Compare commits

..

44 Commits

Author SHA1 Message Date
Sergey M․
1fa0dce2c0 release 2017.12.10 2017-12-10 23:18:53 +07:00
Sergey M․
fa1dd6d2cd [ChangeLog] Actualize 2017-12-10 23:15:24 +07:00
Sergey M․
c38970ca10 [culturebox] Improve video id extraction (closes #14947) 2017-12-10 22:46:21 +07:00
Remita Amine
51f2863357 [twitter] improve extraction(closes #14197) 2017-12-10 14:11:09 +01:00
Sergey M․
913b61eeee [udemy] Extract more HLS formats 2017-12-09 20:02:54 +07:00
Sergey M․
6f1ec339a0 [udemy] Improve course id extraction (closes #14938) 2017-12-09 20:02:49 +07:00
Sergey M․
a3de5e6c0e [stretchinternet] Fix issues and improve (closes #14576) 2017-12-09 17:59:08 +07:00
Andrew Bottom
f4cc03d60b [stretchinternet] Add extractor 2017-12-09 17:58:49 +07:00
Sergey M․
2a57b62b80 [ellentube] Fix issues, improve and simplify (closes #14570) 2017-12-09 02:16:54 +07:00
Alex Seiler
e2707a832c [ellentube] Fix extraction (closes #14407) 2017-12-09 02:16:48 +07:00
Sergey M․
1115271ac6 [raiplay:playlist] Fix issues and improve (closes #14563) 2017-12-09 00:48:04 +07:00
Timendum
d21d0ba6c1 [raiplay:playlist] Add extractor 2017-12-09 00:47:40 +07:00
Sergey M․
a670b1ba26 [README.md] Add is_live, start_time and end_time to output template section (closes #14926) 2017-12-07 22:16:41 +07:00
Remita Amine
1bd4fc96e6 [sonyliv] extract higher quality formats and bypass geo restriction(closes #14922) 2017-12-07 08:46:30 +01:00
Remita Amine
684ae10236 [fox] add support for adobe pass auth and extract subtitles(close #14489)(closes #14205) 2017-12-06 22:56:14 +01:00
Remita Amine
3c4fbfeca2 [dailymotion] remove dailymotion cloud extractor(closes #6794)
https://web.archive.org/web/20160312110217/https://www.dmcloud.net/
2017-12-06 10:56:48 +01:00
Windom
b271e33526 [xhamster] Add support for mobile URLs and fix thumbnail extraction 2017-12-06 00:08:31 +07:00
Sergey M․
d3f8b76b69 [extractor/generic] Fix typo (closes #14902)
Don't pass video_id as mpd_id
2017-12-05 23:11:15 +07:00
Sergey M․
91328f26b0 [ard] Skip invalid stream URLs (closes #14906) 2017-12-05 23:01:57 +07:00
Sergey M․
61d18c8a4b [porncom] Fix metadata extraction (closes #14911) 2017-12-05 22:42:02 +07:00
Sergey M․
c94427dd60 [pluralsight] Detect agreement request (#14913) 2017-12-05 22:34:56 +07:00
Remita Amine
d4f05d4731 [utils] add sami mimetype to mimetype2ext 2017-12-03 00:04:43 +01:00
Remita Amine
d7df308981 [toutv] fix login(closes 14614) 2017-12-02 20:22:40 +01:00
Sergey M․
0d56eddc59 release 2017.12.02 2017-12-02 21:34:34 +07:00
Sergey M․
e25ee72657 [ChangeLog] Actualize 2017-12-02 21:29:06 +07:00
Sergey M․
78593e294c Add references for #14844 2017-12-02 21:22:43 +07:00
Sergey M․
593f2f7989 [downloader/fragment] Commit part file after each fragment
In order to obtain correct resume_len on next iteration
2017-12-02 21:21:11 +07:00
Sergey M․
603fc4e0ea [extractor/common] Add durations for DASH fragments with bare SegmentURLs 2017-12-02 21:21:01 +07:00
Petr Novak
41bf647e89 [extractor/common] Add support for DASH manifests with SegmentLists with bare SegmentURLs 2017-12-02 21:16:36 +07:00
Sergey M․
fea92aa65d [xhamster] Fix extraction (closes #14884) 2017-12-02 19:04:59 +07:00
zcanfly
0981585bef [youku] Update ccode (closes #14872) 2017-12-02 18:16:22 +07:00
Remita Amine
f5ac68d88f [mnet] fix format extraction(fixes #14883) 2017-11-30 23:45:33 +01:00
Remita Amine
1663b32946 [xiami] add Referer header to api request 2017-11-29 20:36:55 +01:00
Remita Amine
5ea765fb72 [mtv] correct scc extention in extracted subtitles(closes #13730) 2017-11-29 17:50:38 +01:00
Remita Amine
fb61b57d0f [vvvvid] fix extraction for kenc videos(fixes #13406) 2017-11-29 16:09:45 +01:00
Remita Amine
07cf18b9c5 [br] add support for BR Mediathek videos(fixes #14560)(fixes #14788) 2017-11-29 14:21:38 +01:00
Remita Amine
5f699251e9 [daisuki] add support for motto.daisuki.com(fixes #14681) 2017-11-28 10:57:22 +01:00
Remita Amine
a3474aa59e [Odnoklassniki] fix api metadata request(fixes #14862) 2017-11-28 09:04:51 +01:00
Remita Amine
115afb77ec [itv] update hls formats extraction 2017-11-27 21:59:27 +01:00
Remita Amine
53f024e7c5 [pbs] add another media id regex 2017-11-27 16:55:27 +01:00
Remita Amine
ffe6979ef9 [utils] add hvc1 codec code to parse_codecs 2017-11-27 16:55:27 +01:00
Yen Chi Hsuan
dafb4c6647 [Makefile] Include setup.cfg in the tarball (closes #14857) 2017-11-27 22:49:35 +08:00
Yen Chi Hsuan
82a62de192 [Makefile,devscripts/run_tests.sh] Actually exclude network tests
Closes #14858
2017-11-27 21:32:06 +08:00
Yen Chi Hsuan
f58a506044 [test_InfoExtractor] Fix flake8 2017-11-27 21:30:47 +08:00
39 changed files with 1128 additions and 399 deletions

View File

@@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.11.26*. 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 **2017.11.26**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.12.10*. 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 **2017.12.10**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
[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 2017.11.26
[debug] youtube-dl version 2017.12.10
[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: {}

View File

@@ -1,3 +1,53 @@
version 2017.12.10
Core
+ [utils] Add sami mimetype to mimetype2ext
Extractors
* [culturebox] Improve video id extraction (#14947)
* [twitter] Improve extraction (#14197)
+ [udemy] Extract more HLS formats
* [udemy] Improve course id extraction (#14938)
+ [stretchinternet] Add support for portal.stretchinternet.com (#14576)
* [ellentube] Fix extraction (#14407, #14570)
+ [raiplay:playlist] Add support for playlists (#14563)
* [sonyliv] Bypass geo restriction
* [sonyliv] Extract higher quality formats (#14922)
* [fox] Extract subtitles
+ [fox] Add support for Adobe Pass authentication (#14205, #14489)
- [dailymotion:cloud] Remove extractor (#6794)
* [xhamster] Fix thumbnail extraction (#14780)
+ [xhamster] Add support for mobile URLs (#14780)
* [generic] Don't pass video id as mpd id while extracting DASH (#14902)
* [ard] Skip invalid stream URLs (#14906)
* [porncom] Fix metadata extraction (#14911)
* [pluralsight] Detect agreement request (#14913)
* [toutv] Fix login (#14614)
version 2017.12.02
Core
+ [downloader/fragment] Commit part file after each fragment
+ [extractor/common] Add durations for DASH fragments with bare SegmentURLs
+ [extractor/common] Add support for DASH manifests with SegmentLists with
bare SegmentURLs (#14844)
+ [utils] Add hvc1 codec code to parse_codecs
Extractors
* [xhamster] Fix extraction (#14884)
* [youku] Update ccode (#14872)
* [mnet] Fix format extraction (#14883)
+ [xiami] Add Referer header to API request
* [mtv] Correct scc extention in extracted subtitles (#13730)
* [vvvvid] Fix extraction for kenc videos (#13406)
+ [br] Add support for BR Mediathek videos (#14560, #14788)
+ [daisuki] Add support for motto.daisuki.com (#14681)
* [odnoklassniki] Fix API metadata request (#14862)
* [itv] Fix HLS formats extraction
+ [pbs] Add another media id regular expression
version 2017.11.26
Core

View File

@@ -36,8 +36,17 @@ test:
ot: offlinetest
# Keep this list in sync with devscripts/run_tests.sh
offlinetest: codetest
$(PYTHON) -m nose --verbose test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py --exclude test_iqiyi_sdk_interpreter.py --exclude test_socks.py
$(PYTHON) -m nose --verbose test \
--exclude test_age_restriction.py \
--exclude test_download.py \
--exclude test_iqiyi_sdk_interpreter.py \
--exclude test_socks.py \
--exclude test_subtitles.py \
--exclude test_write_annotations.py \
--exclude test_youtube_lists.py \
--exclude test_youtube_signature.py
tar: youtube-dl.tar.gz
@@ -115,5 +124,5 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-
bin devscripts test youtube_dl docs \
ChangeLog LICENSE README.md README.txt \
Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion \
youtube-dl.zsh youtube-dl.fish setup.py \
youtube-dl.zsh youtube-dl.fish setup.py setup.cfg \
youtube-dl

View File

@@ -511,6 +511,9 @@ The basic usage is not to set any template arguments when downloading a single f
- `average_rating` (numeric): Average rating give by users, the scale used depends on the webpage
- `comment_count` (numeric): Number of comments on the video
- `age_limit` (numeric): Age restriction for the video (years)
- `is_live` (boolean): Whether this video is a live stream or a fixed-length video
- `start_time` (numeric): Time in seconds where the reproduction should start, as specified in the URL
- `end_time` (numeric): Time in seconds where the reproduction should end, as specified in the URL
- `format` (string): A human-readable description of the format
- `format_id` (string): Format code specified by `--format`
- `format_note` (string): Additional info about the format

