                    'ext': 'ttml',
-                }]
+                'en-US': [
+                    {'ext': 'vtt'},
+                    {'ext': 'tt'},
+                ]
             },
         },
         'params': {

youtube_dl/extractor/crunchyroll.py

@@ -171,7 +171,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
         'info_dict': {
             'id': '727589',
             'ext': 'mp4',
-            'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance from this Judicial Injustice!",
+            'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance From This Judicial Injustice!",
             'description': 'md5:cbcf05e528124b0f3a0a419fc805ea7d',
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'Kadokawa Pictures Inc.',
@@ -179,7 +179,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
             'series': "KONOSUBA -God's blessing on this wonderful world!",
             'season': "KONOSUBA -God's blessing on this wonderful world! 2",
             'season_number': 2,
-            'episode': 'Give Me Deliverance from this Judicial Injustice!',
+            'episode': 'Give Me Deliverance From This Judicial Injustice!',
             'episode_number': 1,
         },
         'params': {

youtube_dl/extractor/dailymotion.py

@@ -50,6 +50,24 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
     ]
 
     _TESTS = [
+        {
+            'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news',
+            'md5': '074b95bdee76b9e3654137aee9c79dfe',
+            'info_dict': {
+                'id': 'x5kesuj',
+                'ext': 'mp4',
+                'title': 'Office Christmas Party Review –  Jason Bateman, Olivia Munn, T.J. Miller',
+                'description': 'Office Christmas Party Review -  Jason Bateman, Olivia Munn, T.J. Miller',
+                'thumbnail': r're:^https?:.*\.(?:jpg|png)$',
+                'duration': 187,
+                'timestamp': 1493651285,
+                'upload_date': '20170501',
+                'uploader': 'Deadline',
+                'uploader_id': 'x1xm8ri',
+                'age_limit': 0,
+                'view_count': int,
+            },
+        },
         {
             'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
             'md5': '2137c41a8e78554bb09225b8eb322406',
@@ -66,7 +84,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                 'uploader_id': 'xijv66',
                 'age_limit': 0,
                 'view_count': int,
-            }
+            },
+            'skip': 'video gone',
         },
         # Vevo video
         {

youtube_dl/extractor/democracynow.py

@@ -21,7 +21,8 @@ class DemocracynowIE(InfoExtractor):
         'info_dict': {
             'id': '2015-0703-001',
             'ext': 'mp4',
-            'title': 'Daily Show',
+            'title': 'Daily Show for July 03, 2015',
+            'description': 'md5:80eb927244d6749900de6072c7cc2c86',
         },
     }, {
         'url': 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree',

youtube_dl/extractor/dotsub.py

@@ -35,7 +35,7 @@ class DotsubIE(InfoExtractor):
             'thumbnail': 're:^https?://dotsub.com/media/747bcf58-bd59-45b7-8c8c-ac312d084ee6/p',
             'duration': 290,
             'timestamp': 1476767794.2809999,
-            'upload_date': '20160525',
+            'upload_date': '20161018',
             'uploader': 'parthivi001',
             'uploader_id': 'user52596202',
             'view_count': int,

youtube_dl/extractor/douyutv.py

@@ -20,7 +20,7 @@ class DouyuTVIE(InfoExtractor):
             'id': '17732',
             'display_id': 'iseven',
             'ext': 'flv',
-            'title': 're:^清晨醒脑！T-ARA根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'title': 're:^清晨醒脑！根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
             'description': r're:.*m7show@163\.com.*',
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': '7师傅',
@@ -51,7 +51,7 @@ class DouyuTVIE(InfoExtractor):
             'id': '17732',
             'display_id': '17732',
             'ext': 'flv',
-            'title': 're:^清晨醒脑！T-ARA根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'title': 're:^清晨醒脑！根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
             'description': r're:.*m7show@163\.com.*',
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': '7师傅',

youtube_dl/extractor/extractors.py

@@ -41,6 +41,7 @@ from .alphaporno import AlphaPornoIE
 from .amcnetworks import AMCNetworksIE
 from .animeondemand import AnimeOnDemandIE
 from .anitube import AnitubeIE
+from .anvato import AnvatoIE
 from .anysex import AnySexIE
 from .aol import AolIE
 from .allocine import AllocineIE
@@ -662,6 +663,7 @@ from .nintendo import NintendoIE
 from .njpwworld import NJPWWorldIE
 from .nobelprize import NobelPrizeIE
 from .noco import NocoIE
+from .noovo import NoovoIE
 from .normalboots import NormalbootsIE
 from .nosvideo import NosVideoIE
 from .nova import NovaIE
@@ -1123,6 +1125,7 @@ from .vgtv import (
 from .vh1 import VH1IE
 from .vice import (
     ViceIE,
+    ViceArticleIE,
     ViceShowIE,
 )
 from .viceland import VicelandIE
@@ -1298,5 +1301,6 @@ from .youtube import (
     YoutubeWatchLaterIE,
 )
 from .zapiks import ZapiksIE
+from .zaq1 import Zaq1IE
 from .zdf import ZDFIE, ZDFChannelIE
 from .zingmp3 import ZingMp3IE

youtube_dl/extractor/foxsports.py

@@ -11,10 +11,10 @@ class FoxSportsIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?foxsports\.com/(?:[^/]+/)*(?P<id>[^/]+)'
 
     _TEST = {
-        'url': 'http://www.foxsports.com/video?vid=432609859715',
+        'url': 'http://www.foxsports.com/tennessee/video/432609859715',
         'md5': 'b49050e955bebe32c301972e4012ac17',
         'info_dict': {
-            'id': 'i0qKWsk3qJaM',
+            'id': 'bwduI3X_TgUB',
             'ext': 'mp4',
             'title': 'Courtney Lee on going up 2-0 in series vs. Blazers',
             'description': 'Courtney Lee talks about Memphis being focused.',
@@ -31,8 +31,9 @@ class FoxSportsIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         config = self._parse_json(
-            self._search_regex(
-                r"data-player-config='([^']+)'", webpage, 'data player config'),
+            self._html_search_regex(
+                r"""class="[^"]*(?:fs-player|platformPlayer-wrapper)[^"]*".+?data-player-config='([^']+)'""",
+                webpage, 'data player config'),
             video_id)
 
         return self.url_result(smuggle_url(update_url_query(

youtube_dl/extractor/funnyordie.py

@@ -58,8 +58,7 @@ class FunnyOrDieIE(InfoExtractor):
             m3u8_url, video_id, 'mp4', 'm3u8_native',
             m3u8_id='hls', fatal=False)
         source_formats = list(filter(
-            lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
-            m3u8_formats))
+            lambda f: f.get('vcodec') != 'none', m3u8_formats))
 
         bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)(?=[,/])', m3u8_url)]
         bitrates.sort()

youtube_dl/extractor/gamespot.py

@@ -78,8 +78,7 @@ class GameSpotIE(OnceIE):
                     if m3u8_formats:
                         self._sort_formats(m3u8_formats)
                         m3u8_formats = list(filter(
-                            lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
-                            m3u8_formats))
+                            lambda f: f.get('vcodec') != 'none', m3u8_formats))
                     if len(qualities) == len(m3u8_formats):
                         for q, m3u8_format in zip(qualities, m3u8_formats):
                             f = m3u8_format.copy()

youtube_dl/extractor/gdcvault.py

@@ -75,6 +75,19 @@ class GDCVaultIE(InfoExtractor):
                 'format': 'jp',  # The japanese audio
             }
         },
+        {
+            # gdc-player.html
+            'url': 'http://www.gdcvault.com/play/1435/An-American-engine-in-Tokyo',
+            'info_dict': {
+                'id': '1435',
+                'display_id': 'An-American-engine-in-Tokyo',
+                'ext': 'flv',
+                'title': 'An American Engine in Tokyo:/nThe collaboration of Epic Games and Square Enix/nFor THE LAST REMINANT',
+            },
+            'params': {
+                'skip_download': True,  # Requires rtmpdump
+            },
+        },
     ]
 
     def _login(self, webpage_url, display_id):
@@ -128,7 +141,7 @@ class GDCVaultIE(InfoExtractor):
                 'title': title,
             }
 
-        PLAYER_REGEX = r'<iframe src="(?P<xml_root>.+?)/player.*?\.html.*?".*?</iframe>'
+        PLAYER_REGEX = r'<iframe src="(?P<xml_root>.+?)/(?:gdc-)?player.*?\.html.*?".*?</iframe>'
 
         xml_root = self._html_search_regex(
             PLAYER_REGEX, start_page, 'xml root', default=None)

youtube_dl/extractor/generic.py

@@ -86,6 +86,8 @@ from .openload import OpenloadIE
 from .videopress import VideoPressIE
 from .rutube import RutubeIE
 from .limelight import LimelightBaseIE
+from .anvato import AnvatoIE
+from .washingtonpost import WashingtonPostIE
 
 
 class GenericIE(InfoExtractor):
@@ -1427,6 +1429,22 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            # Brightcove embed with whitespace around attribute names
+            'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
+            'info_dict': {
+                'id': '3167554373001',
+                'ext': 'mp4',
+                'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
+                'description': 'md5:57bacb0e0f29349de4972bfda3191713',
+                'uploader_id': '1079349493',
+                'upload_date': '20140207',
+                'timestamp': 1391810548,
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
         # Another form of arte.tv embed
         {
             'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
@@ -1677,6 +1695,29 @@ class GenericIE(InfoExtractor):
             },
             'playlist_mincount': 5,
         },
+        {
+            'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
+            'info_dict': {
+                'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
+                'title': 'Standoff with Walnut Creek murder suspect ends',
+                'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
+            },
+            'playlist_mincount': 4,
+        },
+        {
+            # WashingtonPost embed
+            'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
+            'info_dict': {
+                'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
+                'ext': 'mp4',
+                'title': "No one has seen the drama series based on Trump's life \u2014 until now",
+                'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
+                'timestamp': 1455216756,
+                'uploader': 'The Washington Post',
+                'upload_date': '20160211',
+            },
+            'add_ie': [WashingtonPostIE.ie_key()],
+        },
         # {
         #     # TODO: find another test
         #     # http://schema.org/VideoObject
@@ -2537,6 +2578,12 @@ class GenericIE(InfoExtractor):
                 'limelight:media:%s' % mobj.group('id'),
                 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
 
