release 2017.10.20

.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 *2017.10.15.1*. 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 Issues with outdated version will be rejected.
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.10.20*. 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 Issues with outdated version will be rejected.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 **2017.10.15.1**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.10.20**
 
 ### 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 2017.10.15.1
+[debug] youtube-dl version 2017.10.20
 [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 +1,23 @@
+version 2017.10.20
+
+Core
+* [downloader/fragment] Report warning instead of error on inconsistent
+  download state
+* [downloader/hls] Fix total fragments count when ad fragments exist
+
+Extractors
+* [parliamentliveuk] Fix extraction (#14524)
+* [soundcloud] Update client id (#14546)
++ [servus] Add support for servus.com (#14362)
++ [unity] Add support for unity3d.com (#14528)
+* [youtube] Replace youtube redirect URLs in description (#14517)
+* [pbs] Restrict direct video URL regular expression (#14519)
+* [drtv] Respect preference for direct HTTP formats (#14509)
++ [eporner] Add support for embed URLs (#14507)
+* [arte] Capture and output error message
+* [niconico] Improve uploader metadata extraction robustness (#14135)
+
+
 version 2017.10.15.1
 
 Core
@@ -834,7 +854,7 @@ version 2017.04.14
 
 Core
 + [downloader/hls] Add basic support for EXT-X-BYTERANGE tag (#10955)
-+ [adobepass] Improve Comcast and Verison login code (#10803)
++ [adobepass] Improve Comcast and Verizon login code (#10803)
 + [adobepass] Add support for Verizon (#10803)
 
 Extractors

docs/supportedsites.md

@@ -728,6 +728,7 @@
  - **SenateISVP**
  - **SendtoNews**
  - **ServingSys**
+ - **Servus**
  - **Sexu**
  - **Shahid**
  - **Shared**: shared.sx
@@ -887,6 +888,7 @@
  - **UDNEmbed**: 聯合影音
  - **UKTVPlay**
  - **Unistra**
+ - **Unity**
  - **uol.com.br**
  - **uplynk**
  - **uplynk:preplay**

youtube_dl/downloader/fragment.py

@@ -158,7 +158,7 @@ class FragmentFD(FileDownloader):
             if os.path.isfile(encodeFilename(self.ytdl_filename(ctx['filename']))):
                 self._read_ytdl_file(ctx)
                 if ctx['fragment_index'] > 0 and resume_len == 0:
-                    self.report_error(
+                    self.report_warning(
                         'Inconsistent state of incomplete fragment download. '
                         'Restarting from the beginning...')
                     ctx['fragment_index'] = resume_len = 0

youtube_dl/downloader/hls.py

@@ -88,6 +88,7 @@ class HlsFD(FragmentFD):
             if line.startswith('#'):
                 if anvato_ad(line):
                     ad_frags += 1
+                    ad_frag_next = True
                 continue
             if ad_frag_next:
                 ad_frag_next = False

youtube_dl/extractor/arte.py

@@ -6,6 +6,7 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,
+    compat_str,
     compat_urllib_parse_urlparse,
 )
 from ..utils import (
@@ -15,6 +16,7 @@ from ..utils import (
     int_or_none,
     NO_DEFAULT,
     qualities,
+    try_get,
     unified_strdate,
 )
 
@@ -80,12 +82,15 @@ class ArteTVBaseIE(InfoExtractor):
         info = self._download_json(json_url, video_id)
         player_info = info['videoJsonPlayer']
 
-        vsr = player_info['VSR']
+        vsr = try_get(player_info, lambda x: x['VSR'], dict)
-
         if not vsr:
-            raise ExtractorError(
+            error = None
-                'Video %s is not available' % player_info.get('VID') or video_id,
+            if try_get(player_info, lambda x: x['custom_msg']['type']) == 'error':
-                expected=True)
+                error = try_get(
+                    player_info, lambda x: x['custom_msg']['msg'], compat_str)
+            if not error:
+                error = 'Video %s is not available' % player_info.get('VID') or video_id
+            raise ExtractorError(error, expected=True)
 
         upload_date_str = player_info.get('shootingDate')
         if not upload_date_str:

youtube_dl/extractor/drtv.py

@@ -138,6 +138,7 @@ class DRTVIE(InfoExtractor):
                             'tbr': int_or_none(bitrate),
                             'ext': link.get('FileFormat'),
                             'vcodec': 'none' if kind == 'AudioResource' else None,
+                            'preference': preference,
                         })
                 subtitles_list = asset.get('SubtitlesList')
                 if isinstance(subtitles_list, list):

youtube_dl/extractor/eporner.py

@@ -15,7 +15,7 @@ from ..utils import (
 
 
 class EpornerIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\w+)(?:/(?P<display_id>[\w-]+))?'
+    _VALID_URL = r'https?://(?:www\.)?eporner\.com/(?:hd-porn|embed)/(?P<id>\w+)(?:/(?P<display_id>[\w-]+))?'
     _TESTS = [{
         'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
         'md5': '39d486f046212d8e1b911c52ab4691f8',
@@ -35,6 +35,9 @@ class EpornerIE(InfoExtractor):
     }, {
         'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0',
         'only_matching': True,
+    }, {
+        'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/extractors.py