View File

@@ -1,6 +1,7 @@
#!/bin/bash
DOWNLOAD_TESTS="age_restriction|download|subtitles|write_annotations|iqiyi_sdk_interpreter|youtube_lists"
# Keep this list in sync with the `offlinetest` target in Makefile
DOWNLOAD_TESTS="age_restriction|download|iqiyi_sdk_interpreter|socks|subtitles|write_annotations|youtube_lists|youtube_signature"
test_set=""
multiprocess_args=""

View File

@@ -112,11 +112,12 @@
- **BokeCC**
- **BostonGlobe**
- **Bpb**: Bundeszentrale für politische Bildung
- **BR**: Bayerischer Rundfunk Mediathek
- **BR**: Bayerischer Rundfunk
- **BravoTV**
- **Break**
- **brightcove:legacy**
- **brightcove:new**
- **BRMediathek**: Bayerischer Rundfunk Mediathek
- **bt:article**: Bergens Tidende Articles
- **bt:vestlendingen**: Bergens Tidende - Vestlendingen
- **BuzzFeed**
@@ -197,9 +198,8 @@
- **dailymotion**
- **dailymotion:playlist**
- **dailymotion:user**
- **DailymotionCloud**
- **Daisuki**
- **DaisukiPlaylist**
- **DaisukiMotto**
- **DaisukiMottoPlaylist**
- **daum.net**
- **daum.net:clip**
- **daum.net:playlist**
@@ -242,8 +242,9 @@
- **eHow**
- **Einthusan**
- **eitb.tv**
- **EllenTV**
- **EllenTV:clips**
- **EllenTube**
- **EllenTubePlaylist**
- **EllenTubeVideo**
- **ElPais**: El País
- **Embedly**
- **EMPFlix**
@@ -661,6 +662,7 @@
- **Rai**
- **RaiPlay**
- **RaiPlayLive**
- **RaiPlayPlaylist**
- **RBMARadio**
- **RDS**: RDS.ca
- **RedBullTV**
@@ -780,6 +782,7 @@
- **streamcloud.eu**
- **StreamCZ**
- **StreetVoice**
- **StretchInternet**
- **SunPorno**
- **SVT**
- **SVTPlay**: SVT Play and Öppet arkiv

View File

@@ -562,7 +562,89 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
'width': 1920,
'height': 1080,
}]
),
), (
# https://github.com/rg3/youtube-dl/pull/14844
'urls_only',
'http://unknown/manifest.mpd',
[{
'manifest_url': 'http://unknown/manifest.mpd',
'ext': 'mp4',
'format_id': 'h264_aac_144p_m4s',
'format_note': 'DASH video',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'avc3.42c01e',
'tbr': 200,
'width': 256,
'height': 144,
}, {
'manifest_url': 'http://unknown/manifest.mpd',
'ext': 'mp4',
'format_id': 'h264_aac_240p_m4s',
'format_note': 'DASH video',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'avc3.42c01e',
'tbr': 400,
'width': 424,
'height': 240,
}, {
'manifest_url': 'http://unknown/manifest.mpd',
'ext': 'mp4',
'format_id': 'h264_aac_360p_m4s',
'format_note': 'DASH video',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'avc3.42c01e',
'tbr': 800,
'width': 640,
'height': 360,
}, {
'manifest_url': 'http://unknown/manifest.mpd',
'ext': 'mp4',
'format_id': 'h264_aac_480p_m4s',
'format_note': 'DASH video',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'avc3.42c01e',
'tbr': 1200,
'width': 856,
'height': 480,
}, {
'manifest_url': 'http://unknown/manifest.mpd',
'ext': 'mp4',
'format_id': 'h264_aac_576p_m4s',
'format_note': 'DASH video',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'avc3.42c01e',
'tbr': 1600,
'width': 1024,
'height': 576,
}, {
'manifest_url': 'http://unknown/manifest.mpd',
'ext': 'mp4',
'format_id': 'h264_aac_720p_m4s',
'format_note': 'DASH video',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'avc3.42c01e',
'tbr': 2400,
'width': 1280,
'height': 720,
}, {
'manifest_url': 'http://unknown/manifest.mpd',
'ext': 'mp4',
'format_id': 'h264_aac_1080p_m4s',
'format_note': 'DASH video',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'avc3.42c01e',
'tbr': 4400,
'width': 1920,
'height': 1080,
}]
)
]
for mpd_file, mpd_url, expected_formats in _TEST_CASES:
@@ -601,5 +683,6 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
self.ie._sort_formats(formats)
expect_value(self, formats, expected_formats, None)
if __name__ == '__main__':
unittest.main()

218
test/testdata/mpd/urls_only.mpd vendored Normal file
View File

@@ -0,0 +1,218 @@
<?xml version="1.0" ?>
<MPD maxSegmentDuration="PT0H0M10.000S" mediaPresentationDuration="PT0H4M1.728S" minBufferTime="PT1.500S" profiles="urn:mpeg:dash:profile:isoff-main:2011" type="static" xmlns="urn:mpeg:dash:schema:mpd:2011">
<Period duration="PT0H4M1.728S">
<AdaptationSet bitstreamSwitching="true" lang="und" maxHeight="1080" maxWidth="1920" par="16:9" segmentAlignment="true">
<ContentComponent contentType="video" id="1"/>
<Representation audioSamplingRate="44100" bandwidth="200000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="144" id="h264_aac_144p_m4s" mimeType="video/mp4" sar="1:1" startWithSAP="1" width="256">
<SegmentList duration="10000" timescale="1000">
<Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/init/432f65a0.mp4"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/0/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/1/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/2/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/3/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/4/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/5/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/6/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/7/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/8/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/9/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/10/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/11/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/12/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/13/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/14/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/15/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/16/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/17/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/18/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/19/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/20/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/21/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/22/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/23/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/24/432f65a0.m4s"/>
</SegmentList>
</Representation>
<Representation audioSamplingRate="44100" bandwidth="400000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="240" id="h264_aac_240p_m4s" mimeType="video/mp4" sar="160:159" startWithSAP="1" width="424">
<SegmentList duration="10000" timescale="1000">
<Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/init/432f65a0.mp4"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/0/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/1/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/2/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/3/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/4/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/5/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/6/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/7/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/8/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/9/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/10/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/11/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/12/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/13/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/14/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/15/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/16/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/17/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/18/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/19/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/20/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/21/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/22/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/23/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/24/432f65a0.m4s"/>
</SegmentList>
</Representation>
<Representation audioSamplingRate="44100" bandwidth="800000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="360" id="h264_aac_360p_m4s" mimeType="video/mp4" sar="1:1" startWithSAP="1" width="640">
<SegmentList duration="10000" timescale="1000">
<Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/init/432f65a0.mp4"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/0/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/1/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/2/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/3/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/4/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/5/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/6/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/7/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/8/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/9/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/10/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/11/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/12/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/13/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/14/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/15/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/16/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/17/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/18/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/19/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/20/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/21/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/22/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/23/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/24/432f65a0.m4s"/>
</SegmentList>
</Representation>
<Representation audioSamplingRate="44100" bandwidth="1200000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="480" id="h264_aac_480p_m4s" mimeType="video/mp4" sar="320:321" startWithSAP="1" width="856">
<SegmentList duration="10000" timescale="1000">
<Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/init/432f65a0.mp4"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/0/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/1/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/2/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/3/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/4/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/5/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/6/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/7/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/8/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/9/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/10/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/11/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/12/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/13/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/14/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/15/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/16/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/17/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/18/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/19/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/20/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/21/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/22/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/23/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/24/432f65a0.m4s"/>
</SegmentList>
</Representation>
<Representation audioSamplingRate="44100" bandwidth="1600000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="576" id="h264_aac_576p_m4s" mimeType="video/mp4" sar="1:1" startWithSAP="1" width="1024">
<SegmentList duration="10000" timescale="1000">
<Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/init/432f65a0.mp4"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/0/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/1/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/2/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/3/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/4/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/5/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/6/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/7/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/8/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/9/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/10/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/11/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/12/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/13/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/14/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/15/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/16/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/17/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/18/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/19/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/20/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/21/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/22/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/23/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/24/432f65a0.m4s"/>
</SegmentList>
</Representation>
<Representation audioSamplingRate="44100" bandwidth="2400000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="720" id="h264_aac_720p_m4s" mimeType="video/mp4" sar="1:1" startWithSAP="1" width="1280">
<SegmentList duration="10000" timescale="1000">
<Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/init/432f65a0.mp4"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/0/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/1/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/2/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/3/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/4/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/5/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/6/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/7/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/8/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/9/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/10/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/11/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/12/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/13/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/14/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/15/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/16/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/17/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/18/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/19/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/20/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/21/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/22/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/23/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/24/432f65a0.m4s"/>
</SegmentList>
</Representation>
<Representation audioSamplingRate="44100" bandwidth="4400000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="1080" id="h264_aac_1080p_m4s" mimeType="video/mp4" sar="1:1" startWithSAP="1" width="1920">
<SegmentList duration="10000" timescale="1000">
<Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/init/432f65a0.mp4"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/0/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/1/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/2/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/3/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/4/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/5/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/6/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/7/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/8/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/9/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/10/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/11/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/12/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/13/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/14/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/15/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/16/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/17/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/18/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/19/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/20/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/21/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/22/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/23/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/24/432f65a0.m4s"/>
</SegmentList>
</Representation>
</AdaptationSet>
</Period>
</MPD>

View File

@@ -107,6 +107,7 @@ class FragmentFD(FileDownloader):
def _append_fragment(self, ctx, frag_content):
try:
ctx['dest_stream'].write(frag_content)
ctx['dest_stream'].flush()
finally:
if self.__do_ytdl_file(ctx):
self._write_ytdl_file(ctx)