+        # Look for Anvato embeds
+        anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
+        if anvato_urls:
+            return self.playlist_result(
+                anvato_urls, video_id, video_title, video_description)
+
         # Look for AdobeTVVideo embeds
         mobj = re.search(
             r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
@@ -2654,6 +2701,12 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 rutube_urls, ie=RutubeIE.ie_key())
 
+        # Look for WashingtonPost embeds
+        wapo_urls = WashingtonPostIE._extract_urls(webpage)
+        if wapo_urls:
+            return self.playlist_from_matches(
+                wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
+
         # Looking for http://schema.org/VideoObject
         json_ld = self._search_json_ld(
             webpage, video_id, default={}, expected_type='VideoObject')

youtube_dl/extractor/go.py

@@ -36,22 +36,26 @@ class GoIE(AdobePassIE):
             'requestor_id': 'DisneyXD',
         }
     }
-    _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys())
+    _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys())
     _TESTS = [{
-        'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx',
+        'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
         'info_dict': {
-            'id': '0_g86w5onx',
+            'id': 'VDKA3807643',
             'ext': 'mp4',
-            'title': 'Sneak Peek: Language Arts',
-            'description': 'md5:7dcdab3b2d17e5217c953256af964e9c',
+            'title': 'The Traitor in the White House',
+            'description': 'md5:05b009d2d145a1e85d25111bd37222e8',
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         },
     }, {
-        'url': 'http://abc.go.com/shows/after-paradise/video/most-recent/vdka3335601',
-        'only_matching': True,
+        'url': 'http://watchdisneyxd.go.com/doraemon',
+        'info_dict': {
+            'title': 'Doraemon',
+            'id': 'SH55574025',
+        },
+        'playlist_mincount': 51,
     }, {
         'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
         'only_matching': True,
@@ -60,19 +64,36 @@ class GoIE(AdobePassIE):
         'only_matching': True,
     }]
 
+    def _extract_videos(self, brand, video_id='-1', show_id='-1'):
+        display_id = video_id if video_id != '-1' else show_id
+        return self._download_json(
+            'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/%s/-1/%s/-1/-1.json' % (brand, show_id, video_id),
+            display_id)['video']
+
     def _real_extract(self, url):
         sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
+        site_info = self._SITE_INFO[sub_domain]
+        brand = site_info['brand']
         if not video_id:
             webpage = self._download_webpage(url, display_id)
             video_id = self._search_regex(
                 # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
                 # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
-                r'data-video-id=["\']*VDKA(\w+)', webpage, 'video id')
-        site_info = self._SITE_INFO[sub_domain]
-        brand = site_info['brand']
-        video_data = self._download_json(
-            'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (brand, video_id),
-            video_id)['video'][0]
+                r'data-video-id=["\']*(VDKA\w+)', webpage, 'video id', default=None)
+            if not video_id:
+                # show extraction works for Disney, DisneyJunior and DisneyXD
+                # ABC and Freeform has different layout
+                show_id = self._search_regex(r'data-show-id=["\']*(SH\d+)', webpage, 'show id')
+                videos = self._extract_videos(brand, show_id=show_id)
+                show_title = self._search_regex(r'data-show-title="([^"]+)"', webpage, 'show title', fatal=False)
+                entries = []
+                for video in videos:
+                    entries.append(self.url_result(
+                        video['url'], 'Go', video.get('id'), video.get('title')))
+                entries.reverse()
+                return self.playlist_result(entries, show_id, show_title)
+        video_data = self._extract_videos(brand, video_id)[0]
+        video_id = video_data['id']
         title = video_data['title']
 
         formats = []
@@ -105,7 +126,7 @@ class GoIE(AdobePassIE):
                     self._initialize_geo_bypass(['US'])
                 entitlement = self._download_json(
                     'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
-                    video_id, data=urlencode_postdata(data), headers=self.geo_verification_headers())
+                    video_id, data=urlencode_postdata(data))
                 errors = entitlement.get('errors', {}).get('errors', [])
                 if errors:
                     for error in errors:

youtube_dl/extractor/infoq.py

@@ -87,8 +87,8 @@ class InfoQIE(BokeCCBaseIE):
 
     def _extract_http_audio(self, webpage, video_id):
         fields = self._hidden_inputs(webpage)
-        http_audio_url = fields['filename']
-        if http_audio_url is None:
+        http_audio_url = fields.get('filename')
+        if not http_audio_url:
             return []
 
         cookies_header = {'Cookie': self._extract_cookies(webpage)}

youtube_dl/extractor/laola1tv.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import json
+
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
@@ -8,15 +10,15 @@ from ..utils import (
     urlencode_postdata,
     xpath_element,
     xpath_text,
-    urljoin,
     update_url_query,
+    js_to_json,
 )
 
 
 class Laola1TvEmbedIE(InfoExtractor):
     IE_NAME = 'laola1tv:embed'
     _VALID_URL = r'https?://(?:www\.)?laola1\.tv/titanplayer\.php\?.*?\bvideoid=(?P<id>\d+)'
-    _TEST = {
+    _TESTS = [{
         # flashvars.premium = "false";
         'url': 'https://www.laola1.tv/titanplayer.php?videoid=708065&type=V&lang=en&portal=int&customer=1024',
         'info_dict': {
@@ -26,7 +28,30 @@ class Laola1TvEmbedIE(InfoExtractor):
             'uploader': 'ITTF - International Table Tennis Federation',
             'upload_date': '20161211',
         },
-    }
+    }]
+
+    def _extract_token_url(self, stream_access_url, video_id, data):
+        return self._download_json(
+            stream_access_url, video_id, headers={
+                'Content-Type': 'application/json',
+            }, data=json.dumps(data).encode())['data']['stream-access'][0]
+
+    def _extract_formats(self, token_url, video_id):
+        token_doc = self._download_xml(
+            token_url, video_id, 'Downloading token',
+            headers=self.geo_verification_headers())
+
+        token_attrib = xpath_element(token_doc, './/token').attrib
+
+        if token_attrib['status'] != '0':
+            raise ExtractorError(
+                'Token error: %s' % token_attrib['comment'], expected=True)
+
+        formats = self._extract_akamai_formats(
+            '%s?hdnea=%s' % (token_attrib['url'], token_attrib['auth']),
+            video_id)
+        self._sort_formats(formats)
+        return formats
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -68,29 +93,16 @@ class Laola1TvEmbedIE(InfoExtractor):
         else:
             data_abo = urlencode_postdata(
                 dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(','))))
-            token_url = self._download_json(
-                'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access',
-                video_id, query={
+            stream_access_url = update_url_query(
+                'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access', {
                     'videoId': _v('id'),
                     'target': self._search_regex(r'vs_target = (\d+);', webpage, 'vs target'),
                     'label': _v('label'),
                     'area': _v('area'),
-                }, data=data_abo)['data']['stream-access'][0]
+                })
+            token_url = self._extract_token_url(stream_access_url, video_id, data_abo)
 
-        token_doc = self._download_xml(
-            token_url, video_id, 'Downloading token',
-            headers=self.geo_verification_headers())
-
-        token_attrib = xpath_element(token_doc, './/token').attrib
-
-        if token_attrib['status'] != '0':
-            raise ExtractorError(
-                'Token error: %s' % token_attrib['comment'], expected=True)
-
-        formats = self._extract_akamai_formats(
-            '%s?hdnea=%s' % (token_attrib['url'], token_attrib['auth']),
-            video_id)
-        self._sort_formats(formats)
+        formats = self._extract_formats(token_url, video_id)
 
         categories_str = _v('meta_sports')
         categories = categories_str.split(',') if categories_str else []
@@ -107,7 +119,7 @@ class Laola1TvEmbedIE(InfoExtractor):
         }
 
 
-class Laola1TvIE(InfoExtractor):
+class Laola1TvIE(Laola1TvEmbedIE):
     IE_NAME = 'laola1tv'
     _VALID_URL = r'https?://(?:www\.)?laola1\.tv/[a-z]+-[a-z]+/[^/]+/(?P<id>[^/?#&]+)'
     _TESTS = [{
@@ -164,13 +176,42 @@ class Laola1TvIE(InfoExtractor):
         if 'Dieser Livestream ist bereits beendet.' in webpage:
             raise ExtractorError('This live stream has already finished.', expected=True)
 
-        iframe_url = urljoin(url, self._search_regex(
-            r'<iframe[^>]*?id="videoplayer"[^>]*?src="([^"]+)"',
-            webpage, 'iframe url'))
+        conf = self._parse_json(self._search_regex(
+            r'(?s)conf\s*=\s*({.+?});', webpage, 'conf'),
+            display_id, js_to_json)
+
+        video_id = conf['videoid']
+
+        config = self._download_json(conf['configUrl'], video_id, query={
+            'videoid': video_id,
+            'partnerid': conf['partnerid'],
+            'language': conf.get('language', ''),
+            'portal': conf.get('portalid', ''),
+        })
+        error = config.get('error')
+        if error:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
+
+        video_data = config['video']
+        title = video_data['title']
+        is_live = video_data.get('isLivestream') and video_data.get('isLive')
+        meta = video_data.get('metaInformation')
+        sports = meta.get('sports')
+        categories = sports.split(',') if sports else []
+
+        token_url = self._extract_token_url(
+            video_data['streamAccess'], video_id,
+            video_data['abo']['required'])
+
+        formats = self._extract_formats(token_url, video_id)
 
         return {
-            '_type': 'url',
+            'id': video_id,
             'display_id': display_id,
-            'url': iframe_url,
-            'ie_key': 'Laola1TvEmbed',
+            'title': self._live_title(title) if is_live else title,
+            'description': video_data.get('description'),
+            'thumbnail': video_data.get('image'),
+            'categories': categories,
+            'formats': formats,
+            'is_live': is_live,
         }

youtube_dl/extractor/leeco.py

@@ -23,7 +23,6 @@ from ..utils import (
     str_or_none,
     url_basename,
     urshift,
-    update_url_query,
 )
 
