Merge branch 'master' into GoogleDrive-issue-13619

.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 *2017.07.30.1*. 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 Issues with outdated version will be rejected.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 *2017.08.06*. 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 Issues with outdated version will be rejected.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 **2017.07.30.1**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.08.06**
 
 ### 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 2017.07.30.1
+[debug] youtube-dl version 2017.08.06
 [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 +1,25 @@
+version 2017.08.06
+
+Core
+* Use relative paths for DASH fragments (#12990)
+
+Extractors
+* [pluralsight] Fix format selection
+- [mpora] Remove extractor (#13826)
++ [voot] Add support for voot.com (#10255, #11644, #11814, #12350, #13218)
+* [vlive:channel] Limit number of videos per page to 100 (#13830)
+* [podomatic] Extend URL regular expression (#13827)
+* [cinchcast] Extend URL regular expression
+* [yandexdisk] Relax URL regular expression (#13824)
+* [vidme] Extract DASH and HLS formats
+- [teamfour] Remove extractor (#13782)
+* [pornhd] Fix extraction (#13783)
+* [udemy] Fix subtitles extraction (#13812)
+* [mlb] Extend URL regular expression (#13740, #13773)
++ [pbs] Add support for new URL schema (#13801)
+* [nrktv] Update API host (#13796)
+
+
 version 2017.07.30.1
 
 Core

docs/supportedsites.md

@@ -472,7 +472,6 @@
  - **MovieFap**
  - **Moviezine**
  - **MovingImage**
- - **MPORA**
  - **MSN**
  - **mtg**: MTG services
  - **mtv**
@@ -783,7 +782,6 @@
  - **teachertube:user:collection**: teachertube.com user and collection videos
  - **TeachingChannel**
  - **Teamcoco**
- - **TeamFourStar**
  - **TechTalks**
  - **techtv.mit.edu**
  - **ted**
@@ -953,6 +951,7 @@
  - **VODPl**
  - **VODPlatform**
  - **VoiceRepublic**
+ - **Voot**
  - **VoxMedia**
  - **Vporn**
  - **vpro**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl

youtube_dl/extractor/cinchcast.py

@@ -9,12 +9,20 @@ from ..utils import (
 
 
 class CinchcastIE(InfoExtractor):
-    _VALID_URL = r'https?://player\.cinchcast\.com/.*?assetId=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://player\.cinchcast\.com/.*?(?:assetId|show_id)=(?P<id>[0-9]+)'
-    _TEST = {
+    _TESTS = [{
+        'url': 'http://player.cinchcast.com/?show_id=5258197&platformId=1&assetType=single',
+        'info_dict': {
+            'id': '5258197',
+            'ext': 'mp3',
+            'title': 'Train Your Brain to Up Your Game with Coach Mandy',
+            'upload_date': '20130816',
+        },
+    }, {
         # Actual test is run in generic, look for undergroundwellness
         'url': 'http://player.cinchcast.com/?platformId=1&#038;assetType=single&#038;assetId=7141703',
         'only_matching': True,
-    }
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/extractors.py

@@ -584,7 +584,6 @@ from .mixcloud import (
 )
 from .mlb import MLBIE
 from .mnet import MnetIE
-from .mpora import MporaIE
 from .moevideo import MoeVideoIE
 from .mofosex import MofosexIE
 from .mojvideo import MojvideoIE
@@ -1222,6 +1221,7 @@ from .vodlocker import VodlockerIE
 from .vodpl import VODPlIE
 from .vodplatform import VODPlatformIE
 from .voicerepublic import VoiceRepublicIE
+from .voot import VootIE
 from .voxmedia import VoxMediaIE
 from .vporn import VpornIE
 from .vrt import VRTIE