@@ -925,6 +925,7 @@ from .seeker import SeekerIE
 from .senateisvp import SenateISVPIE
 from .sendtonews import SendtoNewsIE
 from .servingsys import ServingSysIE
+from .servus import ServusIE
 from .sexu import SexuIE
 from .shahid import ShahidIE
 from .shared import (
@@ -1138,6 +1139,7 @@ from .udn import UDNEmbedIE
 from .uktvplay import UKTVPlayIE
 from .digiteka import DigitekaIE
 from .unistra import UnistraIE
+from .unity import UnityIE
 from .uol import UOLIE
 from .uplynk import (
     UplynkIE,

youtube_dl/extractor/megaphone.py

@@ -18,7 +18,7 @@ class MegaphoneIE(InfoExtractor):
             'id': 'GLT9749789991',
             'ext': 'mp3',
             'title': '#97 What Kind Of Idiot Gets Phished?',
-            'thumbnail': 're:^https://.*\.png.*$',
+            'thumbnail': r're:^https://.*\.png.*$',
             'duration': 1776.26375,
             'author': 'Reply All',
         },

youtube_dl/extractor/niconico.py

@@ -40,7 +40,7 @@ class NiconicoIE(InfoExtractor):
             'uploader': 'takuya0301',
             'uploader_id': '2698420',
             'upload_date': '20131123',
-            'timestamp': 1385182762,
+            'timestamp': int,  # timestamp is unstable
             'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
             'duration': 33,
             'view_count': int,
@@ -115,8 +115,8 @@ class NiconicoIE(InfoExtractor):
         'skip': 'Requires an account',
     }, {
         # "New" HTML5 video
+        # md5 is unstable
         'url': 'http://www.nicovideo.jp/watch/sm31464864',
-        'md5': '351647b4917660986dc0fa8864085135',
         'info_dict': {
             'id': 'sm31464864',
             'ext': 'mp4',
@@ -124,7 +124,7 @@ class NiconicoIE(InfoExtractor):
             'description': 'md5:e52974af9a96e739196b2c1ca72b5feb',
             'timestamp': 1498514060,
             'upload_date': '20170626',
-            'uploader': 'ゲス',
+            'uploader': 'ゲスト',
             'uploader_id': '40826363',
             'thumbnail': r're:https?://.*',
             'duration': 198,
@@ -132,6 +132,25 @@ class NiconicoIE(InfoExtractor):
             'comment_count': int,
         },
         'skip': 'Requires an account',
+    }, {
+        # Video without owner
+        'url': 'http://www.nicovideo.jp/watch/sm18238488',
+        'md5': 'd265680a1f92bdcbbd2a507fc9e78a9e',
+        'info_dict': {
+            'id': 'sm18238488',
+            'ext': 'mp4',
+            'title': '【実写版】ミュータントタートルズ',
+            'description': 'md5:15df8988e47a86f9e978af2064bf6d8e',
+            'timestamp': 1341160408,
+            'upload_date': '20120701',
+            'uploader': None,
+            'uploader_id': None,
+            'thumbnail': r're:https?://.*',
+            'duration': 5271,
+            'view_count': int,
+            'comment_count': int,
+        },
+        'skip': 'Requires an account',
     }, {
         'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg',
         'only_matching': True,
@@ -395,7 +414,9 @@ class NiconicoIE(InfoExtractor):
 
         webpage_url = get_video_info('watch_url') or url
 
-        owner = api_data.get('owner', {})
+        # Note: cannot use api_data.get('owner', {}) because owner may be set to "null"
+        # in the JSON, which will cause None to be returned instead of {}.
+        owner = try_get(api_data, lambda x: x.get('owner'), dict) or {}
         uploader_id = get_video_info(['ch_id', 'user_id']) or owner.get('id')
         uploader = get_video_info(['ch_name', 'user_nickname']) or owner.get('nickname')
 

youtube_dl/extractor/parliamentliveuk.py

@@ -11,7 +11,7 @@ class ParliamentLiveUKIE(InfoExtractor):
     _TESTS = [{
         'url': 'http://parliamentlive.tv/Event/Index/c1e9d44d-fd6c-4263-b50f-97ed26cc998b',
         'info_dict': {
-            'id': 'c1e9d44d-fd6c-4263-b50f-97ed26cc998b',
+            'id': '1_af9nv9ym',
             'ext': 'mp4',
             'title': 'Home Affairs Committee',
             'uploader_id': 'FFMPEG-01',
@@ -28,14 +28,14 @@ class ParliamentLiveUKIE(InfoExtractor):
         webpage = self._download_webpage(
             'http://vodplayer.parliamentlive.tv/?mid=' + video_id, video_id)
         widget_config = self._parse_json(self._search_regex(
-            r'kWidgetConfig\s*=\s*({.+});',
+            r'(?s)kWidgetConfig\s*=\s*({.+});',
             webpage, 'kaltura widget config'), video_id)
-        kaltura_url = 'kaltura:%s:%s' % (widget_config['wid'][1:], widget_config['entry_id'])
+        kaltura_url = 'kaltura:%s:%s' % (
+            widget_config['wid'][1:], widget_config['entry_id'])
         event_title = self._download_json(
             'http://parliamentlive.tv/Event/GetShareVideo/' + video_id, video_id)['event']['title']
         return {
             '_type': 'url_transparent',
-            'id': video_id,
             'title': event_title,
             'description': '',
             'url': kaltura_url,