 
@@ -51,7 +50,7 @@ class LeIE(InfoExtractor):
             'id': '1415246',
             'ext': 'mp4',
             'title': '美人天下01',
-            'description': 'md5:f88573d9d7225ada1359eaf0dbf8bcda',
+            'description': 'md5:28942e650e82ed4fcc8e4de919ee854d',
         },
         'params': {
             'hls_prefer_native': True,
@@ -69,7 +68,6 @@ class LeIE(InfoExtractor):
         'params': {
             'hls_prefer_native': True,
         },
-        'skip': 'Only available in China',
     }, {
         'url': 'http://sports.le.com/video/25737697.html',
         'only_matching': True,
@@ -81,7 +79,7 @@ class LeIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    # ror() and calc_time_key() are reversed from a embedded swf file in KLetvPlayer.swf
+    # ror() and calc_time_key() are reversed from a embedded swf file in LetvPlayer.swf
     def ror(self, param1, param2):
         _loc3_ = 0
         while _loc3_ < param2:
@@ -90,15 +88,8 @@ class LeIE(InfoExtractor):
         return param1
 
     def calc_time_key(self, param1):
-        _loc2_ = 773625421
-        _loc3_ = self.ror(param1, _loc2_ % 13)
-        _loc3_ = _loc3_ ^ _loc2_
-        _loc3_ = self.ror(_loc3_, _loc2_ % 17)
-        return _loc3_
-
-    # reversed from http://jstatic.letvcdn.com/sdk/player.js
-    def get_mms_key(self, time):
-        return self.ror(time, 8) ^ 185025305
+        _loc2_ = 185025305
+        return self.ror(param1, _loc2_ % 17) ^ _loc2_
 
     # see M3U8Encryption class in KLetvPlayer.swf
     @staticmethod
@@ -122,7 +113,7 @@ class LeIE(InfoExtractor):
 
     def _check_errors(self, play_json):
         # Check for errors
-        playstatus = play_json['playstatus']
+        playstatus = play_json['msgs']['playstatus']
         if playstatus['status'] == 0:
             flag = playstatus['flag']
             if flag == 1:
@@ -134,58 +125,31 @@ class LeIE(InfoExtractor):
         media_id = self._match_id(url)
         page = self._download_webpage(url, media_id)
 
-        play_json_h5 = self._download_json(
-            'http://api.le.com/mms/out/video/playJsonH5',
-            media_id, 'Downloading html5 playJson data', query={
-                'id': media_id,
-                'platid': 3,
-                'splatid': 304,
-                'format': 1,
-                'tkey': self.get_mms_key(int(time.time())),
-                'domain': 'www.le.com',
-                'tss': 'no',
-            },
-            headers=self.geo_verification_headers())
-        self._check_errors(play_json_h5)
-
         play_json_flash = self._download_json(
-            'http://api.le.com/mms/out/video/playJson',
+            'http://player-pc.le.com/mms/out/video/playJson',
             media_id, 'Downloading flash playJson data', query={
                 'id': media_id,
                 'platid': 1,
                 'splatid': 101,
                 'format': 1,
+                'source': 1000,
                 'tkey': self.calc_time_key(int(time.time())),
                 'domain': 'www.le.com',
+                'region': 'cn',
             },
             headers=self.geo_verification_headers())
         self._check_errors(play_json_flash)
 
-        def get_h5_urls(media_url, format_id):
-            location = self._download_json(
-                media_url, media_id,
-                'Download JSON metadata for format %s' % format_id, query={
-                    'format': 1,
-                    'expect': 3,
-                    'tss': 'no',
-                })['location']
-
-            return {
-                'http': update_url_query(location, {'tss': 'no'}),
-                'hls': update_url_query(location, {'tss': 'ios'}),
-            }
-
         def get_flash_urls(media_url, format_id):
-            media_url += '&' + compat_urllib_parse_urlencode({
-                'm3v': 1,
-                'format': 1,
-                'expect': 3,
-                'rateid': format_id,
-            })
-
             nodes_data = self._download_json(
                 media_url, media_id,
-                'Download JSON metadata for format %s' % format_id)
+                'Download JSON metadata for format %s' % format_id,
+                query={
+                    'm3v': 1,
+                    'format': 1,
+                    'expect': 3,
+                    'tss': 'ios',
+                })
 
             req = self._request_webpage(
                 nodes_data['nodelist'][0]['location'], media_id,
@@ -199,29 +163,28 @@ class LeIE(InfoExtractor):
 
         extracted_formats = []
         formats = []
-        for play_json, get_urls in ((play_json_h5, get_h5_urls), (play_json_flash, get_flash_urls)):
-            playurl = play_json['playurl']
-            play_domain = playurl['domain'][0]
+        playurl = play_json_flash['msgs']['playurl']
+        play_domain = playurl['domain'][0]
 
-            for format_id, format_data in playurl.get('dispatch', []).items():
-                if format_id in extracted_formats:
-                    continue
-                extracted_formats.append(format_id)
+        for format_id, format_data in playurl.get('dispatch', []).items():
+            if format_id in extracted_formats:
+                continue
+            extracted_formats.append(format_id)
 
-                media_url = play_domain + format_data[0]
-                for protocol, format_url in get_urls(media_url, format_id).items():
-                    f = {
-                        'url': format_url,
-                        'ext': determine_ext(format_data[1]),
-                        'format_id': '%s-%s' % (protocol, format_id),
-                        'protocol': 'm3u8_native' if protocol == 'hls' else 'http',
-                        'quality': int_or_none(format_id),
-                    }
+            media_url = play_domain + format_data[0]
+            for protocol, format_url in get_flash_urls(media_url, format_id).items():
+                f = {
+                    'url': format_url,
+                    'ext': determine_ext(format_data[1]),
+                    'format_id': '%s-%s' % (protocol, format_id),
+                    'protocol': 'm3u8_native' if protocol == 'hls' else 'http',
+                    'quality': int_or_none(format_id),
+                }
 
-                    if format_id[-1:] == 'p':
-                        f['height'] = int_or_none(format_id[:-1])
+                if format_id[-1:] == 'p':
+                    f['height'] = int_or_none(format_id[:-1])
 
-                    formats.append(f)
+                formats.append(f)
         self._sort_formats(formats, ('height', 'quality', 'format_id'))
 
         publish_time = parse_iso8601(self._html_search_regex(

youtube_dl/extractor/lego.py

@@ -86,7 +86,7 @@ class LEGOIE(InfoExtractor):
         formats = self._extract_akamai_formats(
             '%si/s/public/%s_,%s,.mp4.csmil/master.m3u8' % (streaming_base, path, streaming_path), video_id)
         m3u8_formats = list(filter(
-            lambda f: f.get('protocol') == 'm3u8_native' and f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
+            lambda f: f.get('protocol') == 'm3u8_native' and f.get('vcodec') != 'none',
             formats))
         if len(m3u8_formats) == len(self._BITRATES):
             self._sort_formats(m3u8_formats)

youtube_dl/extractor/noovo.py

@@ -0,0 +1,97 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .brightcove import BrightcoveNewIE
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    smuggle_url,
+    try_get,
+)
+
+
+class NoovoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^/]+\.)?noovo\.ca/videos/(?P<id>[^/]+/[^/?#&]+)'
+    _TESTS = [{
+        # clip
+        'url': 'http://noovo.ca/videos/rpm-plus/chrysler-imperial',
+        'info_dict': {
+            'id': '5386045029001',
+            'ext': 'mp4',
+            'title': 'Chrysler Imperial',
+            'description': 'md5:de3c898d1eb810f3e6243e08c8b4a056',
+            'timestamp': 1491399228,
+            'upload_date': '20170405',
+            'uploader_id': '618566855001',
+            'creator': 'vtele',
+            'view_count': int,
+            'series': 'RPM+',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # episode
+        'url': 'http://noovo.ca/videos/l-amour-est-dans-le-pre/episode-13-8',
+        'info_dict': {
+            'id': '5395865725001',
+            'title': 'Épisode 13 : Les retrouvailles',
+            'description': 'md5:336d5ebc5436534e61d16e63ddfca327',
+            'ext': 'mp4',
+            'timestamp': 1492019320,
+            'upload_date': '20170412',
+            'uploader_id': '618566855001',
+            'creator': 'vtele',
+            'view_count': int,
+            'series': "L'amour est dans le pré",
+            'season_number': 5,
+            'episode': 'Épisode 13',
+            'episode_number': 13,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/618566855001/default_default/index.html?videoId=%s'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        data = self._download_json(
+            'http://api.noovo.ca/api/v1/pages/single-episode/%s' % video_id,
+            video_id)['data']
+
+        content = try_get(data, lambda x: x['contents'][0])
+
+        brightcove_id = data.get('brightcoveId') or content['brightcoveId']
+
+        series = try_get(
+            data, (
+                lambda x: x['show']['title'],
+                lambda x: x['season']['show']['title']),
+            compat_str)
+
+        episode = None
+        og = data.get('og')
+        if isinstance(og, dict) and og.get('type') == 'video.episode':
+            episode = og.get('title')
+
+        video = content or data
+
+        return {
+            '_type': 'url_transparent',
+            'ie_key': BrightcoveNewIE.ie_key(),
+            'url': smuggle_url(
+                self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
+                {'geo_countries': ['CA']}),
+            'id': brightcove_id,
+            'title': video.get('title'),
+            'creator': video.get('source'),
+            'view_count': int_or_none(video.get('viewsCount')),
+            'series': series,
+            'season_number': int_or_none(try_get(
+                data, lambda x: x['season']['seasonNumber'])),
+            'episode': episode,
+            'episode_number': int_or_none(data.get('episodeNumber')),
+        }

youtube_dl/extractor/nrk.py

@@ -148,13 +148,34 @@ class NRKBaseIE(InfoExtractor):
 
         vcodec = 'none' if data.get('mediaType') == 'Audio' else None
 
-        # TODO: extract chapters when https://github.com/rg3/youtube-dl/pull/9409 is merged
-
         for entry in entries:
             entry.update(common_info)
             for f in entry['formats']:
                 f['vcodec'] = vcodec
 
