[nbc] Remove CSNNE extractor

youtube_dl/extractor/aenetworks.py

@@ -6,6 +6,7 @@ import re
 from .theplatform import ThePlatformIE
 from ..utils import (
     ExtractorError,
+    GeoRestrictedError,
     int_or_none,
     update_url_query,
     urlencode_postdata,
@@ -28,6 +29,7 @@ class AENetworksBaseIE(ThePlatformIE):
         'lifetimemovieclub.com': ('LIFETIMEMOVIECLUB', 'lmc'),
         'fyi.tv': ('FYI', 'fyi'),
         'historyvault.com': (None, 'historyvault'),
+        'biography.com': (None, 'biography'),
     }
 
     def _extract_aen_smil(self, smil_url, video_id, auth=None):
@@ -54,6 +56,8 @@ class AENetworksBaseIE(ThePlatformIE):
                 tp_formats, tp_subtitles = self._extract_theplatform_smil(
                     m_url, video_id, 'Downloading %s SMIL data' % (q.get('switch') or q['assetTypes']))
             except ExtractorError as e:
+                if isinstance(e, GeoRestrictedError):
+                    raise
                 last_e = e
                 continue
             formats.extend(tp_formats)
@@ -67,6 +71,34 @@ class AENetworksBaseIE(ThePlatformIE):
             'subtitles': subtitles,
         }
 
+    def _extract_aetn_info(self, domain, filter_key, filter_value, url):
+        requestor_id, brand = self._DOMAIN_MAP[domain]
+        result = self._download_json(
+            'https://feeds.video.aetnd.com/api/v2/%s/videos' % brand,
+            filter_value, query={'filter[%s]' % filter_key: filter_value})['results'][0]
+        title = result['title']
+        video_id = result['id']
+        media_url = result['publicUrl']
+        theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
+            r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
+        info = self._parse_theplatform_metadata(theplatform_metadata)
+        auth = None
+        if theplatform_metadata.get('AETN$isBehindWall'):
+            resource = self._get_mvpd_resource(
+                requestor_id, theplatform_metadata['title'],
+                theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
+                theplatform_metadata['ratings'][0]['rating'])
+            auth = self._extract_mvpd_auth(
+                url, video_id, requestor_id, resource)
+        info.update(self._extract_aen_smil(media_url, video_id, auth))
+        info.update({
+            'title': title,
+            'series': result.get('seriesName'),
+            'season_number': int_or_none(result.get('tvSeasonNumber')),
+            'episode_number': int_or_none(result.get('tvSeasonEpisodeNumber')),
+        })
+        return info
+
 
 class AENetworksIE(AENetworksBaseIE):
     IE_NAME = 'aenetworks'
@@ -139,32 +171,7 @@ class AENetworksIE(AENetworksBaseIE):
 
     def _real_extract(self, url):
         domain, canonical = re.match(self._VALID_URL, url).groups()
-        requestor_id, brand = self._DOMAIN_MAP[domain]
-        result = self._download_json(
-            'https://feeds.video.aetnd.com/api/v2/%s/videos' % brand,
-            canonical, query={'filter[canonical]': '/' + canonical})['results'][0]
-        title = result['title']
-        video_id = result['id']
-        media_url = result['publicUrl']
-        theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
-            r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
-        info = self._parse_theplatform_metadata(theplatform_metadata)
-        auth = None
-        if theplatform_metadata.get('AETN$isBehindWall'):
-            resource = self._get_mvpd_resource(
-                requestor_id, theplatform_metadata['title'],
-                theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
-                theplatform_metadata['ratings'][0]['rating'])
-            auth = self._extract_mvpd_auth(
-                url, video_id, requestor_id, resource)
-        info.update(self._extract_aen_smil(media_url, video_id, auth))
-        info.update({
-            'title': title,
-            'series': result.get('seriesName'),
-            'season_number': int_or_none(result.get('tvSeasonNumber')),
-            'episode_number': int_or_none(result.get('tvSeasonEpisodeNumber')),
-        })
-        return info
+        return self._extract_aetn_info(domain, 'canonical', '/' + canonical, url)
 