youtube_dl/extractor/pbs.py

@@ -187,7 +187,7 @@ class PBSIE(InfoExtractor):
     _VALID_URL = r'''(?x)https?://
         (?:
            # Direct video URL
-           (?:%s)/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
+           (?:%s)/(?:(?:vir|port)alplayer|video)/(?P<id>[0-9]+)(?:[?/]|$) |
            # Article with embedded player (or direct video)
            (?:www\.)?pbs\.org/(?:[^/]+/){1,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
            # Player
@@ -367,6 +367,10 @@ class PBSIE(InfoExtractor):
         {
             'url': 'http://watch.knpb.org/video/2365616055/',
             'only_matching': True,
+        },
+        {
+            'url': 'https://player.pbs.org/portalplayer/3004638221/?uid=',
+            'only_matching': True,
         }
     ]
     _ERRORS = {

youtube_dl/extractor/servus.py

@@ -0,0 +1,43 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class ServusIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?servus\.com/(?:at|de)/p/[^/]+/(?P<id>AA-\w+|\d+-\d+)'
+    _TESTS = [{
+        'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/',
+        'md5': '046dee641cda1c4cabe13baef3be2c1c',
+        'info_dict': {
+            'id': 'AA-1T6VBU5PW1W12',
+            'ext': 'mp4',
+            'title': 'Die Grünen aus Volkssicht',
+            'description': 'md5:052b5da1cb2cd7d562ef1f19be5a5cba',
+            'thumbnail': r're:^https?://.*\.jpg$',
+        }
+    }, {
+        'url': 'https://www.servus.com/at/p/Wie-das-Leben-beginnt/1309984137314-381415152/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        formats = self._extract_m3u8_formats(
+            'https://stv.rbmbtnx.net/api/v1/manifests/%s.m3u8' % video_id,
+            video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/soundcloud.py

@@ -138,7 +138,7 @@ class SoundcloudIE(InfoExtractor):
         },
     ]
 
-    _CLIENT_ID = 'JlZIsxg2hY5WnBgtn3jfS0UYCl0K8DOg'
+    _CLIENT_ID = 'c6CU49JDMapyrQo06UxU9xouB9ZVzqCn'
     _IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf'
 
     @staticmethod

youtube_dl/extractor/unity.py

@@ -0,0 +1,32 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .youtube import YoutubeIE
+
+
+class UnityIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?unity3d\.com/learn/tutorials/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://unity3d.com/learn/tutorials/topics/animation/animate-anything-mecanim',
+        'info_dict': {
+            'id': 'jWuNtik0C8E',
+            'ext': 'mp4',
+            'title': 'Live Training 22nd September 2014 -  Animate Anything',
+            'description': 'md5:e54913114bd45a554c56cdde7669636e',
+            'duration': 2893,
+            'uploader': 'Unity',
+            'uploader_id': 'Unity3D',
+            'upload_date': '20140926',
+        }
+    }, {
+        'url': 'https://unity3d.com/learn/tutorials/projects/2d-ufo-tutorial/following-player-camera?playlist=25844',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        youtube_id = self._search_regex(
+            r'data-video-id="([_0-9a-zA-Z-]+)"',
+            webpage, 'youtube ID')
+        return self.url_result(youtube_id, ie=YoutubeIE.ie_key(), video_id=video_id)

youtube_dl/extractor/youtube.py

@@ -1622,6 +1622,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         # description
         description_original = video_description = get_element_by_id("eow-description", video_webpage)
         if video_description:
+
+            def replace_url(m):
+                redir_url = compat_urlparse.urljoin(url, m.group(1))
+                parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
+                if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect':
+                    qs = compat_parse_qs(parsed_redir_url.query)
+                    q = qs.get('q')
+                    if q and q[0]:
+                        return q[0]
+                return redir_url
+
             description_original = video_description = re.sub(r'''(?x)
                 <a\s+
                     (?:[a-zA-Z-]+="[^"]*"\s+)*?
@@ -1630,7 +1641,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     class="[^"]*"[^>]*>
                 [^<]+\.{3}\s*
                 </a>
-            ''', lambda m: compat_urlparse.urljoin(url, m.group(1)), video_description)
+            ''', replace_url, video_description)
             video_description = clean_html(video_description)
         else:
             fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2017.10.15.1'
+__version__ = '2017.10.20'