[tva] Add support for qub.ca (closes #27235)

youtube_dl/extractor/extractors.py

@@ -1185,7 +1185,10 @@ from .tnaflix import (
     EMPFlixIE,
     MovieFapIE,
 )
-from .toggle import ToggleIE
+from .toggle import (
+    ToggleIE,
+    MeWatchIE,
+)
 from .tonline import TOnlineIE
 from .toongoggles import ToonGogglesIE
 from .toutv import TouTvIE

youtube_dl/extractor/toggle.py

@@ -11,13 +11,13 @@ from ..utils import (
     float_or_none,
     int_or_none,
     parse_iso8601,
-    sanitized_Request,
+    strip_or_none,
 )
 
 
 class ToggleIE(InfoExtractor):
     IE_NAME = 'toggle'
-    _VALID_URL = r'https?://(?:(?:www\.)?mewatch|video\.toggle)\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P<id>[0-9]+)'
+    _VALID_URL = r'(?:https?://(?:(?:www\.)?mewatch|video\.toggle)\.sg/(?:en|zh)/(?:[^/]+/){2,}|toggle:)(?P<id>[0-9]+)'
     _TESTS = [{
         'url': 'http://www.mewatch.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115',
         'info_dict': {
@@ -84,28 +84,12 @@ class ToggleIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    _FORMAT_PREFERENCES = {
-        'wvm-STBMain': -10,
-        'wvm-iPadMain': -20,
-        'wvm-iPhoneMain': -30,
-        'wvm-Android': -40,
-    }
     _API_USER = 'tvpapi_147'
     _API_PASS = '11111'
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(
-            url, video_id, note='Downloading video page')
-
-        api_user = self._search_regex(
-            r'apiUser\s*:\s*(["\'])(?P<user>.+?)\1', webpage, 'apiUser',
-            default=self._API_USER, group='user')
-        api_pass = self._search_regex(
-            r'apiPass\s*:\s*(["\'])(?P<pass>.+?)\1', webpage, 'apiPass',
-            default=self._API_PASS, group='pass')
-
         params = {
             'initObj': {
                 'Locale': {
@@ -118,17 +102,16 @@ class ToggleIE(InfoExtractor):
                 'SiteGuid': 0,
                 'DomainID': '0',
                 'UDID': '',
-                'ApiUser': api_user,
+                'ApiUser': self._API_USER,
-                'ApiPass': api_pass
+                'ApiPass': self._API_PASS
             },
             'MediaID': video_id,
             'mediaType': 0,
         }
 
-        req = sanitized_Request(
+        info = self._download_json(
             'http://tvpapi.as.tvinci.com/v2_9/gateways/jsonpostgw.aspx?m=GetMediaInfo',
-            json.dumps(params).encode('utf-8'))
+            video_id, 'Downloading video info json', data=json.dumps(params).encode('utf-8'))
-        info = self._download_json(req, video_id, 'Downloading video info json')
 
         title = info['MediaName']
 
@@ -141,11 +124,16 @@ class ToggleIE(InfoExtractor):
             vid_format = vid_format.replace(' ', '')
             # if geo-restricted, m3u8 is inaccessible, but mp4 is okay
             if ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
+                m3u8_formats = self._extract_m3u8_formats(
                     video_url, video_id, ext='mp4', m3u8_id=vid_format,
                     note='Downloading %s m3u8 information' % vid_format,
                     errnote='Failed to download %s m3u8 information' % vid_format,
-                    fatal=False))
+                    fatal=False)
+                for f in m3u8_formats:
+                    # Apple FairPlay Streaming
+                    if '/fpshls/' in f['url']:
+                        continue
+                    formats.append(f)
             elif ext == 'mpd':
                 formats.extend(self._extract_mpd_formats(
                     video_url, video_id, mpd_id=vid_format,
@@ -158,28 +146,21 @@ class ToggleIE(InfoExtractor):
                     note='Downloading %s ISM manifest' % vid_format,
                     errnote='Failed to download %s ISM manifest' % vid_format,
                     fatal=False))
-            elif ext in ('mp4', 'wvm'):
+            elif ext == 'mp4':
-                # wvm are drm-protected files
                 formats.append({
                     'ext': ext,
                     'url': video_url,
                     'format_id': vid_format,
-                    'preference': self._FORMAT_PREFERENCES.get(ext + '-' + vid_format) or -1,
-                    'format_note': 'DRM-protected video' if ext == 'wvm' else None
                 })
         if not formats:
+            for meta in (info.get('Metas') or []):
+                if meta.get('Key') == 'Encryption' and meta.get('Value') == '1':
+                    raise ExtractorError(
+                        'This video is DRM protected.', expected=True)
             # Most likely because geo-blocked
             raise ExtractorError('No downloadable videos found', expected=True)
         self._sort_formats(formats)
 
-        duration = int_or_none(info.get('Duration'))
-        description = info.get('Description')
-        created_at = parse_iso8601(info.get('CreationDate') or None)
-
-        average_rating = float_or_none(info.get('Rating'))
-        view_count = int_or_none(info.get('ViewCounter') or info.get('view_counter'))
-        like_count = int_or_none(info.get('LikeCounter') or info.get('like_counter'))
-
         thumbnails = []
         for picture in info.get('Pictures', []):
             if not isinstance(picture, dict):
@@ -199,15 +180,46 @@ class ToggleIE(InfoExtractor):
                 })
             thumbnails.append(thumbnail)
 