 
 class AENetworksListBaseIE(AENetworksBaseIE):
@@ -294,3 +301,42 @@ class HistoryTopicIE(AENetworksBaseIE):
         return self.url_result(
             'http://www.history.com/videos/' + display_id,
             AENetworksIE.ie_key())
+
+
+class HistoryPlayerIE(AENetworksBaseIE):
+    IE_NAME = 'history:player'
+    _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|biography)\.com)/player/(?P<id>\d+)'
+    _TESTS = []
+
+    def _real_extract(self, url):
+        domain, video_id = re.match(self._VALID_URL, url).groups()
+        return self._extract_aetn_info(domain, 'id', video_id, url)
+
+
+class BiographyIE(AENetworksBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?biography\.com/video/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.biography.com/video/vincent-van-gogh-full-episode-2075049808',
+        'info_dict': {
+            'id': '30322987',
+            'ext': 'mp4',
+            'title': 'Vincent Van Gogh - Full Episode',
+            'description': 'A full biography about the most influential 20th century painter, Vincent Van Gogh.',
+            'timestamp': 1311970571,
+            'upload_date': '20110729',
+            'uploader': 'AENE-NEW',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'add_ie': ['ThePlatform'],
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        player_url = self._search_regex(
+            r'<phoenix-iframe[^>]+src="(%s)' % HistoryPlayerIE._VALID_URL,
+            webpage, 'player URL')
+        return self.url_result(player_url, HistoryPlayerIE.ie_key())

youtube_dl/extractor/brightcove.py

@@ -471,13 +471,18 @@ class BrightcoveNewIE(AdobePassIE):
     def _parse_brightcove_metadata(self, json_data, video_id, headers={}):
         title = json_data['name'].strip()
 
+        num_drm_sources = 0
         formats = []
-        for source in json_data.get('sources', []):
+        sources = json_data.get('sources') or []
+        for source in sources:
             container = source.get('container')
             ext = mimetype2ext(source.get('type'))
             src = source.get('src')
             # https://support.brightcove.com/playback-api-video-fields-reference#key_systems_object
-            if ext == 'ism' or container == 'WVM' or source.get('key_systems'):
+            if container == 'WVM' or source.get('key_systems'):
+                num_drm_sources += 1
+                continue
+            elif ext == 'ism':
                 continue
             elif ext == 'm3u8' or container == 'M2TS':
                 if not src:
@@ -535,11 +540,14 @@ class BrightcoveNewIE(AdobePassIE):
                     })
                 formats.append(f)
 
+        if not formats:
             errors = json_data.get('errors')
-        if not formats and errors:
+            if errors:
                 error = errors[0]
                 raise ExtractorError(
                     error.get('message') or error.get('error_subcode') or error['error_code'], expected=True)
+            if sources and num_drm_sources == len(sources):
+                raise ExtractorError('This video is DRM protected.', expected=True)
 
         self._sort_formats(formats)
 

youtube_dl/extractor/extractors.py

@@ -33,6 +33,8 @@ from .aenetworks import (
     AENetworksCollectionIE,
     AENetworksShowIE,
     HistoryTopicIE,
+    HistoryPlayerIE,
+    BiographyIE,
 )
 from .afreecatv import AfreecaTVIE
 from .airmozilla import AirMozillaIE
@@ -690,7 +692,6 @@ from .nba import (
     NBAChannelIE,
 )
 from .nbc import (
-    CSNNEIE,
     NBCIE,
     NBCNewsIE,
     NBCOlympicsIE,

youtube_dl/extractor/nbc.py

@@ -158,7 +158,8 @@ class NBCIE(AdobePassIE):
 
 
 class NBCSportsVPlayerIE(InfoExtractor):
-    _VALID_URL = r'https?://vplayer\.nbcsports\.com/(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
+    _VALID_URL_BASE = r'https?://(?:vplayer\.nbcsports\.com|(?:www\.)?nbcsports\.com/vplayer)/'
+    _VALID_URL = _VALID_URL_BASE + r'(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
 
     _TESTS = [{
         'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/9CsDKds0kvHI',
@@ -174,12 +175,15 @@ class NBCSportsVPlayerIE(InfoExtractor):
     }, {
         'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/media/_hqLjQ95yx8Z',
         'only_matching': True,
+    }, {
+        'url': 'https://www.nbcsports.com/vplayer/p/BxmELC/nbcsports/select/PHJSaFWbrTY9?form=html&autoPlay=true',
+        'only_matching': True,
     }]
 