View File

@@ -5,6 +5,7 @@ import re
from .common import InfoExtractor
from .generic import GenericIE
from ..compat import compat_str
from ..utils import (
determine_ext,
ExtractorError,
@@ -126,6 +127,8 @@ class ARDMediathekIE(InfoExtractor):
quality = stream.get('_quality')
server = stream.get('_server')
for stream_url in stream_urls:
if not isinstance(stream_url, compat_str) or '//' not in stream_url:
continue
ext = determine_ext(stream_url)
if quality != 'auto' and ext in ('f4m', 'm3u8'):
continue
@@ -146,13 +149,11 @@ class ARDMediathekIE(InfoExtractor):
'play_path': stream_url,
'format_id': 'a%s-rtmp-%s' % (num, quality),
}
elif stream_url.startswith('http'):
else:
f = {
'url': stream_url,
'format_id': 'a%s-%s-%s' % (num, ext, quality)
}
else:
continue
m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)\.mp4$', stream_url)
if m:
f.update({

View File

@@ -1,20 +1,23 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
parse_duration,
parse_iso8601,
xpath_element,
xpath_text,
)
class BRIE(InfoExtractor):
IE_DESC = 'Bayerischer Rundfunk Mediathek'
IE_DESC = 'Bayerischer Rundfunk'
_VALID_URL = r'(?P<base_url>https?://(?:www\.)?br(?:-klassik)?\.de)/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html'
_TESTS = [
@@ -123,10 +126,10 @@ class BRIE(InfoExtractor):
for asset in assets.findall('asset'):
format_url = xpath_text(asset, ['downloadUrl', 'url'])
asset_type = asset.get('type')
if asset_type == 'HDS':
if asset_type.startswith('HDS'):
formats.extend(self._extract_f4m_formats(
format_url + '?hdcore=3.2.0', media_id, f4m_id='hds', fatal=False))
elif asset_type == 'HLS':
elif asset_type.startswith('HLS'):
formats.extend(self._extract_m3u8_formats(
format_url, media_id, 'mp4', 'm3u8_native', m3u8_id='hds', fatal=False))
else:
@@ -169,3 +172,140 @@ class BRIE(InfoExtractor):
} for variant in variants.findall('variant') if xpath_text(variant, 'url')]
thumbnails.sort(key=lambda x: x['width'] * x['height'], reverse=True)
return thumbnails
class BRMediathekIE(InfoExtractor):
IE_DESC = 'Bayerischer Rundfunk Mediathek'
_VALID_URL = r'https?://(?:www\.)?br\.de/mediathek/video/[^/?&#]*?-(?P<id>av:[0-9a-f]{24})'
_TESTS = [{
'url': 'https://www.br.de/mediathek/video/gesundheit-die-sendung-vom-28112017-av:5a1e6a6e8fce6d001871cc8e',
'md5': 'fdc3d485835966d1622587d08ba632ec',
'info_dict': {
'id': 'av:5a1e6a6e8fce6d001871cc8e',
'ext': 'mp4',
'title': 'Die Sendung vom 28.11.2017',
'description': 'md5:6000cdca5912ab2277e5b7339f201ccc',
'timestamp': 1511942766,
'upload_date': '20171129',
}
}]
def _real_extract(self, url):
clip_id = self._match_id(url)
clip = self._download_json(
'https://proxy-base.master.mango.express/graphql',
clip_id, data=json.dumps({
"query": """{
viewer {
clip(id: "%s") {
title
description
duration
createdAt
ageRestriction
videoFiles {
edges {
node {
publicLocation
fileSize
videoProfile {
width
height
bitrate
encoding
}
}
}
}
captionFiles {
edges {
node {
publicLocation
}
}
}
teaserImages {
edges {
node {
imageFiles {
edges {
node {
publicLocation
width
height
}
}
}
}
}
}
}
}
}""" % clip_id}).encode(), headers={
'Content-Type': 'application/json',
})['data']['viewer']['clip']
title = clip['title']
formats = []
for edge in clip.get('videoFiles', {}).get('edges', []):
node = edge.get('node', {})
n_url = node.get('publicLocation')
if not n_url:
continue
ext = determine_ext(n_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
n_url, clip_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
else:
video_profile = node.get('videoProfile', {})
tbr = int_or_none(video_profile.get('bitrate'))
format_id = 'http'
if tbr:
format_id += '-%d' % tbr
formats.append({
'format_id': format_id,
'url': n_url,
'width': int_or_none(video_profile.get('width')),
'height': int_or_none(video_profile.get('height')),
'tbr': tbr,
'filesize': int_or_none(node.get('fileSize')),
})
self._sort_formats(formats)
subtitles = {}
for edge in clip.get('captionFiles', {}).get('edges', []):
node = edge.get('node', {})
n_url = node.get('publicLocation')
if not n_url:
continue
subtitles.setdefault('de', []).append({
'url': n_url,
})
thumbnails = []
for edge in clip.get('teaserImages', {}).get('edges', []):
for image_edge in edge.get('node', {}).get('imageFiles', {}).get('edges', []):
node = image_edge.get('node', {})
n_url = node.get('publicLocation')
if not n_url:
continue
thumbnails.append({
'url': n_url,
'width': int_or_none(node.get('width')),
'height': int_or_none(node.get('height')),
})
return {
'id': clip_id,
'title': title,
'description': clip.get('description'),
'duration': int_or_none(clip.get('duration')),
'timestamp': parse_iso8601(clip.get('createdAt')),
'age_limit': int_or_none(clip.get('ageRestriction')),
'formats': formats,
'subtitles': subtitles,
'thumbnails': thumbnails,
}

View File

@@ -1975,6 +1975,22 @@ class InfoExtractor(object):
})
segment_index += 1
representation_ms_info['fragments'] = fragments
elif 'segment_urls' in representation_ms_info:
# Segment URLs with no SegmentTimeline
# Example: https://www.seznam.cz/zpravy/clanek/cesko-zasahne-vitr-o-sile-vichrice-muze-byt-i-zivotu-nebezpecny-39091
# https://github.com/rg3/youtube-dl/pull/14844
fragments = []
segment_duration = float_or_none(
representation_ms_info['segment_duration'],
representation_ms_info['timescale']) if 'segment_duration' in representation_ms_info else None
for segment_url in representation_ms_info['segment_urls']:
fragment = {
location_key(segment_url): segment_url,
}
if segment_duration:
fragment['duration'] = segment_duration
fragments.append(fragment)
representation_ms_info['fragments'] = fragments
# NB: MPD manifest may contain direct URLs to unfragmented media.
# No fragments key is present in this case.
if 'fragments' in representation_ms_info:

View File

@@ -413,52 +413,3 @@ class DailymotionUserIE(DailymotionPlaylistIE):
'title': full_user,
'entries': self._extract_entries(user),
}
class DailymotionCloudIE(DailymotionBaseInfoExtractor):
_VALID_URL_PREFIX = r'https?://api\.dmcloud\.net/(?:player/)?embed/'
_VALID_URL = r'%s[^/]+/(?P<id>[^/?]+)' % _VALID_URL_PREFIX
_VALID_EMBED_URL = r'%s[^/]+/[^\'"]+' % _VALID_URL_PREFIX
_TESTS = [{
# From http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html
# Tested at FranceTvInfo_2
'url': 'http://api.dmcloud.net/embed/4e7343f894a6f677b10006b4/556e03339473995ee145930c?auth=1464865870-0-jyhsm84b-ead4c701fb750cf9367bf4447167a3db&autoplay=1',
'only_matching': True,
}, {
# http://www.francetvinfo.fr/societe/larguez-les-amarres-le-cobaturage-se-developpe_980101.html
'url': 'http://api.dmcloud.net/player/embed/4e7343f894a6f677b10006b4/559545469473996d31429f06?auth=1467430263-0-90tglw2l-a3a4b64ed41efe48d7fccad85b8b8fda&autoplay=1',
'only_matching': True,
}]
@classmethod
def _extract_dmcloud_url(cls, webpage):
mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % cls._VALID_EMBED_URL, webpage)
if mobj:
return mobj.group(1)
mobj = re.search(
r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % cls._VALID_EMBED_URL,
webpage)
if mobj:
return mobj.group(1)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage_no_ff(url, video_id)
title = self._html_search_regex(r'<title>([^>]+)</title>', webpage, 'title')
video_info = self._parse_json(self._search_regex(
r'var\s+info\s*=\s*([^;]+);', webpage, 'video info'), video_id)
# TODO: parse ios_url, which is in fact a manifest
video_url = video_info['mp4_url']
return {
'id': video_id,
'url': video_url,
'title': title,
'thumbnail': video_info.get('thumbnail_url'),
}

