Merge branch 'ytdl-org:master' into mevious/funimation-playlist

youtube_dl/YoutubeDL.py

@@ -773,11 +773,20 @@ class YoutubeDL(object):
 
     def extract_info(self, url, download=True, ie_key=None, extra_info={},
                      process=True, force_generic_extractor=False):
-        '''
-        Returns a list with a dictionary for each video we find.
-        If 'download', also downloads the videos.
-        extra_info is a dict containing the extra values to add to each result
-        '''
+        """
+        Return a list with a dictionary for each video extracted.
+
+        Arguments:
+        url -- URL to extract
+
+        Keyword arguments:
+        download -- whether to download videos during extraction
+        ie_key -- extractor key hint
+        extra_info -- dictionary containing the extra values to add to each result
+        process -- whether to resolve all unresolved references (URLs, playlist items),
+            must be True for download to work.
+        force_generic_extractor -- force using the generic extractor
+        """
 
         if not ie_key and force_generic_extractor:
             ie_key = 'Generic'

youtube_dl/extractor/blinkx.py

@@ -1,86 +0,0 @@
-from __future__ import unicode_literals
-
-import json
-
-from .common import InfoExtractor
-from ..utils import (
-    remove_start,
-    int_or_none,
-)
-
-
-class BlinkxIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://(?:www\.)blinkx\.com/#?ce/|blinkx:)(?P<id>[^?]+)'
-    IE_NAME = 'blinkx'
-
-    _TEST = {
-        'url': 'http://www.blinkx.com/ce/Da0Gw3xc5ucpNduzLuDDlv4WC9PuI4fDi1-t6Y3LyfdY2SZS5Urbvn-UPJvrvbo8LTKTc67Wu2rPKSQDJyZeeORCR8bYkhs8lI7eqddznH2ofh5WEEdjYXnoRtj7ByQwt7atMErmXIeYKPsSDuMAAqJDlQZ-3Ff4HJVeH_s3Gh8oQ',
-        'md5': '337cf7a344663ec79bf93a526a2e06c7',
-        'info_dict': {
-            'id': 'Da0Gw3xc',
-            'ext': 'mp4',
-            'title': 'No Daily Show for John Oliver; HBO Show Renewed - IGN News',
-            'uploader': 'IGN News',
-            'upload_date': '20150217',
-            'timestamp': 1424215740,
-            'description': 'HBO has renewed Last Week Tonight With John Oliver for two more seasons.',
-            'duration': 47.743333,
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        display_id = video_id[:8]
-
-        api_url = ('https://apib4.blinkx.com/api.php?action=play_video&'
-                   + 'video=%s' % video_id)
-        data_json = self._download_webpage(api_url, display_id)
-        data = json.loads(data_json)['api']['results'][0]
-        duration = None
-        thumbnails = []
-        formats = []
-        for m in data['media']:
-            if m['type'] == 'jpg':
-                thumbnails.append({
-                    'url': m['link'],
-                    'width': int(m['w']),
-                    'height': int(m['h']),
-                })
-            elif m['type'] == 'original':
-                duration = float(m['d'])
-            elif m['type'] == 'youtube':
-                yt_id = m['link']
-                self.to_screen('Youtube video detected: %s' % yt_id)
-                return self.url_result(yt_id, 'Youtube', video_id=yt_id)
-            elif m['type'] in ('flv', 'mp4'):
-                vcodec = remove_start(m['vcodec'], 'ff')
-                acodec = remove_start(m['acodec'], 'ff')
-                vbr = int_or_none(m.get('vbr') or m.get('vbitrate'), 1000)
-                abr = int_or_none(m.get('abr') or m.get('abitrate'), 1000)
-                tbr = vbr + abr if vbr and abr else None
-                format_id = '%s-%sk-%s' % (vcodec, tbr, m['w'])
-                formats.append({
-                    'format_id': format_id,
-                    'url': m['link'],
-                    'vcodec': vcodec,
-                    'acodec': acodec,
-                    'abr': abr,
-                    'vbr': vbr,
-                    'tbr': tbr,
-                    'width': int_or_none(m.get('w')),
-                    'height': int_or_none(m.get('h')),
-                })
-
-        self._sort_formats(formats)
-
-        return {
-            'id': display_id,
-            'fullid': video_id,
-            'title': data['title'],
-            'formats': formats,
-            'uploader': data['channel_name'],
-            'timestamp': data['pubdate_epoch'],
-            'description': data.get('description'),
-            'thumbnails': thumbnails,
-            'duration': duration,
-        }