+        def counter(prefix):
+            return int_or_none(
+                info.get(prefix + 'Counter') or info.get(prefix.lower() + '_counter'))
+
         return {
             'id': video_id,
             'title': title,
-            'description': description,
+            'description': strip_or_none(info.get('Description')),
-            'duration': duration,
+            'duration': int_or_none(info.get('Duration')),
-            'timestamp': created_at,
+            'timestamp': parse_iso8601(info.get('CreationDate') or None),
-            'average_rating': average_rating,
+            'average_rating': float_or_none(info.get('Rating')),
-            'view_count': view_count,
+            'view_count': counter('View'),
-            'like_count': like_count,
+            'like_count': counter('Like'),
             'thumbnails': thumbnails,
             'formats': formats,
         }
+
+
+class MeWatchIE(InfoExtractor):
+    IE_NAME = 'mewatch'
+    _VALID_URL = r'https?://(?:www\.)?mewatch\.sg/watch/[0-9a-zA-Z-]+-(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://www.mewatch.sg/watch/Recipe-Of-Life-E1-179371',
+        'info_dict': {
+            'id': '1008625',
+            'ext': 'mp4',
+            'title': 'Recipe Of Life 味之道',
+            'timestamp': 1603306526,
+            'description': 'md5:6e88cde8af2068444fc8e1bc3ebf257c',
+            'upload_date': '20201021',
+        },
+        'params': {
+            'skip_download': 'm3u8 download',
+        },
+    }]
+
+    def _real_extract(self, url):
+        item_id = self._match_id(url)
+        custom_id = self._download_json(
+            'https://cdn.mewatch.sg/api/items/' + item_id,
+            item_id, query={'segments': 'all'})['customId']
+        return self.url_result(
+            'toggle:' + custom_id, ToggleIE.ie_key(), custom_id)

youtube_dl/extractor/tva.py

@@ -4,7 +4,9 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from ..utils import (
     float_or_none,
+    int_or_none,
     smuggle_url,
+    strip_or_none,
 )
 
 
@@ -23,7 +25,8 @@ class TVAIE(InfoExtractor):
         'params': {
             # m3u8 download
             'skip_download': True,
-        }
+        },
+        'skip': 'HTTP Error 404: Not Found',
     }, {
         'url': 'https://video.tva.ca/details/_5596811470001',
         'only_matching': True,
@@ -32,26 +35,54 @@ class TVAIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        video_data = self._download_json(
-            'https://videos.tva.ca/proxy/item/_' + video_id, video_id, headers={
-                'Accept': 'application/json',
-            }, query={
-                'appId': '5955fc5f23eec60006c951f1',
-            })
-
-        def get_attribute(key):
-            for attribute in video_data.get('attributes', []):
-                if attribute.get('key') == key:
-                    return attribute.get('value')
-            return None
 
         return {
             '_type': 'url_transparent',
             'id': video_id,
-            'title': get_attribute('title'),
             'url': smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % video_id, {'geo_countries': ['CA']}),
-            'description': get_attribute('description'),
-            'thumbnail': get_attribute('image-background') or get_attribute('image-landscape'),
-            'duration': float_or_none(get_attribute('video-duration'), 1000),
             'ie_key': 'BrightcoveNew',
         }
+
+
+class QubIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?qub\.ca/(?:[^/]+/)*[0-9a-z-]+-(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.qub.ca/tvaplus/tva/alerte-amber/saison-1/episode-01-1000036619',
+        'md5': '949490fd0e7aee11d0543777611fbd53',
+        'info_dict': {
+            'id': '6084352463001',
+            'ext': 'mp4',
+            'title': 'Épisode 01',
+            'uploader_id': '5481942443001',
+            'upload_date': '20190907',
+            'timestamp': 1567899756,
+            'description': 'md5:9c0d7fbb90939420c651fd977df90145',
+        },
+    }, {
+        'url': 'https://www.qub.ca/tele/video/lcn-ca-vous-regarde-rev-30s-ap369664-1009357943',
+        'only_matching': True,
+    }]
+    # reference_id also works with old account_id(5481942443001)
+    # BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5813221784001/default_default/index.html?videoId=ref:%s'
+
+    def _real_extract(self, url):
+        entity_id = self._match_id(url)
+        entity = self._download_json(
+            'https://www.qub.ca/proxy/pfu/content-delivery-service/v1/entities',
+            entity_id, query={'id': entity_id})
+        video_id = entity['videoId']
+        episode = strip_or_none(entity.get('name'))
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'title': episode,
+            # 'url': self.BRIGHTCOVE_URL_TEMPLATE % entity['referenceId'],
+            'url': 'https://videos.tva.ca/details/_' + video_id,
+            'description': entity.get('longDescription'),
+            'duration': float_or_none(entity.get('durationMillis'), 1000),
+            'episode': episode,
+            'episode_number': int_or_none(entity.get('episodeNumber')),
+            # 'ie_key': 'BrightcoveNew',
+            'ie_key': TVAIE.ie_key(),
+        }