+        points = data.get('shortIndexPoints')
+        if isinstance(points, list):
+            chapters = []
+            for next_num, point in enumerate(points, start=1):
+                if not isinstance(point, dict):
+                    continue
+                start_time = parse_duration(point.get('startPoint'))
+                if start_time is None:
+                    continue
+                end_time = parse_duration(
+                    data.get('duration')
+                    if next_num == len(points)
+                    else points[next_num].get('startPoint'))
+                if end_time is None:
+                    continue
+                chapters.append({
+                    'start_time': start_time,
+                    'end_time': end_time,
+                    'title': point.get('title'),
+                })
+            if chapters and len(entries) == 1:
+                entries[0]['chapters'] = chapters
+
         return self.playlist_result(entries, video_id, title, description)
 
 

youtube_dl/extractor/pbs.py

@@ -8,7 +8,9 @@ from ..utils import (
     ExtractorError,
     determine_ext,
     int_or_none,
+    float_or_none,
     js_to_json,
+    orderedSet,
     strip_jsonp,
     strip_or_none,
     unified_strdate,
@@ -263,6 +265,13 @@ class PBSIE(InfoExtractor):
             },
             'playlist_count': 2,
         },
+        {
+            'url': 'http://www.pbs.org/wgbh/americanexperience/films/great-war/',
+            'info_dict': {
+                'id': 'great-war',
+            },
+            'playlist_count': 3,
+        },
         {
             'url': 'http://www.pbs.org/wgbh/americanexperience/films/death/player/',
             'info_dict': {
@@ -381,10 +390,10 @@ class PBSIE(InfoExtractor):
             # tabbed frontline videos
             MULTI_PART_REGEXES = (
                 r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"',
-                r'<a[^>]+href=["\']#video-\d+["\'][^>]+data-coveid=["\'](\d+)',
+                r'<a[^>]+href=["\']#(?:video-|part)\d+["\'][^>]+data-cove[Ii]d=["\'](\d+)',
             )
             for p in MULTI_PART_REGEXES:
-                tabbed_videos = re.findall(p, webpage)
+                tabbed_videos = orderedSet(re.findall(p, webpage))
                 if tabbed_videos:
                     return tabbed_videos, presumptive_id, upload_date, description
 
@@ -464,6 +473,7 @@ class PBSIE(InfoExtractor):
                     redirects.append(redirect)
                     redirect_urls.add(redirect_url)
 
+        chapters = []
         # Player pages may also serve different qualities
         for page in ('widget/partnerplayer', 'portalplayer'):
             player = self._download_webpage(
@@ -479,6 +489,20 @@ class PBSIE(InfoExtractor):
                     extract_redirect_urls(video_info)
                     if not info:
                         info = video_info
+                if not chapters:
+                    for chapter_data in re.findall(r'(?s)chapters\.push\(({.*?})\)', player):
+                        chapter = self._parse_json(chapter_data, video_id, js_to_json, fatal=False)
+                        if not chapter:
+                            continue
+                        start_time = float_or_none(chapter.get('start_time'), 1000)
+                        duration = float_or_none(chapter.get('duration'), 1000)
+                        if start_time is None or duration is None:
+                            continue
+                        chapters.append({
+                            'start_time': start_time,
+                            'end_time': start_time + duration,
+                            'title': chapter.get('title'),
+                        })
 
         formats = []
         http_url = None
@@ -515,7 +539,7 @@ class PBSIE(InfoExtractor):
                     http_url = format_url
         self._remove_duplicate_formats(formats)
         m3u8_formats = list(filter(
-            lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
+            lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none',
             formats))
         if http_url:
             for m3u8_format in m3u8_formats:
@@ -588,4 +612,5 @@ class PBSIE(InfoExtractor):
             'upload_date': upload_date,
             'formats': formats,
             'subtitles': subtitles,
+            'chapters': chapters,
         }

youtube_dl/extractor/pornhub.py

@@ -33,7 +33,7 @@ class PornHubIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)|
+                            (?:[a-z]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
                             (?:www\.)?thumbzilla\.com/video/
                         )
                         (?P<id>[\da-z]+)
@@ -97,6 +97,9 @@ class PornHubIE(InfoExtractor):
     }, {
         'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex',
         'only_matching': True,
+    }, {
+        'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
+        'only_matching': True,
     }]
 
     @staticmethod

youtube_dl/extractor/r7.py

@@ -62,8 +62,7 @@ class R7IE(InfoExtractor):
             # m3u8 format always matches the http format, let's copy metadata from
             # one to another
             m3u8_formats = list(filter(
-                lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
-                formats))
+                lambda f: f.get('vcodec') != 'none', formats))
             if len(m3u8_formats) == 1:
                 f_copy = m3u8_formats[0].copy()
                 f_copy.update(f)

youtube_dl/extractor/rmcdecouverte.py

@@ -13,21 +13,20 @@ class RMCDecouverteIE(InfoExtractor):
     _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/mediaplayer-replay.*?\bid=(?P<id>\d+)'
 
     _TEST = {
-        'url': 'http://rmcdecouverte.bfmtv.com/mediaplayer-replay/?id=1430&title=LES%20HEROS%20DU%2088e%20ETAGE',
+        'url': 'http://rmcdecouverte.bfmtv.com/mediaplayer-replay/?id=13502&title=AQUAMEN:LES%20ROIS%20DES%20AQUARIUMS%20:UN%20DELICIEUX%20PROJET',
         'info_dict': {
-            'id': '5111223049001',
+            'id': '5419055995001',
             'ext': 'mp4',
-            'title': ': LES HEROS DU 88e ETAGE',
-            'description': 'Découvrez comment la bravoure de deux hommes dans la Tour Nord du World Trade Center a sauvé  la vie d\'innombrables personnes le 11 septembre 2001.',
+            'title': 'UN DELICIEUX PROJET',
+            'description': 'md5:63610df7c8b1fc1698acd4d0d90ba8b5',
             'uploader_id': '1969646226001',
-            'upload_date': '20160904',
-            'timestamp': 1472951103,
+            'upload_date': '20170502',
+            'timestamp': 1493745308,
         },
         'params': {
-            # rtmp download
             'skip_download': True,
         },
-        'skip': 'Only works from France',
+        'skip': 'only available for a week',
     }
     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1969646226001/default_default/index.html?videoId=%s'
 
@@ -35,5 +34,12 @@ class RMCDecouverteIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
         brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
-        brightcove_id = compat_parse_qs(compat_urlparse.urlparse(brightcove_legacy_url).query)['@videoPlayer'][0]
-        return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)
+        if brightcove_legacy_url:
+            brightcove_id = compat_parse_qs(compat_urlparse.urlparse(
+                brightcove_legacy_url).query)['@videoPlayer'][0]
+        else:
+            brightcove_id = self._search_regex(
+                r'data-video-id=["\'](\d+)', webpage, 'brightcove id')
+        return self.url_result(
+            self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew',
+            brightcove_id)

youtube_dl/extractor/streamable.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class StreamableIE(InfoExtractor):
-    _VALID_URL = r'https?://streamable\.com/(?:e/)?(?P<id>\w+)'
+    _VALID_URL = r'https?://streamable\.com/(?:[es]/)?(?P<id>\w+)'
     _TESTS = [
         {
             'url': 'https://streamable.com/dnd1',
@@ -47,6 +47,10 @@ class StreamableIE(InfoExtractor):
         {
             'url': 'https://streamable.com/e/dnd1',
             'only_matching': True,
+        },
+        {
+            'url': 'https://streamable.com/s/okkqk/drxjds',
+            'only_matching': True,
         }
     ]
 

youtube_dl/extractor/ted.py

@@ -210,7 +210,7 @@ class TEDIE(InfoExtractor):
                     resources.get('stream'), video_name, 'mp4', m3u8_id=format_id, fatal=False))
 
         m3u8_formats = list(filter(
-            lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
+            lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none',
             formats))
         if http_url:
             for m3u8_format in m3u8_formats:

youtube_dl/extractor/theplatform.py

@@ -80,14 +80,33 @@ class ThePlatformBaseIE(OnceIE):
                     'url': src,
                 })
 
+        duration = info.get('duration')
+        tp_chapters = info.get('chapters', [])
+        chapters = []
+        if tp_chapters:
+            def _add_chapter(start_time, end_time):
+                start_time = float_or_none(start_time, 1000)
+                end_time = float_or_none(end_time, 1000)
+                if start_time is None or end_time is None:
+                    return
+                chapters.append({
+                    'start_time': start_time,
+                    'end_time': end_time,
+                })
+
+            for chapter in tp_chapters[:-1]:
+                _add_chapter(chapter.get('startTime'), chapter.get('endTime'))
+            _add_chapter(tp_chapters[-1].get('startTime'), tp_chapters[-1].get('endTime') or duration)
+
         return {
             'title': info['title'],
             'subtitles': subtitles,
             'description': info['description'],
             'thumbnail': info['defaultThumbnailUrl'],
-            'duration': int_or_none(info.get('duration'), 1000),
+            'duration': float_or_none(duration, 1000),
             'timestamp': int_or_none(info.get('pubDate'), 1000) or None,
             'uploader': info.get('billingCode'),
+            'chapters': chapters,
         }
 
     def _extract_theplatform_metadata(self, path, video_id):

youtube_dl/extractor/tvp.py

@@ -150,8 +150,7 @@ class TVPEmbedIE(InfoExtractor):
                 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
             self._sort_formats(m3u8_formats)
             m3u8_formats = list(filter(
-                lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
-                m3u8_formats))
+                lambda f: f.get('vcodec') != 'none', m3u8_formats))
             formats.extend(m3u8_formats)
             for i, m3u8_format in enumerate(m3u8_formats, 2):
                 http_url = '%s-%d.mp4' % (video_url_base, i)

youtube_dl/extractor/tvplayer.py

@@ -2,9 +2,13 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_HTTPError
+from ..compat import (
+    compat_HTTPError,
+    compat_str,
+)
 from ..utils import (
     extract_attributes,
+    try_get,
     urlencode_postdata,
     ExtractorError,
 )
@@ -34,25 +38,32 @@ class TVPlayerIE(InfoExtractor):
             webpage, 'channel element'))
         title = current_channel['data-name']
 