youtube_dl/extractor/dispeak.py

@@ -32,6 +32,18 @@ class DigitallySpeakingIE(InfoExtractor):
         # From http://www.gdcvault.com/play/1013700/Advanced-Material
         'url': 'http://sevt.dispeak.com/ubm/gdc/eur10/xml/11256_1282118587281VNIT.xml',
         'only_matching': True,
+    }, {
+        # From https://gdcvault.com/play/1016624, empty speakerVideo
+        'url': 'https://sevt.dispeak.com/ubm/gdc/online12/xml/201210-822101_1349794556671DDDD.xml',
+        'info_dict': {
+            'id': '201210-822101_1349794556671DDDD',
+            'ext': 'flv',
+            'title': 'Pre-launch - Preparing to Take the Plunge',
+        },
+    }, {
+        # From http://www.gdcvault.com/play/1014846/Conference-Keynote-Shigeru, empty slideVideo
+        'url': 'http://events.digitallyspeaking.com/gdc/project25/xml/p25-miyamoto1999_1282467389849HSVB.xml',
+        'only_matching': True,
     }]
 
     def _parse_mp4(self, metadata):
@@ -84,25 +96,19 @@ class DigitallySpeakingIE(InfoExtractor):
                 'vcodec': 'none',
                 'format_id': audio.get('code'),
             })
-        slide_video_path = xpath_text(metadata, './slideVideo', fatal=True)
+        for video_key, format_id, preference in (
+                ('slide', 'slides', -2), ('speaker', 'speaker', -1)):
+            video_path = xpath_text(metadata, './%sVideo' % video_key)
+            if not video_path:
+                continue
             formats.append({
                 'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url,
-            'play_path': remove_end(slide_video_path, '.flv'),
+                'play_path': remove_end(video_path, '.flv'),
                 'ext': 'flv',
-            'format_note': 'slide deck video',
-            'quality': -2,
-            'preference': -2,
-            'format_id': 'slides',
-        })
-        speaker_video_path = xpath_text(metadata, './speakerVideo', fatal=True)
-        formats.append({
-            'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url,
-            'play_path': remove_end(speaker_video_path, '.flv'),
-            'ext': 'flv',
-            'format_note': 'speaker video',
-            'quality': -1,
-            'preference': -1,
-            'format_id': 'speaker',
+                'format_note': '%s video' % video_key,
+                'quality': preference,
+                'preference': preference,
+                'format_id': format_id,
             })
         return formats
 

youtube_dl/extractor/extractors.py

@@ -132,7 +132,6 @@ from .bleacherreport import (
     BleacherReportIE,
     BleacherReportCMSIE,
 )
-from .blinkx import BlinkxIE
 from .bloomberg import BloombergIE
 from .bokecc import BokeCCIE
 from .bongacams import BongaCamsIE

youtube_dl/extractor/funimation.py

@@ -17,7 +17,7 @@ from ..utils import (
 
 
 class FunimationIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/shows/[^/]+/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/(?:[^/]+/)?shows/[^/]+/(?P<id>[^/?#&]+)'
 
     _NETRC_MACHINE = 'funimation'
     _TOKEN = None
@@ -52,6 +52,10 @@ class FunimationIE(InfoExtractor):
     }, {
         'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
         'only_matching': True,
+    }, {
+        # with lang code
+        'url': 'https://www.funimation.com/en/shows/hacksign/role-play/',
+        'only_matching': True,
     }]
 
     def _login(self):