youtube_dl/extractor/mpora.py

@@ -1,62 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..utils import int_or_none
-
-
-class MporaIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?mpora\.(?:com|de)/videos/(?P<id>[^?#/]+)'
-    IE_NAME = 'MPORA'
-
-    _TEST = {
-        'url': 'http://mpora.de/videos/AAdo8okx4wiz/embed?locale=de',
-        'md5': 'a7a228473eedd3be741397cf452932eb',
-        'info_dict': {
-            'id': 'AAdo8okx4wiz',
-            'ext': 'mp4',
-            'title': 'Katy Curd -  Winter in the Forest',
-            'duration': 416,
-            'uploader': 'Peter Newman Media',
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        data_json = self._search_regex(
-            [r"new FM\.Player\('[^']+',\s*(\{.*?)\).player;",
-             r"new\s+FM\.Kaltura\.Player\('[^']+'\s*,\s*({.+?})\);"],
-            webpage, 'json')
-        data = self._parse_json(data_json, video_id)
-
-        uploader = data['info_overlay'].get('username')
-        duration = data['video']['duration'] // 1000
-        thumbnail = data['video']['encodings']['sd']['poster']
-        title = data['info_overlay']['title']
-
-        formats = []
-        for encoding_id, edata in data['video']['encodings'].items():
-            for src in edata['sources']:
-                width_str = self._search_regex(
-                    r'_([0-9]+)\.[a-zA-Z0-9]+$', src['src'],
-                    False, default=None)
-                vcodec = src['type'].partition('/')[2]
-
-                formats.append({
-                    'format_id': encoding_id + '-' + vcodec,
-                    'url': src['src'],
-                    'vcodec': vcodec,
-                    'width': int_or_none(width_str),
-                })
-
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'formats': formats,
-            'uploader': uploader,
-            'duration': duration,
-            'thumbnail': thumbnail,
-        }

youtube_dl/extractor/pluralsight.py

@@ -224,6 +224,7 @@ class PluralsightIE(PluralsightBaseIE):
                 req_format_split = req_format.split('-', 1)
                 if len(req_format_split) > 1:
                     req_ext, req_quality = req_format_split
+                    req_quality = '-'.join(req_quality.split('-')[:2])
                     for allowed_quality in ALLOWED_QUALITIES:
                         if req_ext == allowed_quality.ext and req_quality in allowed_quality.qualities:
                             return (AllowedQuality(req_ext, (req_quality, )), )

youtube_dl/extractor/podomatic.py

@@ -9,10 +9,16 @@ from ..utils import int_or_none
 
 class PodomaticIE(InfoExtractor):
     IE_NAME = 'podomatic'
-    _VALID_URL = r'^(?P<proto>https?)://(?P<channel>[^.]+)\.podomatic\.com/entry/(?P<id>[^?]+)'
+    _VALID_URL = r'''(?x)
+                    (?P<proto>https?)://
+                        (?:
+                            (?P<channel>[^.]+)\.podomatic\.com/entry|
+                            (?:www\.)?podomatic\.com/podcasts/(?P<channel_2>[^/]+)/episodes
+                        )/
+                        (?P<id>[^/?#&]+)
+                '''
 
-    _TESTS = [
+    _TESTS = [{
-        {
         'url': 'http://scienceteachingtips.podomatic.com/entry/2009-01-02T16_03_35-08_00',
         'md5': '84bb855fcf3429e6bf72460e1eed782d',
         'info_dict': {
@@ -23,8 +29,7 @@ class PodomaticIE(InfoExtractor):
             'title': '64.  When the Moon Hits Your Eye',
             'duration': 446,
         }
-        },
+    }, {
-        {
         'url': 'http://ostbahnhof.podomatic.com/entry/2013-11-15T16_31_21-08_00',
         'md5': 'd2cf443931b6148e27638650e2638297',
         'info_dict': {
@@ -35,13 +40,15 @@ class PodomaticIE(InfoExtractor):
             'title': 'Einunddreizig',
             'duration': 3799,
         }
-        },
+    }, {
-    ]
+        'url': 'https://www.podomatic.com/podcasts/scienceteachingtips/episodes/2009-01-02T16_03_35-08_00',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        channel = mobj.group('channel')
+        channel = mobj.group('channel') or mobj.group('channel_2')
 