View File

@@ -13,33 +13,30 @@ from ..aes import (
from ..utils import (
bytes_to_intlist,
bytes_to_long,
clean_html,
extract_attributes,
ExtractorError,
intlist_to_bytes,
get_element_by_id,
js_to_json,
int_or_none,
long_to_bytes,
pkcs1pad,
remove_end,
)
class DaisukiIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?daisuki\.net/[^/]+/[^/]+/[^/]+/watch\.[^.]+\.(?P<id>\d+)\.html'
class DaisukiMottoIE(InfoExtractor):
_VALID_URL = r'https?://motto\.daisuki\.net/framewatch/embed/[^/]+/(?P<id>[0-9a-zA-Z]{3})'
_TEST = {
'url': 'http://www.daisuki.net/tw/en/anime/watch.TheIdolMasterCG.11213.html',
'url': 'http://motto.daisuki.net/framewatch/embed/embedDRAGONBALLSUPERUniverseSurvivalsaga/V2e/760/428',
'info_dict': {
'id': '11213',
'id': 'V2e',
'ext': 'mp4',
'title': '#01 Who is in the pumpkin carriage? - THE IDOLM@STER CINDERELLA GIRLS',
'title': '#117 SHOWDOWN OF LOVE! ANDROIDS VS UNIVERSE 2!!',
'subtitles': {
'mul': [{
'ext': 'ttml',
}],
},
'creator': 'BANDAI NAMCO Entertainment',
},
'params': {
'skip_download': True, # AES-encrypted HLS stream
@@ -73,15 +70,17 @@ class DaisukiIE(InfoExtractor):
n, e = self._RSA_KEY
encrypted_aeskey = long_to_bytes(pow(bytes_to_long(padded_aeskey), e, n))
init_data = self._download_json('http://www.daisuki.net/bin/bgn/init', video_id, query={
's': flashvars.get('s', ''),
'c': flashvars.get('ss3_prm', ''),
'e': url,
'd': base64.b64encode(intlist_to_bytes(aes_cbc_encrypt(
bytes_to_intlist(json.dumps(data)),
aes_key, iv))).decode('ascii'),
'a': base64.b64encode(encrypted_aeskey).decode('ascii'),
}, note='Downloading JSON metadata' + (' (try #%d)' % (idx + 1) if idx > 0 else ''))
init_data = self._download_json(
'http://motto.daisuki.net/fastAPI/bgn/init/',
video_id, query={
's': flashvars.get('s', ''),
'c': flashvars.get('ss3_prm', ''),
'e': url,
'd': base64.b64encode(intlist_to_bytes(aes_cbc_encrypt(
bytes_to_intlist(json.dumps(data)),
aes_key, iv))).decode('ascii'),
'a': base64.b64encode(encrypted_aeskey).decode('ascii'),
}, note='Downloading JSON metadata' + (' (try #%d)' % (idx + 1) if idx > 0 else ''))
if 'rtn' in init_data:
encrypted_rtn = init_data['rtn']
@@ -98,14 +97,11 @@ class DaisukiIE(InfoExtractor):
aes_key, iv)).decode('utf-8').rstrip('\0'),
video_id)
title = rtn['title_str']
formats = self._extract_m3u8_formats(
rtn['play_url'], video_id, ext='mp4', entry_protocol='m3u8_native')
title = remove_end(self._og_search_title(webpage), ' - DAISUKI')
creator = self._html_search_regex(
r'Creator\s*:\s*([^<]+)', webpage, 'creator', fatal=False)
subtitles = {}
caption_url = rtn.get('caption_url')
if caption_url:
@@ -120,21 +116,18 @@ class DaisukiIE(InfoExtractor):
'title': title,
'formats': formats,
'subtitles': subtitles,
'creator': creator,
}
class DaisukiPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)daisuki\.net/[^/]+/[^/]+/[^/]+/detail\.(?P<id>[a-zA-Z0-9]+)\.html'
class DaisukiMottoPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://motto\.daisuki\.net/(?P<id>information)/'
_TEST = {
'url': 'http://www.daisuki.net/tw/en/anime/detail.TheIdolMasterCG.html',
'url': 'http://motto.daisuki.net/information/',
'info_dict': {
'id': 'TheIdolMasterCG',
'title': 'THE IDOLM@STER CINDERELLA GIRLS',
'description': 'md5:0f2c028a9339f7a2c7fbf839edc5c5d8',
'title': 'DRAGON BALL SUPER',
},
'playlist_count': 26,
'playlist_mincount': 117,
}
def _real_extract(self, url):
@@ -142,18 +135,19 @@ class DaisukiPlaylistIE(InfoExtractor):
webpage = self._download_webpage(url, playlist_id)
episode_pattern = r'''(?sx)
<img[^>]+delay="[^"]+/(\d+)/movie\.jpg".+?
<p[^>]+class=".*?\bepisodeNumber\b.*?">(?:<a[^>]+>)?([^<]+)'''
entries = [{
'_type': 'url_transparent',
'url': url.replace('detail', 'watch').replace('.html', '.' + movie_id + '.html'),
'episode_id': episode_id,
'episode_number': int_or_none(episode_id),
} for movie_id, episode_id in re.findall(episode_pattern, webpage)]
entries = []
for li in re.findall(r'(<li[^>]+?data-product_id="[a-zA-Z0-9]{3}"[^>]+>)', webpage):
attr = extract_attributes(li)
ad_id = attr.get('data-ad_id')
product_id = attr.get('data-product_id')
if ad_id and product_id:
episode_id = attr.get('data-chapter')
entries.append({
'_type': 'url_transparent',
'url': 'http://motto.daisuki.net/framewatch/embed/%s/%s/760/428' % (ad_id, product_id),
'episode_id': episode_id,
'episode_number': int_or_none(episode_id),
'ie_key': 'DaisukiMotto',
})
playlist_title = remove_end(
self._og_search_title(webpage, fatal=False), ' - Anime - DAISUKI')
playlist_description = clean_html(get_element_by_id('synopsisTxt', webpage))
return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
return self.playlist_result(entries, playlist_title='DRAGON BALL SUPER')

View File

@@ -0,0 +1,133 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_html,
extract_attributes,
float_or_none,
int_or_none,
try_get,
)
class EllenTubeBaseIE(InfoExtractor):
def _extract_data_config(self, webpage, video_id):
details = self._search_regex(
r'(<[^>]+\bdata-component=(["\'])[Dd]etails.+?></div>)', webpage,
'details')
return self._parse_json(
extract_attributes(details)['data-config'], video_id)
def _extract_video(self, data, video_id):
title = data['title']
formats = []
duration = None
for entry in data.get('media'):
if entry.get('id') == 'm3u8':
formats = self._extract_m3u8_formats(
entry['url'], video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls')
duration = int_or_none(entry.get('duration'))
break
self._sort_formats(formats)
def get_insight(kind):
return int_or_none(try_get(
data, lambda x: x['insight']['%ss' % kind]))
return {
'extractor_key': EllenTubeIE.ie_key(),
'id': video_id,
'title': title,
'description': data.get('description'),
'duration': duration,
'thumbnail': data.get('thumbnail'),
'timestamp': float_or_none(data.get('publishTime'), scale=1000),
'view_count': get_insight('view'),
'like_count': get_insight('like'),
'formats': formats,
}
class EllenTubeIE(EllenTubeBaseIE):
_VALID_URL = r'''(?x)
(?:
ellentube:|
https://api-prod\.ellentube\.com/ellenapi/api/item/
)
(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})
'''
_TESTS = [{
'url': 'https://api-prod.ellentube.com/ellenapi/api/item/0822171c-3829-43bf-b99f-d77358ae75e3',
'md5': '2fabc277131bddafdd120e0fc0f974c9',
'info_dict': {
'id': '0822171c-3829-43bf-b99f-d77358ae75e3',
'ext': 'mp4',
'title': 'Ellen Meets Las Vegas Survivors Jesus Campos and Stephen Schuck',
'description': 'md5:76e3355e2242a78ad9e3858e5616923f',
'thumbnail': r're:^https?://.+?',
'duration': 514,
'timestamp': 1508505120,
'upload_date': '20171020',
'view_count': int,
'like_count': int,
}
}, {
'url': 'ellentube:734a3353-f697-4e79-9ca9-bfc3002dc1e0',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
'https://api-prod.ellentube.com/ellenapi/api/item/%s' % video_id,
video_id)
return self._extract_video(data, video_id)
class EllenTubeVideoIE(EllenTubeBaseIE):
_VALID_URL = r'https?://(?:www\.)?ellentube\.com/video/(?P<id>.+?)\.html'
_TEST = {
'url': 'https://www.ellentube.com/video/ellen-meets-las-vegas-survivors-jesus-campos-and-stephen-schuck.html',
'only_matching': True,
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._extract_data_config(webpage, display_id)['id']
return self.url_result(
'ellentube:%s' % video_id, ie=EllenTubeIE.ie_key(),
video_id=video_id)
class EllenTubePlaylistIE(EllenTubeBaseIE):
_VALID_URL = r'https?://(?:www\.)?ellentube\.com/(?:episode|studios)/(?P<id>.+?)\.html'
_TESTS = [{
'url': 'https://www.ellentube.com/episode/dax-shepard-jordan-fisher-haim.html',
'info_dict': {
'id': 'dax-shepard-jordan-fisher-haim',
'title': "Dax Shepard, 'DWTS' Team Jordan Fisher & Lindsay Arnold, HAIM",
'description': 'md5:bfc982194dabb3f4e325e43aa6b2e21c',
},
'playlist_count': 6,
}, {
'url': 'https://www.ellentube.com/studios/macey-goes-rving0.html',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
data = self._extract_data_config(webpage, display_id)['data']
feed = self._download_json(
'https://api-prod.ellentube.com/ellenapi/api/feed/?%s'
% data['filter'], display_id)
entries = [
self._extract_video(elem, elem['id'])
for elem in feed if elem.get('type') == 'VIDEO' and elem.get('id')]
return self.playlist_result(
entries, display_id, data.get('title'),
clean_html(data.get('description')))