     @staticmethod
     def _extract_url(webpage):
         iframe_m = re.search(
-            r'<iframe[^>]+src="(?P<url>https?://vplayer\.nbcsports\.com/[^"]+)"', webpage)
+            r'<(?:iframe[^>]+|div[^>]+data-(?:mpx-)?)src="(?P<url>%s[^"]+)"' % NBCSportsVPlayerIE._VALID_URL_BASE, webpage)
         if iframe_m:
             return iframe_m.group('url')
 
@@ -192,21 +196,29 @@ class NBCSportsVPlayerIE(InfoExtractor):
 
 
 class NBCSportsIE(InfoExtractor):
-    # Does not include https because its certificate is invalid
-    _VALID_URL = r'https?://(?:www\.)?nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
+    _VALID_URL = r'https?://(?:www\.)?nbcsports\.com//?(?!vplayer/)(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
 
-    _TEST = {
+    _TESTS = [{
+        # iframe src
         'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
         'info_dict': {
             'id': 'PHJSaFWbrTY9',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Tom Izzo, Michigan St. has \'so much respect\' for Duke',
             'description': 'md5:ecb459c9d59e0766ac9c7d5d0eda8113',
             'uploader': 'NBCU-SPORTS',
             'upload_date': '20150330',
             'timestamp': 1427726529,
         }
-    }
+    }, {
+        # data-mpx-src
+        'url': 'https://www.nbcsports.com/philadelphia/philadelphia-phillies/bruce-bochy-hector-neris-hes-idiot',
+        'only_matching': True,
+    }, {
+        # data-src
+        'url': 'https://www.nbcsports.com/boston/video/report-card-pats-secondary-no-match-josh-allen',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -274,33 +286,6 @@ class NBCSportsStreamIE(AdobePassIE):
         }
 
 
-class CSNNEIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?csnne\.com/video/(?P<id>[0-9a-z-]+)'
-
-    _TEST = {
-        'url': 'http://www.csnne.com/video/snc-evening-update-wright-named-red-sox-no-5-starter',
-        'info_dict': {
-            'id': 'yvBLLUgQ8WU0',
-            'ext': 'mp4',
-            'title': 'SNC evening update: Wright named Red Sox\' No. 5 starter.',
-            'description': 'md5:1753cfee40d9352b19b4c9b3e589b9e3',
-            'timestamp': 1459369979,
-            'upload_date': '20160330',
-            'uploader': 'NBCU-SPORTS',
-        }
-    }
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        return {
-            '_type': 'url_transparent',
-            'ie_key': 'ThePlatform',
-            'url': self._html_search_meta('twitter:player:stream', webpage),
-            'display_id': display_id,
-        }
-
-
 class NBCNewsIE(ThePlatformIE):
     _VALID_URL = r'(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/([^/]+/)*(?:.*-)?(?P<id>[^/?]+)'
 

youtube_dl/extractor/sevenplus.py

@@ -4,8 +4,12 @@ from __future__ import unicode_literals
 import re
 
 from .brightcove import BrightcoveNewIE
-from ..compat import compat_str
+from ..compat import (
+    compat_HTTPError,
+    compat_str,
+)
 from ..utils import (
+    ExtractorError,
     try_get,
     update_url_query,
 )
@@ -41,6 +45,7 @@ class SevenPlusIE(BrightcoveNewIE):
     def _real_extract(self, url):
         path, episode_id = re.match(self._VALID_URL, url).groups()
 
+        try:
             media = self._download_json(
                 'https://videoservice.swm.digital/playback', episode_id, query={
                     'appId': '7plus',
@@ -51,6 +56,11 @@ class SevenPlusIE(BrightcoveNewIE):
                     'deliveryId': 'csai',
                     'videoType': 'vod',
                 })['media']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+                raise ExtractorError(self._parse_json(
+                    e.cause.read().decode(), episode_id)[0]['error_code'], expected=True)
+            raise
 
         for source in media.get('sources', {}):
             src = source.get('src')

youtube_dl/extractor/tenplay.py

@@ -3,9 +3,10 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
+    HEADRequest,
     parse_age_limit,
     parse_iso8601,
-    smuggle_url,
+    # smuggle_url,
 )
 