-        resource_id = self._search_regex(
-            r'resourceId\s*=\s*"(\d+)"', webpage, 'resource id')
-        platform = self._search_regex(
-            r'platform\s*=\s*"([^"]+)"', webpage, 'platform')
+        resource_id = current_channel['data-id']
+
         token = self._search_regex(
-            r'token\s*=\s*"([^"]+)"', webpage, 'token', default='null')
-        validate = self._search_regex(
-            r'validate\s*=\s*"([^"]+)"', webpage, 'validate', default='null')
+            r'data-token=(["\'])(?P<token>(?!\1).+)\1', webpage,
+            'token', group='token')
+
+        context = self._download_json(
+            'https://tvplayer.com/watch/context', display_id,
+            'Downloading JSON context', query={
+                'resource': resource_id,
+                'nonce': token,
+            })
+
+        validate = context['validate']
+        platform = try_get(
+            context, lambda x: x['platform']['key'], compat_str) or 'firefox'
 
         try:
             response = self._download_json(
                 'http://api.tvplayer.com/api/v2/stream/live',
-                resource_id, headers={
+                display_id, 'Downloading JSON stream', headers={
                     'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
                 }, data=urlencode_postdata({
+                    'id': resource_id,
                     'service': 1,
                     'platform': platform,
-                    'id': resource_id,
-                    'token': token,
                     'validate': validate,
                 }))['tvplayer']['response']
         except ExtractorError as e:
@@ -63,7 +74,7 @@ class TVPlayerIE(InfoExtractor):
                     '%s said: %s' % (self.IE_NAME, response['error']), expected=True)
             raise
 
-        formats = self._extract_m3u8_formats(response['stream'], resource_id, 'mp4')
+        formats = self._extract_m3u8_formats(response['stream'], display_id, 'mp4')
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/vevo.py

@@ -1,6 +1,7 @@
 from __future__ import unicode_literals
 
 import re
+import json
 
 from .common import InfoExtractor
 from ..compat import (
@@ -11,7 +12,6 @@ from ..compat import (
 from ..utils import (
     ExtractorError,
     int_or_none,
-    sanitized_Request,
     parse_iso8601,
 )
 
@@ -154,19 +154,24 @@ class VevoIE(VevoBaseIE):
     }
 
     def _initialize_api(self, video_id):
-        req = sanitized_Request(
-            'http://www.vevo.com/auth', data=b'')
         webpage = self._download_webpage(
-            req, None,
+            'https://accounts.vevo.com/token', None,
             note='Retrieving oauth token',
-            errnote='Unable to retrieve oauth token')
+            errnote='Unable to retrieve oauth token',
+            data=json.dumps({
+                'client_id': 'SPupX1tvqFEopQ1YS6SS',
+                'grant_type': 'urn:vevo:params:oauth:grant-type:anonymous',
+            }).encode('utf-8'),
+            headers={
+                'Content-Type': 'application/json',
+            })
 
         if re.search(r'(?i)THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION', webpage):
             self.raise_geo_restricted(
                 '%s said: This page is currently unavailable in your region' % self.IE_NAME)
 
         auth_info = self._parse_json(webpage, video_id)
-        self._api_url_template = self.http_scheme() + '//apiv2.vevo.com/%s?token=' + auth_info['access_token']
+        self._api_url_template = self.http_scheme() + '//apiv2.vevo.com/%s?token=' + auth_info['legacy_token']
 
     def _call_api(self, path, *args, **kwargs):
         try:

youtube_dl/extractor/vice.py

@@ -20,7 +20,7 @@ from ..utils import (
 
 
 class ViceBaseIE(AdobePassIE):
-    def _extract_preplay_video(self, url, webpage):
+    def _extract_preplay_video(self, url, locale, webpage):
         watch_hub_data = extract_attributes(self._search_regex(
             r'(?s)(<watch-hub\s*.+?</watch-hub>)', webpage, 'watch hub'))
         video_id = watch_hub_data['vms-id']
@@ -32,7 +32,8 @@ class ViceBaseIE(AdobePassIE):
             resource = self._get_mvpd_resource(
                 'VICELAND', title, video_id,
                 watch_hub_data.get('video-rating'))
-            query['tvetoken'] = self._extract_mvpd_auth(url, video_id, 'VICELAND', resource)
+            query['tvetoken'] = self._extract_mvpd_auth(
+                url, video_id, 'VICELAND', resource)
 
         # signature generation algorithm is reverse engineered from signatureGenerator in
         # webpack:///../shared/~/vice-player/dist/js/vice-player.js in
@@ -45,11 +46,14 @@ class ViceBaseIE(AdobePassIE):
 
         try:
             host = 'www.viceland' if is_locked else self._PREPLAY_HOST
-            preplay = self._download_json('https://%s.com/en_us/preplay/%s' % (host, video_id), video_id, query=query)
+            preplay = self._download_json(
+                'https://%s.com/%s/preplay/%s' % (host, locale, video_id),
+                video_id, query=query)
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
                 error = json.loads(e.cause.read().decode())
-                raise ExtractorError('%s said: %s' % (self.IE_NAME, error['details']), expected=True)
+                raise ExtractorError('%s said: %s' % (
+                    self.IE_NAME, error['details']), expected=True)
             raise
 
         video_data = preplay['video']
@@ -88,41 +92,30 @@ class ViceBaseIE(AdobePassIE):
 
 
 class ViceIE(ViceBaseIE):
-    _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?videos?/(?P<id>[^/?#&]+)'
+    IE_NAME = 'vice'
+    _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:(?P<locale>[^/]+)/)?videos?/(?P<id>[^/?#&]+)'
 
     _TESTS = [{
-        'url': 'http://www.vice.com/video/cowboy-capitalists-part-1',
-        'md5': 'e9d77741f9e42ba583e683cd170660f7',
+        'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab',
+        'md5': '7d3ae2f9ba5f196cdd9f9efd43657ac2',
         'info_dict': {
-            'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
+            'id': 'N2bzkydjraWDGwnt8jAttCF6Y0PDv4Zj',
             'ext': 'flv',
-            'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
-            'duration': 725.983,
+            'title': 'Monkey Labs of Holland',
+            'description': 'md5:92b3c7dcbfe477f772dd4afa496c9149',
         },
         'add_ie': ['Ooyala'],
-    }, {
-        'url': 'http://www.vice.com/video/how-to-hack-a-car',
-        'md5': 'a7ecf64ee4fa19b916c16f4b56184ae2',
-        'info_dict': {
-            'id': '3jstaBeXgAs',
-            'ext': 'mp4',
-            'title': 'How to Hack a Car: Phreaked Out (Episode 2)',
-            'description': 'md5:ee95453f7ff495db8efe14ae8bf56f30',
-            'uploader_id': 'MotherboardTV',
-            'uploader': 'Motherboard',
-            'upload_date': '20140529',
-        },
-        'add_ie': ['Youtube'],
     }, {
         'url': 'https://video.vice.com/en_us/video/the-signal-from-tolva/5816510690b70e6c5fd39a56',
-        'md5': '',
         'info_dict': {
             'id': '5816510690b70e6c5fd39a56',
             'ext': 'mp4',
             'uploader': 'Waypoint',
             'title': 'The Signal From Tölva',
+            'description': 'md5:3927e3c79f9e8094606a2b3c5b5e55d5',
             'uploader_id': '57f7d621e05ca860fa9ccaf9',
-            'timestamp': 1477941983938,
+            'timestamp': 1477941983,
+            'upload_date': '20161031',
         },
         'params': {
             # m3u8 download
@@ -130,19 +123,31 @@ class ViceIE(ViceBaseIE):
         },
         'add_ie': ['UplynkPreplay'],
     }, {
-        'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab',
-        'only_matching': True,
+        'url': 'https://video.vice.com/alps/video/ulfs-wien-beruchtigste-grafitti-crew-part-1/581b12b60a0e1f4c0fb6ea2f',
+        'info_dict': {
+            'id': '581b12b60a0e1f4c0fb6ea2f',
+            'ext': 'mp4',
+            'title': 'ULFs - Wien berüchtigste Grafitti Crew - Part 1',
+            'description': '<p>Zwischen Hinterzimmer-Tattoos und U-Bahnschächten erzählen uns die Ulfs, wie es ist, "süchtig nach Sachbeschädigung" zu sein.</p>',
+            'uploader': 'VICE',
+            'uploader_id': '57a204088cb727dec794c67b',
+            'timestamp': 1485368119,
+            'upload_date': '20170125',
+            'age_limit': 14,
+        },
+        'params': {
+            # AES-encrypted m3u8
+            'skip_download': True,
+        },
+        'add_ie': ['UplynkPreplay'],
     }, {
-        'url': 'http://www.vice.com/ru/video/big-night-out-ibiza-clive-martin-229',
-        'only_matching': True,
-    }, {
-        'url': 'https://munchies.vice.com/en/videos/watch-the-trailer-for-our-new-series-the-pizza-show',
+        'url': 'https://video.vice.com/en_us/video/pizza-show-trailer/56d8c9a54d286ed92f7f30e4',
         'only_matching': True,
     }]
     _PREPLAY_HOST = 'video.vice'
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        locale, video_id = re.match(self._VALID_URL, url).groups()
         webpage, urlh = self._download_webpage_handle(url, video_id)
         embed_code = self._search_regex(
             r'embedCode=([^&\'"]+)', webpage,
@@ -153,10 +158,11 @@ class ViceIE(ViceBaseIE):
             r'data-youtube-id="([^"]+)"', webpage, 'youtube id', default=None)
         if youtube_id:
             return self.url_result(youtube_id, 'Youtube')
-        return self._extract_preplay_video(urlh.geturl(), webpage)
+        return self._extract_preplay_video(urlh.geturl(), locale, webpage)
 
 
 class ViceShowIE(InfoExtractor):
+    IE_NAME = 'vice:show'
     _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?show/(?P<id>[^/?#&]+)'
 