View File

@@ -1,101 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils import NO_DEFAULT
class EllenTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
_TESTS = [{
'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
'md5': '4294cf98bc165f218aaa0b89e0fd8042',
'info_dict': {
'id': '0_ipq1gsai',
'ext': 'mov',
'title': 'Fast Fingers of Fate',
'description': 'md5:3539013ddcbfa64b2a6d1b38d910868a',
'timestamp': 1428035648,
'upload_date': '20150403',
'uploader_id': 'batchUser',
},
}, {
# not available via http://widgets.ellentube.com/
'url': 'http://www.ellentv.com/videos/1-szkgu2m2/',
'info_dict': {
'id': '1_szkgu2m2',
'ext': 'flv',
'title': "Ellen's Amazingly Talented Audience",
'description': 'md5:86ff1e376ff0d717d7171590e273f0a5',
'timestamp': 1255140900,
'upload_date': '20091010',
'uploader_id': 'ellenkaltura@gmail.com',
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
URLS = ('http://widgets.ellentube.com/videos/%s' % video_id, url)
for num, url_ in enumerate(URLS, 1):
webpage = self._download_webpage(
url_, video_id, fatal=num == len(URLS))
default = NO_DEFAULT if num == len(URLS) else None
partner_id = self._search_regex(
r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id',
default=default)
kaltura_id = self._search_regex(
[r'id="kaltura_player_([^"]+)"',
r"_wb_entry_id\s*:\s*'([^']+)",
r'data-kaltura-entry-id="([^"]+)'],
webpage, 'kaltura id', default=default)
if partner_id and kaltura_id:
break
return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), KalturaIE.ie_key())
class EllenTVClipsIE(InfoExtractor):
IE_NAME = 'EllenTV:clips'
_VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)'
_TEST = {
'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/',
'info_dict': {
'id': 'meryl-streep-vanessa-hudgens',
'title': 'Meryl Streep, Vanessa Hudgens',
},
'playlist_mincount': 5,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
playlist = self._extract_playlist(webpage, playlist_id)
return {
'_type': 'playlist',
'id': playlist_id,
'title': self._og_search_title(webpage),
'entries': self._extract_entries(playlist)
}
def _extract_playlist(self, webpage, playlist_id):
json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
return self._parse_json('[{' + json_string + '}]', playlist_id)
def _extract_entries(self, playlist):
return [
self.url_result(
'kaltura:%s:%s' % (item['kaltura_partner_id'], item['kaltura_entry_id']),
KalturaIE.ie_key(), video_id=item['kaltura_entry_id'])
for item in playlist]

View File

@@ -127,7 +127,10 @@ from .bloomberg import BloombergIE
from .bokecc import BokeCCIE
from .bostonglobe import BostonGlobeIE
from .bpb import BpbIE
from .br import BRIE
from .br import (
BRIE,
BRMediathekIE,
)
from .bravotv import BravoTVIE
from .breakcom import BreakIE
from .brightcove import (
@@ -243,11 +246,10 @@ from .dailymotion import (
DailymotionIE,
DailymotionPlaylistIE,
DailymotionUserIE,
DailymotionCloudIE,
)
from .daisuki import (
DaisukiIE,
DaisukiPlaylistIE,
DaisukiMottoIE,
DaisukiMottoPlaylistIE,
)
from .daum import (
DaumIE,
@@ -309,9 +311,10 @@ from .ehow import EHowIE
from .eighttracks import EightTracksIE
from .einthusan import EinthusanIE
from .eitb import EitbIE
from .ellentv import (
EllenTVIE,
EllenTVClipsIE,
from .ellentube import (
EllenTubeIE,
EllenTubeVideoIE,
EllenTubePlaylistIE,
)
from .elpais import ElPaisIE
from .embedly import EmbedlyIE
@@ -854,6 +857,7 @@ from .radiofrance import RadioFranceIE
from .rai import (
RaiPlayIE,
RaiPlayLiveIE,
RaiPlayPlaylistIE,
RaiIE,
)
from .rbmaradio import RBMARadioIE
@@ -997,6 +1001,7 @@ from .streamango import StreamangoIE
from .streamcloud import StreamcloudIE
from .streamcz import StreamCZIE
from .streetvoice import StreetVoiceIE
from .stretchinternet import StretchInternetIE
from .sunporno import SunPornoIE
from .svt import (
SVTIE,

View File

@@ -11,6 +11,7 @@ from ..utils import (
parse_duration,
try_get,
unified_timestamp,
update_url_query,
)
@@ -62,7 +63,8 @@ class FOXIE(AdobePassIE):
duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
video.get('duration')) or parse_duration(video.get('duration'))
timestamp = unified_timestamp(video.get('datePublished'))
age_limit = parse_age_limit(video.get('contentRating'))
rating = video.get('contentRating')
age_limit = parse_age_limit(rating)
data = try_get(
video, lambda x: x['trackingData']['properties'], dict) or {}
@@ -77,8 +79,24 @@ class FOXIE(AdobePassIE):
release_year = int_or_none(video.get('releaseYear'))
if data.get('authRequired'):
# TODO: AP
pass
resource = self._get_mvpd_resource(
'fbc-fox', title, video.get('guid'), rating)
release_url = update_url_query(
release_url, {
'auth': self._extract_mvpd_auth(
url, video_id, 'fbc-fox', resource)
})
subtitles = {}
for doc_rel in video.get('documentReleases', []):
rel_url = doc_rel.get('url')
if not url or doc_rel.get('format') != 'SCC':
continue
subtitles['en'] = [{
'url': rel_url,
'ext': 'scc',
}]
break
info = {
'id': video_id,
@@ -93,6 +111,7 @@ class FOXIE(AdobePassIE):
'episode': episode,
'episode_number': episode_number,
'release_year': release_year,
'subtitles': subtitles,
}
urlh = self._request_webpage(HEADRequest(release_url), video_id)

View File

@@ -13,10 +13,7 @@ from ..utils import (
parse_duration,
determine_ext,
)
from .dailymotion import (
DailymotionIE,
DailymotionCloudIE,
)
from .dailymotion import DailymotionIE
class FranceTVBaseInfoExtractor(InfoExtractor):
@@ -290,10 +287,6 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
page_title = mobj.group('title')
webpage = self._download_webpage(url, page_title)
dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
if dmcloud_url:
return self.url_result(dmcloud_url, DailymotionCloudIE.ie_key())
dailymotion_urls = DailymotionIE._extract_urls(webpage)
if dailymotion_urls:
return self.playlist_result([
@@ -363,6 +356,7 @@ class CultureboxIE(FranceTVBaseInfoExtractor):
raise ExtractorError('Video %s is not available' % name, expected=True)
video_id, catalogue = self._search_regex(
r'"https?://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')
r'["\'>]https?://videos\.francetv\.fr/video/([^@]+@.+?)["\'<]',
webpage, 'video id').split('@')
return self._extract_video(video_id, catalogue)

View File

@@ -59,10 +59,7 @@ from .tnaflix import TNAFlixNetworkEmbedIE
from .drtuber import DrTuberIE
from .redtube import RedTubeIE
from .vimeo import VimeoIE
from .dailymotion import (
DailymotionIE,
DailymotionCloudIE,
)
from .dailymotion import DailymotionIE
from .dailymail import DailyMailIE
from .onionstudios import OnionStudiosIE
from .viewlift import ViewLiftEmbedIE
@@ -1472,23 +1469,6 @@ class GenericIE(InfoExtractor):
'timestamp': 1432570283,
},
},
# Dailymotion Cloud video
{
'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
'info_dict': {
'id': 'x2uy8t3',
'ext': 'mp4',
'title': 'Sauvons les abeilles ! - Le débat',
'description': 'md5:d9082128b1c5277987825d684939ca26',
'thumbnail': r're:^https?://.*\.jpe?g$',
'timestamp': 1434970506,
'upload_date': '20150622',
'uploader': 'Public Sénat',
'uploader_id': 'xa9gza',
},
'skip': 'File not found.',
},
# OnionStudios embed
{
'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
@@ -2195,7 +2175,7 @@ class GenericIE(InfoExtractor):
return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
info_dict['formats'] = self._parse_mpd_formats(
doc, video_id,
doc,
mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
mpd_url=url)
self._sort_formats(info_dict['formats'])
@@ -2704,11 +2684,6 @@ class GenericIE(InfoExtractor):
if senate_isvp_url:
return self.url_result(senate_isvp_url, 'SenateISVP')
# Look for Dailymotion Cloud videos
dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
if dmcloud_url:
return self.url_result(dmcloud_url, 'DailymotionCloud')
# Look for OnionStudios embeds
onionstudios_url = OnionStudiosIE._extract_url(webpage)
if onionstudios_url:

View File

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
import uuid
import xml.etree.ElementTree as etree
import json
import re
from .common import InfoExtractor
from ..compat import (
@@ -142,9 +143,9 @@ class ITVIE(InfoExtractor):
f['url'] = rtmp_url
formats.append(f)
ios_playlist_url = params.get('data-video-playlist')
ios_playlist_url = params.get('data-video-playlist') or params.get('data-video-id')
hmac = params.get('data-video-hmac')
if ios_playlist_url and hmac:
if ios_playlist_url and hmac and re.match(r'https?://', ios_playlist_url):
headers = self.geo_verification_headers()
headers.update({
'Accept': 'application/vnd.itv.vod.playlist.v2+json',
@@ -159,12 +160,12 @@ class ITVIE(InfoExtractor):
'token': ''
},
'device': {
'manufacturer': 'Apple',
'model': 'iPad',
'manufacturer': 'Safari',
'model': '5',
'os': {
'name': 'iPhone OS',
'version': '9.3',
'type': 'ios'
'name': 'Windows NT',
'version': '6.1',
'type': 'desktop'
}
},
'client': {
@@ -173,10 +174,10 @@ class ITVIE(InfoExtractor):
},
'variantAvailability': {
'featureset': {
'min': ['hls', 'aes'],
'max': ['hls', 'aes']
'min': ['hls', 'aes', 'outband-webvtt'],
'max': ['hls', 'aes', 'outband-webvtt']
},
'platformTag': 'mobile'
'platformTag': 'dotcom'
}
}).encode(), headers=headers, fatal=False)
if ios_playlist:

View File

@@ -40,21 +40,29 @@ class MnetIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
# TODO: extract rtmp formats
# no stype -> rtmp url
# stype=H -> m3u8 url
# stype=M -> mpd url
info = self._download_json(
'http://content.api.mnet.com/player/vodConfig?id=%s&ctype=CLIP' % video_id,
video_id, 'Downloading vod config JSON')['data']['info']
'http://content.api.mnet.com/player/vodConfig',
video_id, 'Downloading vod config JSON', query={
'id': video_id,
'ctype': 'CLIP',
'stype': 'H',
})['data']['info']
title = info['title']
rtmp_info = self._download_json(
info['cdn'], video_id, 'Downloading vod cdn JSON')
formats = [{
'url': rtmp_info['serverurl'] + rtmp_info['fileurl'],
'ext': 'flv',
'page_url': url,
'player_url': 'http://flvfile.mnet.com/service/player/201602/cjem_player_tv.swf?v=201602191318',
}]
cdn_data = self._download_json(
info['cdn'], video_id, 'Downloading vod cdn JSON')['data'][0]
m3u8_url = cdn_data['url']
token = cdn_data.get('token')
if token and token != '-':
m3u8_url += '?' + token
formats = self._extract_wowza_formats(
m3u8_url, video_id, skip_protocols=['rtmp', 'rtsp', 'f4m'])
self._sort_formats(formats)
description = info.get('ment')
duration = parse_duration(info.get('time'))