youtube_dl/extractor/gdcvault.py

@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from .kaltura import KalturaIE
 from ..utils import (
     HEADRequest,
+    remove_start,
     sanitized_Request,
     smuggle_url,
     urlencode_postdata,
@@ -102,6 +103,26 @@ class GDCVaultIE(InfoExtractor):
                 'format': 'mp4-408',
             },
         },
+        {
+            # Kaltura embed, whitespace between quote and embedded URL in iframe's src
+            'url': 'https://www.gdcvault.com/play/1025699',
+            'info_dict': {
+                'id': '0_zagynv0a',
+                'ext': 'mp4',
+                'title': 'Tech Toolbox',
+                'upload_date': '20190408',
+                'uploader_id': 'joe@blazestreaming.com',
+                'timestamp': 1554764629,
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
+        {
+            # HTML5 video
+            'url': 'http://www.gdcvault.com/play/1014846/Conference-Keynote-Shigeru',
+            'only_matching': True,
+        },
     ]
 
     def _login(self, webpage_url, display_id):
@@ -175,7 +196,18 @@ class GDCVaultIE(InfoExtractor):
 
             xml_name = self._html_search_regex(
                 r'<iframe src=".*?\?xml(?:=|URL=xml/)(.+?\.xml).*?".*?</iframe>',
-                start_page, 'xml filename')
+                start_page, 'xml filename', default=None)
+            if not xml_name:
+                info = self._parse_html5_media_entries(url, start_page, video_id)[0]
+                info.update({
+                    'title': remove_start(self._search_regex(
+                        r'>Session Name:\s*<.*?>\s*<td>(.+?)</td>', start_page,
+                        'title', default=None) or self._og_search_title(
+                        start_page, default=None), 'GDC Vault - '),
+                    'id': video_id,
+                    'display_id': display_id,
+                })
+                return info
             embed_url = '%s/xml/%s' % (xml_root, xml_name)
             ie_key = 'DigitallySpeaking'
 

youtube_dl/extractor/kaltura.py

@@ -120,7 +120,7 @@ class KalturaIE(InfoExtractor):
     def _extract_urls(webpage):
         # Embed codes: https://knowledge.kaltura.com/embedding-kaltura-media-players-your-site
         finditer = (
-            re.finditer(
+            list(re.finditer(
                 r"""(?xs)
                     kWidget\.(?:thumb)?[Ee]mbed\(
                     \{.*?
@@ -128,8 +128,8 @@ class KalturaIE(InfoExtractor):
                         (?P<q2>['"])_?(?P<partner_id>(?:(?!(?P=q2)).)+)(?P=q2),.*?
                         (?P<q3>['"])entry_?[Ii]d(?P=q3)\s*:\s*
                         (?P<q4>['"])(?P<id>(?:(?!(?P=q4)).)+)(?P=q4)(?:,|\s*\})
-                """, webpage)
-            or re.finditer(
+                """, webpage))
+            or list(re.finditer(
                 r'''(?xs)
                     (?P<q1>["'])
                         (?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)*
@@ -142,16 +142,16 @@ class KalturaIE(InfoExtractor):
                         \[\s*(?P<q2_1>["'])entry_?[Ii]d(?P=q2_1)\s*\]\s*=\s*
                     )
                     (?P<q3>["'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3)
-                ''', webpage)
-            or re.finditer(
+                ''', webpage))
+            or list(re.finditer(
                 r'''(?xs)
-                    <(?:iframe[^>]+src|meta[^>]+\bcontent)=(?P<q1>["'])
+                    <(?:iframe[^>]+src|meta[^>]+\bcontent)=(?P<q1>["'])\s*
                       (?:https?:)?//(?:(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)
                       (?:(?!(?P=q1)).)*
                       [?&;]entry_id=(?P<id>(?:(?!(?P=q1))[^&])+)
                       (?:(?!(?P=q1)).)*
                     (?P=q1)
-                ''', webpage)
+                ''', webpage))
         )
         urls = []
         for mobj in finditer:

youtube_dl/extractor/medaltv.py

@@ -15,7 +15,7 @@ from ..utils import (
 
 
 class MedalTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?medal\.tv/clips/(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?medal\.tv/clips/(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'https://medal.tv/clips/2mA60jWAGQCBH',
         'md5': '7b07b064331b1cf9e8e5c52a06ae68fa',
@@ -42,6 +42,12 @@ class MedalTVIE(InfoExtractor):
             'upload_date': '20201117',
             'uploader_id': '5156321',
         }
+    }, {
+        'url': 'https://medal.tv/clips/37rMeFpryCC-9',
+        'only_matching': True,
+    }, {
+        'url': 'https://medal.tv/clips/2WRj40tpY_EU9',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):