     _TEST = {
@@ -183,6 +189,86 @@ class ViceShowIE(InfoExtractor):
             r'<title>(.+?)</title>', webpage, 'title', default=None)
         if title:
             title = re.sub(r'(.+)\s*\|\s*.+$', r'\1', title).strip()
-        description = self._html_search_meta('description', webpage, 'description')
+        description = self._html_search_meta(
+            'description', webpage, 'description')
 
         return self.playlist_result(entries, show_id, title, description)
+
+
+class ViceArticleIE(InfoExtractor):
+    IE_NAME = 'vice:article'
+    _VALID_URL = r'https://www.vice.com/[^/]+/article/(?P<id>[^?#]+)'
+
+    _TESTS = [{
+        'url': 'https://www.vice.com/en_us/article/on-set-with-the-woman-making-mormon-porn-in-utah',
+        'info_dict': {
+            'id': '58dc0a3dee202d2a0ccfcbd8',
+            'ext': 'mp4',
+            'title': 'Mormon War on Porn ',
+            'description': 'md5:ad396a2481e7f8afb5ed486878421090',
+            'uploader': 'VICE',
+            'uploader_id': '57a204088cb727dec794c693',
+            'timestamp': 1489160690,
+            'upload_date': '20170310',
+        },
+        'params': {
+            # AES-encrypted m3u8
+            'skip_download': True,
+        },
+        'add_ie': ['UplynkPreplay'],
+    }, {
+        'url': 'https://www.vice.com/en_us/article/how-to-hack-a-car',
+        'md5': 'a7ecf64ee4fa19b916c16f4b56184ae2',
+        'info_dict': {
+            'id': '3jstaBeXgAs',
+            'ext': 'mp4',
+            'title': 'How to Hack a Car: Phreaked Out (Episode 2)',
+            'description': 'md5:ee95453f7ff495db8efe14ae8bf56f30',
+            'uploader_id': 'MotherboardTV',
+            'uploader': 'Motherboard',
+            'upload_date': '20140529',
+        },
+        'add_ie': ['Youtube'],
+    }, {
+        'url': 'https://www.vice.com/en_us/article/cowboy-capitalists-part-1',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.vice.com/ru/article/big-night-out-ibiza-clive-martin-229',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        prefetch_data = self._parse_json(self._search_regex(
+            r'window\.__PREFETCH_DATA\s*=\s*({.*});',
+            webpage, 'prefetch data'), display_id)
+        body = prefetch_data['body']
+
+        def _url_res(video_url, ie_key):
+            return {
+                '_type': 'url_transparent',
+                'url': video_url,
+                'display_id': display_id,
+                'ie_key': ie_key,
+            }
+
+        embed_code = self._search_regex(
+            r'embedCode=([^&\'"]+)', body,
+            'ooyala embed code', default=None)
+        if embed_code:
+            return _url_res('ooyala:%s' % embed_code, 'Ooyala')
+
+        youtube_url = self._html_search_regex(
+            r'<iframe[^>]+src="(.*youtube\.com/.*)"',
+            body, 'YouTube URL', default=None)
+        if youtube_url:
+            return _url_res(youtube_url, 'Youtube')
+
+        video_url = self._html_search_regex(
+            r'data-video-url="([^"]+)"',
+            prefetch_data['embed_code'], 'video URL')
+
+        return _url_res(video_url, ViceIE.ie_key())

youtube_dl/extractor/viceland.py

@@ -1,11 +1,13 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .vice import ViceBaseIE
 
 
 class VicelandIE(ViceBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?viceland\.com/[^/]+/video/[^/]+/(?P<id>[a-f0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?viceland\.com/(?P<locale>[^/]+)/video/[^/]+/(?P<id>[a-f0-9]+)'
     _TEST = {
         'url': 'https://www.viceland.com/en_us/video/trapped/588a70d0dba8a16007de7316',
         'info_dict': {
@@ -24,10 +26,13 @@ class VicelandIE(ViceBaseIE):
             'skip_download': True,
         },
         'add_ie': ['UplynkPreplay'],
+        'skip': '404',
     }
     _PREPLAY_HOST = 'www.viceland'
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        locale = mobj.group('locale')
         webpage = self._download_webpage(url, video_id)
-        return self._extract_preplay_video(url, webpage)
+        return self._extract_preplay_video(url, locale, webpage)

youtube_dl/extractor/videopress.py

@@ -1,7 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import random
 import re
 
 from .common import InfoExtractor
@@ -11,6 +10,7 @@ from ..utils import (
     float_or_none,
     parse_age_limit,
     qualities,
+    random_birthday,
     try_get,
     unified_timestamp,
     urljoin,
@@ -47,13 +47,10 @@ class VideoPressIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
+        query = random_birthday('birth_year', 'birth_month', 'birth_day')
         video = self._download_json(
             'https://public-api.wordpress.com/rest/v1.1/videos/%s' % video_id,
-            video_id, query={
-                'birth_month': random.randint(1, 12),
-                'birth_day': random.randint(1, 31),
-                'birth_year': random.randint(1950, 1995),
-            })
+            video_id, query=query)
 
         title = video['title']
 

youtube_dl/extractor/viewster.py

@@ -176,8 +176,7 @@ class ViewsterIE(InfoExtractor):
                     if m3u8_formats:
                         self._sort_formats(m3u8_formats)
                         m3u8_formats = list(filter(
-                            lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
-                            m3u8_formats))
+                            lambda f: f.get('vcodec') != 'none', m3u8_formats))
                     if len(qualities) == len(m3u8_formats):
                         for q, m3u8_format in zip(qualities, m3u8_formats):
                             f = m3u8_format.copy()

youtube_dl/extractor/washingtonpost.py

@@ -13,6 +13,7 @@ from ..utils import (
 class WashingtonPostIE(InfoExtractor):
     IE_NAME = 'washingtonpost'
     _VALID_URL = r'(?:washingtonpost:|https?://(?:www\.)?washingtonpost\.com/video/(?:[^/]+/)*)(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
+    _EMBED_URL = r'https?://(?:www\.)?washingtonpost\.com/video/c/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
     _TEST = {
         'url': 'https://www.washingtonpost.com/video/c/video/480ba4ee-1ec7-11e6-82c2-a7dcb313287d',
         'md5': '6f537e1334b714eb15f9563bd4b9cdfa',
@@ -27,6 +28,11 @@ class WashingtonPostIE(InfoExtractor):
         },
     }
 
+    @classmethod
+    def _extract_urls(cls, webpage):
+        return re.findall(
+            r'<iframe[^>]+\bsrc=["\'](%s)' % cls._EMBED_URL, webpage)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         video_data = self._download_json(

youtube_dl/extractor/xtube.py

@@ -6,6 +6,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
+    js_to_json,
     orderedSet,
     parse_duration,
     sanitized_Request,
@@ -37,6 +38,22 @@ class XTubeIE(InfoExtractor):
             'comment_count': int,
             'age_limit': 18,
         }
+    }, {
+        # FLV videos with duplicated formats
+        'url': 'http://www.xtube.com/video-watch/A-Super-Run-Part-1-YT-9299752',
+        'md5': 'a406963eb349dd43692ec54631efd88b',
+        'info_dict': {
+            'id': '9299752',
+            'display_id': 'A-Super-Run-Part-1-YT',
+            'ext': 'flv',
+            'title': 'A Super Run - Part 1 (YT)',
+            'description': 'md5:ca0d47afff4a9b2942e4b41aa970fd93',
+            'uploader': 'tshirtguy59',
+            'duration': 579,
+            'view_count': int,
+            'comment_count': int,
+            'age_limit': 18,
+        },
     }, {
         # new URL schema
         'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
@@ -68,8 +85,9 @@ class XTubeIE(InfoExtractor):
             })
 
         sources = self._parse_json(self._search_regex(
-            r'(["\'])sources\1\s*:\s*(?P<sources>{.+?}),',
-            webpage, 'sources', group='sources'), video_id)
+            r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
+            webpage, 'sources', group='sources'), video_id,
+            transform_source=js_to_json)
 
         formats = []
         for format_id, format_url in sources.items():
@@ -78,6 +96,7 @@ class XTubeIE(InfoExtractor):
                 'format_id': format_id,
                 'height': int_or_none(format_id),
             })
+        self._remove_duplicate_formats(formats)
         self._sort_formats(formats)
 
         title = self._search_regex(

youtube_dl/extractor/xvideos.py

@@ -6,8 +6,10 @@ from .common import InfoExtractor
 from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     clean_html,
-    ExtractorError,
     determine_ext,
+    ExtractorError,
+    int_or_none,
+    parse_duration,
 )
 
 
@@ -20,6 +22,7 @@ class XVideosIE(InfoExtractor):
             'id': '4588838',
             'ext': 'mp4',
             'title': 'Biker Takes his Girl',
+            'duration': 108,
             'age_limit': 18,
         }
     }
@@ -36,6 +39,11 @@ class XVideosIE(InfoExtractor):
             r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
         video_thumbnail = self._search_regex(
             r'url_bigthumb=(.+?)&amp', webpage, 'thumbnail', fatal=False)
+        video_duration = int_or_none(self._og_search_property(
+            'duration', webpage, default=None)) or parse_duration(
+            self._search_regex(
+                r'<span[^>]+class=["\']duration["\'][^>]*>.*?(\d[^<]+)',
+                webpage, 'duration', fatal=False))
 
         formats = []
 
@@ -67,6 +75,7 @@ class XVideosIE(InfoExtractor):
             'id': video_id,
             'formats': formats,
             'title': video_title,
+            'duration': video_duration,
             'thumbnail': video_thumbnail,
             'age_limit': 18,
         }

youtube_dl/extractor/yandexmusic.py

@@ -234,7 +234,8 @@ class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE):
                 'overembed': 'false',
             })['playlist']
 
-        tracks, track_ids = playlist['tracks'], map(compat_str, playlist['trackIds'])
+        tracks = playlist['tracks']
+        track_ids = [compat_str(track_id) for track_id in playlist['trackIds']]
 