View File

@@ -115,10 +115,17 @@ class MTVServicesInfoExtractor(InfoExtractor):
if transcript.get('kind') != 'captions':
continue
lang = transcript.get('srclang')
subtitles[lang] = [{
'url': compat_str(typographic.get('src')),
'ext': typographic.get('format')
} for typographic in transcript.findall('./typographic')]
for typographic in transcript.findall('./typographic'):
sub_src = typographic.get('src')
if not sub_src:
continue
ext = typographic.get('format')
if ext == 'cea-608':
ext = 'scc'
subtitles.setdefault(lang, []).append({
'url': compat_str(sub_src),
'ext': ext
})
return subtitles
def _get_video_info(self, itemdoc, use_hls=True):

View File

@@ -14,6 +14,7 @@ from ..utils import (
int_or_none,
qualities,
unescapeHTML,
urlencode_postdata,
)
@@ -56,7 +57,7 @@ class OdnoklassnikiIE(InfoExtractor):
'url': 'http://ok.ru/video/64211978996595-1',
'md5': '2f206894ffb5dbfcce2c5a14b909eea5',
'info_dict': {
'id': '64211978996595-1',
'id': 'V_VztHT5BzY',
'ext': 'mp4',
'title': 'Космическая среда от 26 августа 2015',
'description': 'md5:848eb8b85e5e3471a3a803dae1343ed0',
@@ -127,9 +128,14 @@ class OdnoklassnikiIE(InfoExtractor):
if metadata:
metadata = self._parse_json(metadata, video_id)
else:
data = {}
st_location = flashvars.get('location')
if st_location:
data['st.location'] = st_location
metadata = self._download_json(
compat_urllib_parse_unquote(flashvars['metadataUrl']),
video_id, 'Downloading metadata JSON')
video_id, 'Downloading metadata JSON',
data=urlencode_postdata(data))
movie = metadata['movie']

View File

@@ -421,6 +421,7 @@ class PBSIE(InfoExtractor):
r'class="coveplayerid">([^<]+)<', # coveplayer
r'<section[^>]+data-coveid="(\d+)"', # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/
r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>', # jwplayer
r"(?s)window\.PBS\.playerConfig\s*=\s*{.*?id\s*:\s*'([0-9]+)',",
]
media_id = self._search_regex(

View File

@@ -131,6 +131,13 @@ class PluralsightIE(PluralsightBaseIE):
if BLOCKED in response:
raise ExtractorError(
'Unable to login: %s' % BLOCKED, expected=True)
MUST_AGREE = 'To continue using Pluralsight, you must agree to'
if any(p in response for p in (MUST_AGREE, '>Disagree<', '>Agree<')):
raise ExtractorError(
'Unable to login: %s some documents. Go to pluralsight.com, '
'log in and agree with what Pluralsight requires.'
% MUST_AGREE, expected=True)
raise ExtractorError('Unable to log in')
def _get_subtitles(self, author, clip_id, lang, name, duration, video_id):

View File

@@ -77,12 +77,14 @@ class PornComIE(InfoExtractor):
self._sort_formats(formats)
view_count = str_to_int(self._search_regex(
r'class=["\']views["\'][^>]*><p>([\d,.]+)', webpage,
(r'Views:\s*</span>\s*<span>\s*([\d,.]+)',
r'class=["\']views["\'][^>]*><p>([\d,.]+)'), webpage,
'view count', fatal=False))
def extract_list(kind):
s = self._search_regex(
r'(?s)<p[^>]*>%s:(.+?)</p>' % kind.capitalize(),
(r'(?s)%s:\s*</span>\s*<span>(.+?)</span>' % kind.capitalize(),
r'(?s)<p[^>]*>%s:(.+?)</p>' % kind.capitalize()),
webpage, kind, fatal=False)
return re.findall(r'<a[^>]+>([^<]+)</a>', s or '')

View File

@@ -17,6 +17,7 @@ from ..utils import (
parse_duration,
strip_or_none,
try_get,
unescapeHTML,
unified_strdate,
unified_timestamp,
update_url_query,
@@ -249,6 +250,41 @@ class RaiPlayLiveIE(RaiBaseIE):
}
class RaiPlayPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/',
'info_dict': {
'id': 'nondirloalmiocapo',
'title': 'Non dirlo al mio capo',
'description': 'md5:9f3d603b2947c1c7abb098f3b14fac86',
},
'playlist_mincount': 12,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
title = self._html_search_meta(
('programma', 'nomeProgramma'), webpage, 'title')
description = unescapeHTML(self._html_search_meta(
('description', 'og:description'), webpage, 'description'))
print(description)
entries = []
for mobj in re.finditer(
r'<a\b[^>]+\bhref=(["\'])(?P<path>/raiplay/video/.+?)\1',
webpage):
video_url = urljoin(url, mobj.group('path'))
entries.append(self.url_result(
video_url, ie=RaiPlayIE.ie_key(),
video_id=RaiPlayIE._match_id(video_url)))
return self.playlist_result(entries, playlist_id, title, description)
class RaiIE(RaiBaseIE):
_VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/dl/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE
_TESTS = [{

View File

@@ -2,6 +2,7 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import smuggle_url
class SonyLIVIE(InfoExtractor):
@@ -10,12 +11,12 @@ class SonyLIVIE(InfoExtractor):
'url': "http://www.sonyliv.com/details/episodes/5024612095001/Ep.-1---Achaari-Cheese-Toast---Bachelor's-Delight",
'info_dict': {
'title': "Ep. 1 - Achaari Cheese Toast - Bachelor's Delight",
'id': '5024612095001',
'id': 'ref:5024612095001',
'ext': 'mp4',
'upload_date': '20160707',
'upload_date': '20170923',
'description': 'md5:7f28509a148d5be9d0782b4d5106410d',
'uploader_id': '4338955589001',
'timestamp': 1467870968,
'uploader_id': '5182475815001',
'timestamp': 1506200547,
},
'params': {
'skip_download': True,
@@ -26,9 +27,11 @@ class SonyLIVIE(InfoExtractor):
'only_matching': True,
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/4338955589001/default_default/index.html?videoId=%s'
# BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/4338955589001/default_default/index.html?videoId=%s'
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5182475815001/default_default/index.html?videoId=ref:%s'
def _real_extract(self, url):
brightcove_id = self._match_id(url)
return self.url_result(
self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)
smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, {'geo_countries': ['IN']}),
'BrightcoveNew', brightcove_id)

View File

@@ -0,0 +1,48 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import int_or_none
class StretchInternetIE(InfoExtractor):
_VALID_URL = r'https?://portal\.stretchinternet\.com/[^/]+/portal\.htm\?.*?\beventId=(?P<id>\d+)'
_TEST = {
'url': 'https://portal.stretchinternet.com/umary/portal.htm?eventId=313900&streamType=video',
'info_dict': {
'id': '313900',
'ext': 'mp4',
'title': 'Augustana (S.D.) Baseball vs University of Mary',
'description': 'md5:7578478614aae3bdd4a90f578f787438',
'timestamp': 1490468400,
'upload_date': '20170325',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
stream = self._download_json(
'https://neo-client.stretchinternet.com/streamservice/v1/media/stream/v%s'
% video_id, video_id)
video_url = 'https://%s' % stream['source']
event = self._download_json(
'https://neo-client.stretchinternet.com/portal-ws/getEvent.json',
video_id, query={
'clientID': 99997,
'eventID': video_id,
'token': 'asdf',
})['event']
title = event.get('title') or event['mobileTitle']
description = event.get('customText')
timestamp = int_or_none(event.get('longtime'))
return {
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'url': video_url,
}

View File

@@ -1,6 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
@@ -41,7 +43,7 @@ class TouTvIE(InfoExtractor):
email, password = self._get_login_info()
if email is None:
return
state = 'http://ici.tou.tv//'
state = 'http://ici.tou.tv/'
webpage = self._download_webpage(state, None, 'Downloading homepage')
toutvlogin = self._parse_json(self._search_regex(
r'(?s)toutvlogin\s*=\s*({.+?});', webpage, 'toutvlogin'), None, js_to_json)
@@ -54,16 +56,30 @@ class TouTvIE(InfoExtractor):
'scope': 'media-drmt openid profile email id.write media-validation.read.privileged',
'state': state,
})
login_form = self._search_regex(
r'(?s)(<form[^>]+(?:id|name)="Form-login".+?</form>)', login_webpage, 'login form')
form_data = self._hidden_inputs(login_form)
def extract_form_url_and_data(wp, default_form_url, form_spec_re=''):
form, form_elem = re.search(
r'(?s)((<form[^>]+?%s[^>]*?>).+?</form>)' % form_spec_re, wp).groups()
form_data = self._hidden_inputs(form)
form_url = extract_attributes(form_elem).get('action') or default_form_url
return form_url, form_data
post_url, form_data = extract_form_url_and_data(
login_webpage,
'https://services.radio-canada.ca/auth/oauth/v2/authorize/login',
r'(?:id|name)="Form-login"')
form_data.update({
'login-email': email,
'login-password': password,
})
post_url = extract_attributes(login_form).get('action') or authorize_url
_, urlh = self._download_webpage_handle(
consent_webpage = self._download_webpage(
post_url, None, 'Logging in', data=urlencode_postdata(form_data))
post_url, form_data = extract_form_url_and_data(
consent_webpage,
'https://services.radio-canada.ca/auth/oauth/v2/authorize/consent')
_, urlh = self._download_webpage_handle(
post_url, None, 'Following Redirection',
data=urlencode_postdata(form_data))
self._access_token = self._search_regex(
r'access_token=([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
urlh.geturl(), 'access token')