         json_url = (('%s://%s.podomatic.com/entry/embed_params/%s' +
                      '?permalink=true&rtmp=0') %

youtube_dl/extractor/vlive.py

@@ -236,7 +236,12 @@ class VLiveChannelIE(InfoExtractor):
                 query={
                     'app_id': app_id,
                     'channelSeq': channel_seq,
-                    'maxNumOfRows': 1000,
+                    # Large values of maxNumOfRows (~300 or above) may cause
+                    # empty responses (see [1]), e.g. this happens for [2] that
+                    # has more than 300 videos.
+                    # 1. https://github.com/rg3/youtube-dl/issues/13830
+                    # 2. http://channels.vlive.tv/EDBF.
+                    'maxNumOfRows': 100,
                     '_': int(time.time()),
                     'pageNo': page_num
                 }

youtube_dl/extractor/voot.py

@@ -0,0 +1,98 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .kaltura import KalturaIE
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    try_get,
+    unified_timestamp,
+)
+
+
+class VootIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?voot\.com/(?:[^/]+/)+(?P<id>\d+)'
+    _GEO_COUNTRIES = ['IN']
+    _TESTS = [{
+        'url': 'https://www.voot.com/shows/ishq-ka-rang-safed/1/360558/is-this-the-end-of-kamini-/441353',
+        'info_dict': {
+            'id': '0_8ledb18o',
+            'ext': 'mp4',
+            'title': 'Ishq Ka Rang Safed - Season 01 - Episode 340',
+            'description': 'md5:06291fbbbc4dcbe21235c40c262507c1',
+            'uploader_id': 'batchUser',
+            'timestamp': 1472162937,
+            'upload_date': '20160825',
+            'duration': 1146,
+            'series': 'Ishq Ka Rang Safed',
+            'season_number': 1,
+            'episode': 'Is this the end of Kamini?',
+            'episode_number': 340,
+            'view_count': int,
+            'like_count': int,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'expected_warnings': ['Failed to download m3u8 information'],
+    }, {
+        'url': 'https://www.voot.com/kids/characters/mighty-cat-masked-niyander-e-/400478/school-bag-disappears/440925',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.voot.com/movies/pandavas-5/424627',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        media_info = self._download_json(
+            'https://wapi.voot.com/ws/ott/getMediaInfo.json', video_id,
+            query={
+                'platform': 'Web',
+                'pId': 2,
+                'mediaId': video_id,
+            })
+
+        status_code = try_get(media_info, lambda x: x['status']['code'], int)
+        if status_code != 0:
+            raise ExtractorError(media_info['status']['message'], expected=True)
+
+        media = media_info['assets']
+
+        entry_id = media['EntryId']
+        title = media['MediaName']
+
+        description, series, season_number, episode, episode_number = [None] * 5
+
+        for meta in try_get(media, lambda x: x['Metas'], list) or []:
+            key, value = meta.get('Key'), meta.get('Value')
+            if not key or not value:
+                continue
+            if key == 'ContentSynopsis':
+                description = value
+            elif key == 'RefSeriesTitle':
+                series = value
+            elif key == 'RefSeriesSeason':
+                season_number = int_or_none(value)
+            elif key == 'EpisodeMainTitle':
+                episode = value
+            elif key == 'EpisodeNo':
+                episode_number = int_or_none(value)
+
+        return {
+            '_type': 'url_transparent',
+            'url': 'kaltura:1982551:%s' % entry_id,
+            'ie_key': KalturaIE.ie_key(),
+            'title': title,
+            'description': description,
+            'series': series,
+            'season_number': season_number,
+            'episode': episode,
+            'episode_number': episode_number,
+            'timestamp': unified_timestamp(media.get('CreationDate')),
+            'duration': int_or_none(media.get('Duration')),
+            'view_count': int_or_none(media.get('ViewCounter')),
+            'like_count': int_or_none(media.get('like_counter')),
+        }

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2017.07.30.1'
+__version__ = '2017.08.06'