         # tracks dictionary shipped with playlist.jsx API is limited to 150 tracks,
         # missing tracks should be retrieved manually.

youtube_dl/extractor/youtube.py

@@ -38,7 +38,6 @@ from ..utils import (
     parse_duration,
     remove_quotes,
     remove_start,
-    sanitized_Request,
     smuggle_url,
     str_to_int,
     try_get,
@@ -54,7 +53,11 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
     """Provide base functions for Youtube extractors"""
     _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
     _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
-    _PASSWORD_CHALLENGE_URL = 'https://accounts.google.com/signin/challenge/sl/password'
+
+    _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup'
+    _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge'
+    _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
+
     _NETRC_MACHINE = 'youtube'
     # If True it will raise an error if no login info is provided
     _LOGIN_REQUIRED = False
@@ -96,72 +99,150 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
 
         login_form = self._hidden_inputs(login_page)
 
-        login_form.update({
-            'checkConnection': 'youtube',
-            'Email': username,
-            'Passwd': password,
-        })
-
-        login_results = self._download_webpage(
-            self._PASSWORD_CHALLENGE_URL, None,
-            note='Logging in', errnote='unable to log in', fatal=False,
-            data=urlencode_postdata(login_form))
-        if login_results is False:
-            return False
-
-        error_msg = self._html_search_regex(
-            r'<[^>]+id="errormsg_0_Passwd"[^>]*>([^<]+)<',
-            login_results, 'error message', default=None)
-        if error_msg:
-            raise ExtractorError('Unable to login: %s' % error_msg, expected=True)
-
-        if re.search(r'id="errormsg_0_Passwd"', login_results) is not None:
-            raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True)
-
-        # Two-Factor
-        # TODO add SMS and phone call support - these require making a request and then prompting the user
-
-        if re.search(r'(?i)<form[^>]+id="challenge"', login_results) is not None:
-            tfa_code = self._get_tfa_info('2-step verification code')
-
-            if not tfa_code:
-                self._downloader.report_warning(
-                    'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
-                    '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
-                return False
-
-            tfa_code = remove_start(tfa_code, 'G-')
-
-            tfa_form_strs = self._form_hidden_inputs('challenge', login_results)
-
-            tfa_form_strs.update({
-                'Pin': tfa_code,
-                'TrustDevice': 'on',
+        def req(url, f_req, note, errnote):
+            data = login_form.copy()
+            data.update({
+                'pstMsg': 1,
+                'checkConnection': 'youtube',
+                'checkedDomains': 'youtube',
+                'hl': 'en',
+                'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
+                'f.req': json.dumps(f_req),
+                'flowName': 'GlifWebSignIn',
+                'flowEntry': 'ServiceLogin',
             })
+            return self._download_json(
+                url, None, note=note, errnote=errnote,
+                transform_source=lambda s: re.sub(r'^[^[]*', '', s),
+                fatal=False,
+                data=urlencode_postdata(data), headers={
+                    'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
+                    'Google-Accounts-XSRF': 1,
+                })
 
-            tfa_data = urlencode_postdata(tfa_form_strs)
+        def warn(message):
+            self._downloader.report_warning(message)
 
-            tfa_req = sanitized_Request(self._TWOFACTOR_URL, tfa_data)
-            tfa_results = self._download_webpage(
-                tfa_req, None,
-                note='Submitting TFA code', errnote='unable to submit tfa', fatal=False)
+        lookup_req = [
+            username,
+            None, [], None, 'US', None, None, 2, False, True,
+            [
+                None, None,
+                [2, 1, None, 1,
+                 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn',
+                 None, [], 4],
+                1, [None, None, []], None, None, None, True
+            ],
+            username,
+        ]
 
-            if tfa_results is False:
-                return False
+        lookup_results = req(
+            self._LOOKUP_URL, lookup_req,
+            'Looking up account info', 'Unable to look up account info')
 
-            if re.search(r'(?i)<form[^>]+id="challenge"', tfa_results) is not None:
-                self._downloader.report_warning('Two-factor code expired or invalid. Please try again, or use a one-use backup code instead.')
-                return False
-            if re.search(r'(?i)<form[^>]+id="gaia_loginform"', tfa_results) is not None:
-                self._downloader.report_warning('unable to log in - did the page structure change?')
-                return False
-            if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None:
-                self._downloader.report_warning('Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.')
-                return False
-
-        if re.search(r'(?i)<form[^>]+id="gaia_loginform"', login_results) is not None:
-            self._downloader.report_warning('unable to log in: bad username or password')
+        if lookup_results is False:
             return False
+
+        user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
+        if not user_hash:
+            warn('Unable to extract user hash')
+            return False
+
+        challenge_req = [
+            user_hash,
+            None, 1, None, [1, None, None, None, [password, None, True]],
+            [
+                None, None, [2, 1, None, 1, 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn', None, [], 4],
+                1, [None, None, []], None, None, None, True
+            ]]
+
+        challenge_results = req(
+            self._CHALLENGE_URL, challenge_req,
+            'Logging in', 'Unable to log in')
+
+        if challenge_results is False:
+            return
+
+        login_res = try_get(challenge_results, lambda x: x[0][5], list)
+        if login_res:
+            login_msg = try_get(login_res, lambda x: x[5], compat_str)
+            warn(
+                'Unable to login: %s' % 'Invalid password'
+                if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
+            return False
+
+        res = try_get(challenge_results, lambda x: x[0][-1], list)
+        if not res:
+            warn('Unable to extract result entry')
+            return False
+
+        tfa = try_get(res, lambda x: x[0][0], list)
+        if tfa:
+            tfa_str = try_get(tfa, lambda x: x[2], compat_str)
+            if tfa_str == 'TWO_STEP_VERIFICATION':
+                # SEND_SUCCESS - TFA code has been successfully sent to phone
+                # QUOTA_EXCEEDED - reached the limit of TFA codes
+                status = try_get(tfa, lambda x: x[5], compat_str)
+                if status == 'QUOTA_EXCEEDED':
+                    warn('Exceeded the limit of TFA codes, try later')
+                    return False
+
+                tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
+                if not tl:
+                    warn('Unable to extract TL')
+                    return False
+
+                tfa_code = self._get_tfa_info('2-step verification code')
+
+                if not tfa_code:
+                    warn(
+                        'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
+                        '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
+                    return False
+
+                tfa_code = remove_start(tfa_code, 'G-')
+
+                tfa_req = [
+                    user_hash, None, 2, None,
+                    [
+                        9, None, None, None, None, None, None, None,
+                        [None, tfa_code, True, 2]
+                    ]]
+
+                tfa_results = req(
+                    self._TFA_URL.format(tl), tfa_req,
+                    'Submitting TFA code', 'Unable to submit TFA code')
+
+                if tfa_results is False:
+                    return False
+
+                tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
+                if tfa_res:
+                    tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
+                    warn(
+                        'Unable to finish TFA: %s' % 'Invalid TFA code'
+                        if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
+                    return False
+
+                check_cookie_url = try_get(
+                    tfa_results, lambda x: x[0][-1][2], compat_str)
+        else:
+            check_cookie_url = try_get(res, lambda x: x[2], compat_str)
+
+        if not check_cookie_url:
+            warn('Unable to extract CheckCookie URL')
+            return False
+
+        check_cookie_results = self._download_webpage(
+            check_cookie_url, None, 'Checking cookie', fatal=False)
+
+        if check_cookie_results is False:
+            return False
+
+        if 'https://myaccount.google.com/' not in check_cookie_results:
+            warn('Unable to log in')
+            return False
+
         return True
 
     def _real_initialize(self):
@@ -963,7 +1044,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
     def _extract_signature_function(self, video_id, player_url, example_sig):
         id_m = re.match(
-            r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|/base)?\.(?P<ext>[a-z]+)$',
+            r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
             player_url)
         if not id_m:
             raise ExtractorError('Cannot identify player %r' % player_url)
@@ -1257,6 +1338,35 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
         return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
 
+    @staticmethod
+    def _extract_chapters(description, duration):
+        if not description:
+            return None
+        chapter_lines = re.findall(
+            r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)',
+            description)
+        if not chapter_lines:
+            return None
+        chapters = []
+        for next_num, (chapter_line, time_point) in enumerate(
+                chapter_lines, start=1):
+            start_time = parse_duration(time_point)
+            if start_time is None:
+                continue
+            end_time = (duration if next_num == len(chapter_lines)
+                        else parse_duration(chapter_lines[next_num][1]))
+            if end_time is None:
+                continue
+            chapter_title = re.sub(
+                r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
+            chapter_title = re.sub(r'\s+', ' ', chapter_title)
+            chapters.append({
+                'start_time': start_time,
+                'end_time': end_time,
+                'title': chapter_title,
+            })
+        return chapters
+
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})
 
@@ -1399,9 +1509,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             video_title = '_'
 
         # description
-        video_description = get_element_by_id("eow-description", video_webpage)
+        description_original = video_description = get_element_by_id("eow-description", video_webpage)
         if video_description:
-            video_description = re.sub(r'''(?x)
+            description_original = video_description = re.sub(r'''(?x)
                 <a\s+
                     (?:[a-zA-Z-]+="[^"]*"\s+)*?
                     (?:title|href)="([^"]+)"\s+
@@ -1558,6 +1668,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         if self._downloader.params.get('writeannotations', False):
             video_annotations = self._extract_annotations(video_id)
 