View File

@@ -43,7 +43,7 @@ class TwitterBaseIE(InfoExtractor):
class TwitterCardIE(TwitterBaseIE):
IE_NAME = 'twitter:card'
_VALID_URL = r'https?://(?:www\.)?twitter\.com/i/(?:cards/tfw/v1|videos(?:/tweet)?)/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?twitter\.com/i/(?P<path>cards/tfw/v1|videos(?:/tweet)?)/(?P<id>\d+)'
_TESTS = [
{
'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
@@ -51,11 +51,10 @@ class TwitterCardIE(TwitterBaseIE):
'info_dict': {
'id': '560070183650213889',
'ext': 'mp4',
'title': 'Twitter Card',
'title': 'Twitter web player',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 30.033,
},
'skip': 'Video gone',
},
{
'url': 'https://twitter.com/i/cards/tfw/v1/623160978427936768',
@@ -63,11 +62,9 @@ class TwitterCardIE(TwitterBaseIE):
'info_dict': {
'id': '623160978427936768',
'ext': 'mp4',
'title': 'Twitter Card',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 80.155,
'title': 'Twitter web player',
'thumbnail': r're:^https?://.*(?:\bformat=|\.)jpg',
},
'skip': 'Video gone',
},
{
'url': 'https://twitter.com/i/cards/tfw/v1/654001591733886977',
@@ -120,15 +117,15 @@ class TwitterCardIE(TwitterBaseIE):
elif media_url.endswith('.mpd'):
formats.extend(self._extract_mpd_formats(media_url, video_id, mpd_id='dash'))
else:
vbr = int_or_none(dict_get(media_variant, ('bitRate', 'bitrate')), scale=1000)
tbr = int_or_none(dict_get(media_variant, ('bitRate', 'bitrate')), scale=1000)
a_format = {
'url': media_url,
'format_id': 'http-%d' % vbr if vbr else 'http',
'vbr': vbr,
'format_id': 'http-%d' % tbr if tbr else 'http',
'tbr': tbr,
}
# Reported bitRate may be zero
if not a_format['vbr']:
del a_format['vbr']
if not a_format['tbr']:
del a_format['tbr']
self._search_dimensions_in_video_url(a_format, media_url)
@@ -150,79 +147,83 @@ class TwitterCardIE(TwitterBaseIE):
bearer_token = self._search_regex(
r'BEARER_TOKEN\s*:\s*"([^"]+)"',
main_script, 'bearer token')
guest_token = self._search_regex(
r'document\.cookie\s*=\s*decodeURIComponent\("gt=(\d+)',
webpage, 'guest token')
# https://developer.twitter.com/en/docs/tweets/post-and-engage/api-reference/get-statuses-show-id
api_data = self._download_json(
'https://api.twitter.com/2/timeline/conversation/%s.json' % video_id,
video_id, 'Downloading mobile API data',
'https://api.twitter.com/1.1/statuses/show/%s.json' % video_id,
video_id, 'Downloading API data',
headers={
'Authorization': 'Bearer ' + bearer_token,
'x-guest-token': guest_token,
})
media_info = try_get(api_data, lambda o: o['globalObjects']['tweets'][video_id]
['extended_entities']['media'][0]['video_info']) or {}
media_info = try_get(api_data, lambda o: o['extended_entities']['media'][0]['video_info']) or {}
return self._parse_media_info(media_info, video_id)
def _real_extract(self, url):
video_id = self._match_id(url)
path, video_id = re.search(self._VALID_URL, url).groups()
config = None
formats = []
duration = None
webpage = self._download_webpage(url, video_id)
urls = [url]
if path.startswith('cards/'):
urls.append('https://twitter.com/i/videos/' + video_id)
iframe_url = self._html_search_regex(
r'<iframe[^>]+src="((?:https?:)?//(?:www\.youtube\.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"',
webpage, 'video iframe', default=None)
if iframe_url:
return self.url_result(iframe_url)
for u in urls:
webpage = self._download_webpage(u, video_id)
config = self._parse_json(self._html_search_regex(
r'data-(?:player-)?config="([^"]+)"', webpage,
'data player config', default='{}'),
video_id)
iframe_url = self._html_search_regex(
r'<iframe[^>]+src="((?:https?:)?//(?:www\.youtube\.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"',
webpage, 'video iframe', default=None)
if iframe_url:
return self.url_result(iframe_url)
if config.get('source_type') == 'vine':
return self.url_result(config['player_url'], 'Vine')
config = self._parse_json(self._html_search_regex(
r'data-(?:player-)?config="([^"]+)"', webpage,
'data player config', default='{}'),
video_id)
periscope_url = PeriscopeIE._extract_url(webpage)
if periscope_url:
return self.url_result(periscope_url, PeriscopeIE.ie_key())
if config.get('source_type') == 'vine':
return self.url_result(config['player_url'], 'Vine')
video_url = config.get('video_url') or config.get('playlist', [{}])[0].get('source')
periscope_url = PeriscopeIE._extract_url(webpage)
if periscope_url:
return self.url_result(periscope_url, PeriscopeIE.ie_key())
if video_url:
if determine_ext(video_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(video_url, video_id, ext='mp4', m3u8_id='hls'))
else:
f = {
'url': video_url,
}
video_url = config.get('video_url') or config.get('playlist', [{}])[0].get('source')
self._search_dimensions_in_video_url(f, video_url)
if video_url:
if determine_ext(video_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(video_url, video_id, ext='mp4', m3u8_id='hls'))
else:
f = {
'url': video_url,
}
formats.append(f)
self._search_dimensions_in_video_url(f, video_url)
vmap_url = config.get('vmapUrl') or config.get('vmap_url')
if vmap_url:
formats.extend(
self._extract_formats_from_vmap_url(vmap_url, video_id))
formats.append(f)
media_info = None
vmap_url = config.get('vmapUrl') or config.get('vmap_url')
if vmap_url:
formats.extend(
self._extract_formats_from_vmap_url(vmap_url, video_id))
for entity in config.get('status', {}).get('entities', []):
if 'mediaInfo' in entity:
media_info = entity['mediaInfo']
media_info = None
if media_info:
formats.extend(self._parse_media_info(media_info, video_id))
duration = float_or_none(media_info.get('duration', {}).get('nanos'), scale=1e9)
for entity in config.get('status', {}).get('entities', []):
if 'mediaInfo' in entity:
media_info = entity['mediaInfo']
username = config.get('user', {}).get('screen_name')
if username:
formats.extend(self._extract_mobile_formats(username, video_id))
if media_info:
formats.extend(self._parse_media_info(media_info, video_id))
duration = float_or_none(media_info.get('duration', {}).get('nanos'), scale=1e9)
username = config.get('user', {}).get('screen_name')
if username:
formats.extend(self._extract_mobile_formats(username, video_id))
if formats:
break
self._remove_duplicate_formats(formats)
self._sort_formats(formats)
@@ -258,9 +259,6 @@ class TwitterIE(InfoExtractor):
'uploader_id': 'freethenipple',
'duration': 12.922,
},
'params': {
'skip_download': True, # requires ffmpeg
},
}, {
'url': 'https://twitter.com/giphz/status/657991469417025536/photo/1',
'md5': 'f36dcd5fb92bf7057f155e7d927eeb42',
@@ -277,7 +275,6 @@ class TwitterIE(InfoExtractor):
'skip': 'Account suspended',
}, {
'url': 'https://twitter.com/starwars/status/665052190608723968',
'md5': '39b7199856dee6cd4432e72c74bc69d4',
'info_dict': {
'id': '665052190608723968',
'ext': 'mp4',
@@ -303,20 +300,16 @@ class TwitterIE(InfoExtractor):
},
}, {
'url': 'https://twitter.com/jaydingeer/status/700207533655363584',
'md5': '',
'info_dict': {
'id': '700207533655363584',
'ext': 'mp4',
'title': 'あかさ - BEAT PROD: @suhmeduh #Damndaniel',
'description': 'あかさ on Twitter: "BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"',
'title': 'JG - BEAT PROD: @suhmeduh #Damndaniel',
'description': 'JG on Twitter: "BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"',
'thumbnail': r're:^https?://.*\.jpg',
'uploader': 'あかさ',
'uploader': 'JG',
'uploader_id': 'jaydingeer',
'duration': 30.0,
},
'params': {
'skip_download': True, # requires ffmpeg
},
}, {
'url': 'https://twitter.com/Filmdrunk/status/713801302971588609',
'md5': '89a15ed345d13b86e9a5a5e051fa308a',
@@ -342,9 +335,6 @@ class TwitterIE(InfoExtractor):
'uploader': 'Captain America',
'duration': 3.17,
},
'params': {
'skip_download': True, # requires ffmpeg
},
}, {
'url': 'https://twitter.com/OPP_HSD/status/779210622571536384',
'info_dict': {
@@ -370,9 +360,6 @@ class TwitterIE(InfoExtractor):
'uploader_id': 'news_al3alm',
'duration': 277.4,
},
'params': {
'format': 'best[format_id^=http-]',
},
}, {
'url': 'https://twitter.com/i/web/status/910031516746514432',
'info_dict': {

View File

@@ -62,11 +62,11 @@ class UdemyIE(InfoExtractor):
def _extract_course_info(self, webpage, video_id):
course = self._parse_json(
unescapeHTML(self._search_regex(
r'ng-init=["\'].*\bcourse=({.+?});', webpage, 'course', default='{}')),
r'ng-init=["\'].*\bcourse=({.+?})[;"\']',
webpage, 'course', default='{}')),
video_id, fatal=False) or {}
course_id = course.get('id') or self._search_regex(
(r'&quot;id&quot;\s*:\s*(\d+)', r'data-course-id=["\'](\d+)'),
webpage, 'course id')
r'data-course-id=["\'](\d+)', webpage, 'course id')
return course_id, course.get('title')
def _enroll_course(self, base_url, webpage, course_id):
@@ -257,6 +257,11 @@ class UdemyIE(InfoExtractor):
video_url = source.get('file') or source.get('src')
if not video_url or not isinstance(video_url, compat_str):
continue
if source.get('type') == 'application/x-mpegURL' or determine_ext(video_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
continue
format_id = source.get('label')
f = {
'url': video_url,