 
@@ -24,14 +25,16 @@ class TenPlayIE(InfoExtractor):
             'uploader_id': '2199827728001',
         },
         'params': {
-            'format': 'bestvideo',
+            # 'format': 'bestvideo',
             'skip_download': True,
         }
     }, {
         'url': 'https://10play.com.au/how-to-stay-married/web-extras/season-1/terrys-talks-ep-1-embracing-change/tpv190915ylupc',
         'only_matching': True,
     }]
-    BRIGHTCOVE_URL_TEMPLATE = 'https://players.brightcove.net/2199827728001/cN6vRtRQt_default/index.html?videoId=%s'
+    # BRIGHTCOVE_URL_TEMPLATE = 'https://players.brightcove.net/2199827728001/cN6vRtRQt_default/index.html?videoId=%s'
+    _GEO_BYPASS = False
+    _FASTLY_URL_TEMPL = 'https://10-selector.global.ssl.fastly.net/s/kYEXFC/media/%s?mbr=true&manifest=m3u&format=redirect'
 
     def _real_extract(self, url):
         content_id = self._match_id(url)
@@ -40,19 +43,28 @@ class TenPlayIE(InfoExtractor):
         video = data.get('video') or {}
         metadata = data.get('metaData') or {}
         brightcove_id = video.get('videoId') or metadata['showContentVideoId']
-        brightcove_url = smuggle_url(
-            self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
-            {'geo_countries': ['AU']})
+        # brightcove_url = smuggle_url(
+        #     self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
+        #     {'geo_countries': ['AU']})
+        m3u8_url = self._request_webpage(HEADRequest(
+            self._FASTLY_URL_TEMPL % brightcove_id), brightcove_id).geturl()
+        if '10play-not-in-oz' in m3u8_url:
+            self.raise_geo_restricted(countries=['AU'])
+        formats = self._extract_m3u8_formats(m3u8_url, brightcove_id, 'mp4')
+        self._sort_formats(formats)
 
         return {
-            '_type': 'url_transparent',
-            'url': brightcove_url,
-            'id': content_id,
-            'title': video.get('title') or metadata.get('pageContentName') or metadata.get('showContentName'),
+            # '_type': 'url_transparent',
+            # 'url': brightcove_url,
+            'formats': formats,
+            'id': brightcove_id,
+            'title': video.get('title') or metadata.get('pageContentName') or metadata['showContentName'],
             'description': video.get('description'),
             'age_limit': parse_age_limit(video.get('showRatingClassification') or metadata.get('showProgramClassification')),
             'series': metadata.get('showName'),
             'season': metadata.get('showContentSeason'),
             'timestamp': parse_iso8601(metadata.get('contentPublishDate') or metadata.get('pageContentPublishDate')),
-            'ie_key': 'BrightcoveNew',
+            'thumbnail': video.get('poster'),
+            'uploader_id': '2199827728001',
+            # 'ie_key': 'BrightcoveNew',
         }

youtube_dl/extractor/uktvplay.py

@@ -5,10 +5,9 @@ from .common import InfoExtractor
 
 
 class UKTVPlayIE(InfoExtractor):
-    _VALID_URL = r'https?://uktvplay\.uktv\.co\.uk/.+?\?.*?\bvideo=(?P<id>\d+)'
-    _TEST = {
+    _VALID_URL = r'https?://uktvplay\.uktv\.co\.uk/(?:.+?\?.*?\bvideo=|([^/]+/)*watch-online/)(?P<id>\d+)'
+    _TESTS = [{
         'url': 'https://uktvplay.uktv.co.uk/shows/world-at-war/c/200/watch-online/?video=2117008346001',
-        'md5': '',
         'info_dict': {
             'id': '2117008346001',
             'ext': 'mp4',
@@ -23,7 +22,11 @@ class UKTVPlayIE(InfoExtractor):
             'skip_download': True,
         },
         'expected_warnings': ['Failed to download MPD manifest']
-    }
+    }, {
+        'url': 'https://uktvplay.uktv.co.uk/shows/africa/watch-online/5983349675001',
+        'only_matching': True,
+    }]
+    # BRIGHTCOVE_URL_TEMPLATE = 'https://players.brightcove.net/1242911124001/OrCyvJ2gyL_default/index.html?videoId=%s'
     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1242911124001/H1xnMOqP_default/index.html?videoId=%s'
 
     def _real_extract(self, url):