+        chapters = self._extract_chapters(description_original, video_duration)
+
         if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
             self.report_rtmp_download()
             formats = [{
@@ -1629,7 +1741,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                                 player_desc = 'flash player %s' % player_version
                             else:
                                 player_version = self._search_regex(
-                                    [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r'(?:www|player)-([^/]+)/base\.js'],
+                                    [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
+                                     r'(?:www|player)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'],
                                     player_url,
                                     'html5 player', fatal=False)
                                 player_desc = 'html5 player %s' % player_version
@@ -1789,6 +1902,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'duration': video_duration,
             'age_limit': 18 if age_gate else 0,
             'annotations': video_annotations,
+            'chapters': chapters,
             'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
             'view_count': view_count,
             'like_count': like_count,

youtube_dl/extractor/zaq1.py

@@ -0,0 +1,101 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unified_timestamp,
+)
+
+
+class Zaq1IE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?zaq1\.pl/video/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'http://zaq1.pl/video/xev0e',
+        'md5': '24a5eb3f052e604ae597c4d0d19b351e',
+        'info_dict': {
+            'id': 'xev0e',
+            'title': 'DJ NA WESELE. TANIEC Z FIGURAMI.węgrów/sokołów podlaski/siedlce/mińsk mazowiecki/warszawa',
+            'description': 'www.facebook.com/weseledjKontakt: 728 448 199 / 505 419 147',
+            'ext': 'mp4',
+            'duration': 511,
+            'timestamp': 1490896361,
+            'uploader': 'Anonim',
+            'upload_date': '20170330',
+            'view_count': int,
+        }
+    }, {
+        # malformed JSON-LD
+        'url': 'http://zaq1.pl/video/x81vn',
+        'info_dict': {
+            'id': 'x81vn',
+            'title': 'SEKRETNE ŻYCIE WALTERA MITTY',
+            'ext': 'mp4',
+            'duration': 6234,
+            'timestamp': 1493494860,
+            'uploader': 'Anonim',
+            'upload_date': '20170429',
+            'view_count': int,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'expected_warnings': ['Failed to parse JSON'],
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._search_regex(
+            r'data-video-url=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+            'video url', group='url')
+
+        info = self._search_json_ld(webpage, video_id, fatal=False)
+
+        def extract_data(field, name, fatal=False):
+            return self._search_regex(
+                r'data-%s=(["\'])(?P<field>(?:(?!\1).)+)\1' % field,
+                webpage, field, fatal=fatal, group='field')
+
+        if not info.get('title'):
+            info['title'] = extract_data('file-name', 'title', fatal=True)
+
+        if not info.get('duration'):
+            info['duration'] = int_or_none(extract_data('duration', 'duration'))
+
+        if not info.get('thumbnail'):
+            info['thumbnail'] = extract_data('photo-url', 'thumbnail')
+
+        if not info.get('timestamp'):
+            info['timestamp'] = unified_timestamp(self._html_search_meta(
+                'uploadDate', webpage, 'timestamp'))
+
+        if not info.get('interactionCount'):
+            info['view_count'] = int_or_none(self._html_search_meta(
+                'interactionCount', webpage, 'view count'))
+
+        uploader = self._html_search_regex(
+            r'Wideo dodał:\s*<a[^>]*>([^<]+)</a>', webpage, 'uploader',
+            fatal=False)
+
+        width = int_or_none(self._html_search_meta(
+            'width', webpage, fatal=False))
+        height = int_or_none(self._html_search_meta(
+            'height', webpage, fatal=False))
+
+        info.update({
+            'id': video_id,
+            'formats': [{
+                'url': video_url,
+                'width': width,
+                'height': height,
+                'http_headers': {
+                    'Referer': url,
+                },
+            }],
+            'uploader': uploader,
+        })
+
+        return info

youtube_dl/postprocessor/ffmpeg.py

@@ -4,6 +4,7 @@ import io
 import os
 import subprocess
 import time
+import re
 
 
 from .common import AudioConversionError, PostProcessor
@@ -22,6 +23,7 @@ from ..utils import (
     subtitles_filename,
     dfxp2srt,
     ISO639Utils,
+    replace_extension,
 )
 
 
@@ -429,17 +431,40 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
 
         filename = info['filepath']
         temp_filename = prepend_extension(filename, 'temp')
+        in_filenames = [filename]
+        options = []
 
         if info['ext'] == 'm4a':
-            options = ['-vn', '-acodec', 'copy']
+            options.extend(['-vn', '-acodec', 'copy'])
         else:
-            options = ['-c', 'copy']
+            options.extend(['-c', 'copy'])
 
         for (name, value) in metadata.items():
             options.extend(['-metadata', '%s=%s' % (name, value)])
 
+        chapters = info.get('chapters', [])
+        if chapters:
+            metadata_filename = encodeFilename(replace_extension(filename, 'meta'))
+            with io.open(metadata_filename, 'wt', encoding='utf-8') as f:
+                def ffmpeg_escape(text):
+                    return re.sub(r'(=|;|#|\\|\n)', r'\\\1', text)
+
+                metadata_file_content = ';FFMETADATA1\n'
+                for chapter in chapters:
+                    metadata_file_content += '[CHAPTER]\nTIMEBASE=1/1000\n'
+                    metadata_file_content += 'START=%d\n' % (chapter['start_time'] * 1000)
+                    metadata_file_content += 'END=%d\n' % (chapter['end_time'] * 1000)
+                    chapter_title = chapter.get('title')
+                    if chapter_title:
+                        metadata_file_content += 'title=%s\n' % ffmpeg_escape(chapter_title)
+                f.write(metadata_file_content)
+                in_filenames.append(metadata_filename)
+                options.extend(['-map_metadata', '1'])
+
         self._downloader.to_screen('[ffmpeg] Adding metadata to \'%s\'' % filename)
-        self.run_ffmpeg(filename, temp_filename, options)
+        self.run_ffmpeg_multiple_files(in_filenames, temp_filename, options)
+        if chapters:
+            os.remove(metadata_filename)
         os.remove(encodeFilename(filename))
         os.rename(encodeFilename(temp_filename), encodeFilename(filename))
         return [], info

youtube_dl/utils.py

@@ -11,6 +11,7 @@ import contextlib
 import ctypes
 import datetime
 import email.utils
+import email.header
 import errno
 import functools
 import gzip
@@ -421,8 +422,8 @@ def clean_html(html):
 
     # Newline vs <br />
     html = html.replace('\n', ' ')
-    html = re.sub(r'\s*<\s*br\s*/?\s*>\s*', '\n', html)
-    html = re.sub(r'<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)
+    html = re.sub(r'(?u)\s*<\s*br\s*/?\s*>\s*', '\n', html)
+    html = re.sub(r'(?u)<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)
     # Strip html tags
     html = re.sub('<.*?>', '', html)
     # Replace html entities
@@ -1194,6 +1195,11 @@ def unified_timestamp(date_str, day_first=True):
     # Remove AM/PM + timezone
     date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str)
 
+    # Remove unrecognized timezones from ISO 8601 alike timestamps
+    m = re.search(r'\d{1,2}:\d{1,2}(?:\.\d+)?(?P<tz>\s*[A-Z]+)$', date_str)
+    if m:
+        date_str = date_str[:-len(m.group('tz'))]
+
     for expression in date_formats(day_first):
         try:
             dt = datetime.datetime.strptime(date_str, expression) - timezone + datetime.timedelta(hours=pm_delta)
@@ -2092,6 +2098,58 @@ def update_Request(req, url=None, data=None, headers={}, query={}):
     return new_req
 
 
+def _multipart_encode_impl(data, boundary):
+    content_type = 'multipart/form-data; boundary=%s' % boundary
+
+    out = b''
+    for k, v in data.items():
+        out += b'--' + boundary.encode('ascii') + b'\r\n'
+        if isinstance(k, compat_str):
+            k = k.encode('utf-8')
+        if isinstance(v, compat_str):
+            v = v.encode('utf-8')
+        # RFC 2047 requires non-ASCII field names to be encoded, while RFC 7578
+        # suggests sending UTF-8 directly. Firefox sends UTF-8, too
+        content = b'Content-Disposition: form-data; name="' + k + b'"\r\n\r\n' + v + b'\r\n'
+        if boundary.encode('ascii') in content:
+            raise ValueError('Boundary overlaps with data')
+        out += content
+
+    out += b'--' + boundary.encode('ascii') + b'--\r\n'
+
+    return out, content_type
+
+
+def multipart_encode(data, boundary=None):
+    '''
+    Encode a dict to RFC 7578-compliant form-data
+
+    data:
+        A dict where keys and values can be either Unicode or bytes-like
+        objects.
+    boundary:
+        If specified a Unicode object, it's used as the boundary. Otherwise
+        a random boundary is generated.
+
+    Reference: https://tools.ietf.org/html/rfc7578
+    '''
+    has_specified_boundary = boundary is not None
+
+    while True:
+        if boundary is None:
+            boundary = '---------------' + str(random.randrange(0x0fffffff, 0xffffffff))
+
+        try:
+            out, content_type = _multipart_encode_impl(data, boundary)
+            break
+        except ValueError:
+            if has_specified_boundary:
+                raise
+            boundary = None
+
+    return out, content_type
+
+
 def dict_get(d, key_or_keys, default=None, skip_false_values=True):
     if isinstance(key_or_keys, (list, tuple)):
         for key in key_or_keys:
@@ -2273,10 +2331,8 @@ def mimetype2ext(mt):
     return {
         '3gpp': '3gp',
         'smptett+xml': 'tt',
-        'srt': 'srt',
         'ttaf+xml': 'dfxp',
         'ttml+xml': 'ttml',
-        'vtt': 'vtt',
         'x-flv': 'flv',
         'x-mp4-fragmented': 'mp4',
         'x-ms-wmv': 'wmv',
@@ -2284,11 +2340,11 @@ def mimetype2ext(mt):
         'x-mpegurl': 'm3u8',
         'vnd.apple.mpegurl': 'm3u8',
         'dash+xml': 'mpd',
-        'f4m': 'f4m',
         'f4m+xml': 'f4m',
         'hds+xml': 'f4m',
         'vnd.ms-sstr+xml': 'ism',
         'quicktime': 'mov',
+        'mp2t': 'ts',
     }.get(res, res)
 
 
@@ -3757,3 +3813,11 @@ def write_xattr(path, key, value):
                         "Couldn't find a tool to set the xattrs. "
                         "Install either the python 'xattr' module, "
                         "or the 'xattr' binary.")
+
+
+def random_birthday(year_field, month_field, day_field):
+    return {
+        year_field: str(random.randint(1950, 1995)),
+        month_field: str(random.randint(1, 12)),
+        day_field: str(random.randint(1, 31)),
+    }

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2017.04.26'
+__version__ = '2017.05.07'