View File

@@ -22,6 +22,9 @@ class VVVVIDIE(InfoExtractor):
'ext': 'mp4',
'title': 'Ping Pong',
},
'params': {
'skip_download': True,
},
}, {
# video_type == 'video/rcs'
'url': 'https://www.vvvvid.it/#!show/376/death-note-live-action/377/482493/episodio-01',
@@ -31,6 +34,9 @@ class VVVVIDIE(InfoExtractor):
'ext': 'mp4',
'title': 'Episodio 01',
},
'params': {
'skip_download': True,
},
}]
_conn_id = None
@@ -116,8 +122,20 @@ class VVVVIDIE(InfoExtractor):
embed_code = ds(embed_code)
video_type = video_data.get('video_type')
if video_type in ('video/rcs', 'video/kenc'):
formats.extend(self._extract_akamai_formats(
embed_code, video_id))
embed_code = re.sub(r'https?://([^/]+)/z/', r'https://\1/i/', embed_code).replace('/manifest.f4m', '/master.m3u8')
if video_type == 'video/kenc':
kenc = self._download_json(
'https://www.vvvvid.it/kenc', video_id, query={
'action': 'kt',
'conn_id': self._conn_id,
'url': embed_code,
}, fatal=False) or {}
kenc_message = kenc.get('message')
if kenc_message:
embed_code += '?' + ds(kenc_message)
formats.extend(self._extract_m3u8_formats(
embed_code, video_id, 'mp4',
m3u8_id='hls', fatal=False))
else:
formats.extend(self._extract_wowza_formats(
'http://sb.top-ix.org/videomg/_definst_/mp4:%s/playlist.m3u8' % embed_code, video_id))

View File

@@ -6,10 +6,12 @@ from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
clean_html,
determine_ext,
dict_get,
ExtractorError,
int_or_none,
parse_duration,
try_get,
unified_strdate,
)
@@ -32,6 +34,7 @@ class XHamsterIE(InfoExtractor):
'display_id': 'femaleagent_shy_beauty_takes_the_bait',
'ext': 'mp4',
'title': 'FemaleAgent Shy beauty takes the bait',
'timestamp': 1350194821,
'upload_date': '20121014',
'uploader': 'Ruseful2011',
'duration': 893,
@@ -45,6 +48,7 @@ class XHamsterIE(InfoExtractor):
'display_id': 'britney_spears_sexy_booty',
'ext': 'mp4',
'title': 'Britney Spears Sexy Booty',
'timestamp': 1379123460,
'upload_date': '20130914',
'uploader': 'jojo747400',
'duration': 200,
@@ -61,6 +65,7 @@ class XHamsterIE(InfoExtractor):
'id': '5667973',
'ext': 'mp4',
'title': '....',
'timestamp': 1454948101,
'upload_date': '20160208',
'uploader': 'parejafree',
'duration': 72,
@@ -70,6 +75,10 @@ class XHamsterIE(InfoExtractor):
'params': {
'skip_download': True,
},
}, {
# mobile site
'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111',
'only_matching': True,
}, {
'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
'only_matching': True,
@@ -88,7 +97,8 @@ class XHamsterIE(InfoExtractor):
video_id = mobj.group('id') or mobj.group('id_2')
display_id = mobj.group('display_id') or mobj.group('display_id_2')
webpage = self._download_webpage(url, video_id)
desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
webpage = self._download_webpage(desktop_url, video_id)
error = self._html_search_regex(
r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
@@ -96,6 +106,83 @@ class XHamsterIE(InfoExtractor):
if error:
raise ExtractorError(error, expected=True)
age_limit = self._rta_search(webpage)
def get_height(s):
return int_or_none(self._search_regex(
r'^(\d+)[pP]', s, 'height', default=None))
initials = self._parse_json(
self._search_regex(
r'window\.initials\s*=\s*({.+?})\s*;\s*\n', webpage, 'initials',
default='{}'),
video_id, fatal=False)
if initials:
video = initials['videoModel']
title = video['title']
formats = []
for format_id, formats_dict in video['sources'].items():
if not isinstance(formats_dict, dict):
continue
for quality, format_item in formats_dict.items():
if format_id == 'download':
# Download link takes some time to be generated,
# skipping for now
continue
if not isinstance(format_item, dict):
continue
format_url = format_item.get('link')
filesize = int_or_none(
format_item.get('size'), invscale=1000000)
else:
format_url = format_item
filesize = None
if not isinstance(format_url, compat_str):
continue
formats.append({
'format_id': '%s-%s' % (format_id, quality),
'url': format_url,
'ext': determine_ext(format_url, 'mp4'),
'height': get_height(quality),
'filesize': filesize,
})
self._sort_formats(formats)
categories_list = video.get('categories')
if isinstance(categories_list, list):
categories = []
for c in categories_list:
if not isinstance(c, dict):
continue
c_name = c.get('name')
if isinstance(c_name, compat_str):
categories.append(c_name)
else:
categories = None
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': video.get('description'),
'timestamp': int_or_none(video.get('created')),
'uploader': try_get(
video, lambda x: x['author']['name'], compat_str),
'thumbnail': video.get('thumbURL'),
'duration': int_or_none(video.get('duration')),
'view_count': int_or_none(video.get('views')),
'like_count': int_or_none(try_get(
video, lambda x: x['rating']['likes'], int)),
'dislike_count': int_or_none(try_get(
video, lambda x: x['rating']['dislikes'], int)),
'comment_count': int_or_none(video.get('views')),
'age_limit': age_limit,
'categories': categories,
'formats': formats,
}
# Old layout fallback
title = self._html_search_regex(
[r'<h1[^>]*>([^<]+)</h1>',
r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
@@ -119,8 +206,7 @@ class XHamsterIE(InfoExtractor):
formats.append({
'format_id': format_id,
'url': format_url,
'height': int_or_none(self._search_regex(
r'^(\d+)[pP]', format_id, 'height', default=None))
'height': get_height(format_id),
})
video_url = self._search_regex(
@@ -148,8 +234,8 @@ class XHamsterIE(InfoExtractor):
webpage, 'uploader', default='anonymous')
thumbnail = self._search_regex(
[r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
[r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
webpage, 'thumbnail', fatal=False, group='thumbnail')
duration = parse_duration(self._search_regex(
@@ -167,8 +253,6 @@ class XHamsterIE(InfoExtractor):
mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
comment_count = mobj.group('commentcount') if mobj else 0
age_limit = self._rta_search(webpage)
categories_html = self._search_regex(
r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
'categories', default=None)
@@ -195,15 +279,16 @@ class XHamsterIE(InfoExtractor):
class XHamsterEmbedIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
_VALID_URL = r'https?://(?:.+?\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
_TEST = {
'url': 'http://xhamster.com/xembed.php?video=3328539',
'info_dict': {
'id': '3328539',
'ext': 'mp4',
'title': 'Pen Masturbation',
'timestamp': 1406581861,
'upload_date': '20140728',
'uploader_id': 'anonymous',
'uploader': 'ManyakisArt',
'duration': 5,
'age_limit': 18,
}

View File

@@ -40,9 +40,12 @@ class XiamiBaseIE(InfoExtractor):
'subtitles': subtitles,
}
def _extract_tracks(self, item_id, typ=None):
def _extract_tracks(self, item_id, referer, typ=None):
playlist = self._download_json(
'%s/%s%s' % (self._API_BASE_URL, item_id, '/type/%s' % typ if typ else ''), item_id)
'%s/%s%s' % (self._API_BASE_URL, item_id, '/type/%s' % typ if typ else ''),
item_id, headers={
'Referer': referer,
})
return [
self._extract_track(track, item_id)
for track in playlist['data']['trackList']]
@@ -135,13 +138,13 @@ class XiamiSongIE(XiamiBaseIE):
}]
def _real_extract(self, url):
return self._extract_tracks(self._match_id(url))[0]
return self._extract_tracks(self._match_id(url), url)[0]
class XiamiPlaylistBaseIE(XiamiBaseIE):
def _real_extract(self, url):
item_id = self._match_id(url)
return self.playlist_result(self._extract_tracks(item_id, self._TYPE), item_id)
return self.playlist_result(self._extract_tracks(item_id, url, self._TYPE), item_id)
class XiamiAlbumIE(XiamiPlaylistBaseIE):

View File

@@ -154,7 +154,7 @@ class YoukuIE(InfoExtractor):
# request basic data
basic_data_params = {
'vid': video_id,
'ccode': '0502',
'ccode': '0501',
'client_ip': '192.168.1.1',
'utid': cna,
'client_ts': time.time() / 1000,

View File

@@ -2350,6 +2350,7 @@ def mimetype2ext(mt):
'ttml+xml': 'ttml',
'x-flv': 'flv',
'x-mp4-fragmented': 'mp4',
'x-ms-sami': 'sami',
'x-ms-wmv': 'wmv',
'mpegurl': 'm3u8',
'x-mpegurl': 'm3u8',
@@ -2372,7 +2373,7 @@ def parse_codecs(codecs_str):
vcodec, acodec = None, None
for full_codec in splited_codecs:
codec = full_codec.split('.')[0]
if codec in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', 'h263', 'h264', 'mp4v'):
if codec in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', 'h263', 'h264', 'mp4v', 'hvc1'):
if not vcodec:
vcodec = full_codec
elif codec in ('mp4a', 'opus', 'vorbis', 'mp3', 'aac', 'ac-3', 'ec-3', 'eac3', 'dtsc', 'dtse', 'dtsh', 'dtsl'):

View File

@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2017.11.26'
__version__ = '2017.12.10'