[tv4] relax _VALID_URL(closes #27964)

closes #17091
closes #27841

youtube_dl/extractor/adn.py

@@ -26,6 +26,7 @@ from ..utils import (
     strip_or_none,
     try_get,
     unified_strdate,
+    urlencode_postdata,
 )
 
 
@@ -51,9 +52,12 @@ class ADNIE(InfoExtractor):
         }
     }
 
+    _NETRC_MACHINE = 'animedigitalnetwork'
     _BASE_URL = 'http://animedigitalnetwork.fr'
     _API_BASE_URL = 'https://gw.api.animedigitalnetwork.fr/'
     _PLAYER_BASE_URL = _API_BASE_URL + 'player/'
+    _HEADERS = {}
+    _LOGIN_ERR_MESSAGE = 'Unable to log in'
     _RSA_KEY = (0x9B42B08905199A5CCE2026274399CA560ECB209EE9878A708B1C0812E1BB8CB5D1FB7441861147C1A1F2F3A0476DD63A9CAC20D3E983613346850AA6CB38F16DC7D720FD7D86FC6E5B3D5BBC72E14CD0BF9E869F2CEA2CCAD648F1DCE38F1FF916CEFB2D339B64AA0264372344BC775E265E8A852F88144AB0BD9AA06C1A4ABB, 65537)
     _POS_ALIGN_MAP = {
         'start': 1,
@@ -129,19 +133,42 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
             }])
         return subtitles
 
+    def _real_initialize(self):
+        username, password = self._get_login_info()
+        if not username:
+            return
+        try:
+            access_token = (self._download_json(
+                self._API_BASE_URL + 'authentication/login', None,
+                'Logging in', self._LOGIN_ERR_MESSAGE, fatal=False,
+                data=urlencode_postdata({
+                    'password': password,
+                    'rememberMe': False,
+                    'source': 'Web',
+                    'username': username,
+                })) or {}).get('accessToken')
+            if access_token:
+                self._HEADERS = {'authorization': 'Bearer ' + access_token}
+        except ExtractorError as e:
+            message = None
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+                resp = self._parse_json(
+                    e.cause.read().decode(), None, fatal=False) or {}
+                message = resp.get('message') or resp.get('code')
+            self.report_warning(message or self._LOGIN_ERR_MESSAGE)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         video_base_url = self._PLAYER_BASE_URL + 'video/%s/' % video_id
         player = self._download_json(
             video_base_url + 'configuration', video_id,
-            'Downloading player config JSON metadata')['player']
+            'Downloading player config JSON metadata',
+            headers=self._HEADERS)['player']
         options = player['options']
 
         user = options['user']
         if not user.get('hasAccess'):
-            raise ExtractorError(
+            self.raise_login_required()
-                'This video is only available for paying users', expected=True)
-            # self.raise_login_required() # FIXME: Login is not implemented
 
         token = self._download_json(
             user.get('refreshTokenUrl') or (self._PLAYER_BASE_URL + 'refresh/token'),
@@ -188,8 +215,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
                 message = error.get('message')
                 if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country':
                     self.raise_geo_restricted(msg=message)
-                else:
+                raise ExtractorError(message)
-                    raise ExtractorError(message)
         else:
             raise ExtractorError('Giving up retrying')
 

youtube_dl/extractor/extractors.py

@@ -1260,6 +1260,7 @@ from .tv2 import (
     TV2IE,
     TV2ArticleIE,
     KatsomoIE,
+    MTVUutisetArticleIE,
 )
 from .tv2dk import (
     TV2DKIE,

youtube_dl/extractor/tv2.py

@@ -20,7 +20,7 @@ from ..utils import (
 
 class TV2IE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?tv2\.no/v/(?P<id>\d+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.tv2.no/v/916509/',
         'info_dict': {
             'id': '916509',
@@ -33,7 +33,7 @@ class TV2IE(InfoExtractor):
             'view_count': int,
             'categories': list,
         },
-    }
+    }]
     _API_DOMAIN = 'sumo.tv2.no'
     _PROTOCOLS = ('HDS', 'HLS', 'DASH')
     _GEO_COUNTRIES = ['NO']
@@ -42,6 +42,12 @@ class TV2IE(InfoExtractor):
         video_id = self._match_id(url)
         api_base = 'http://%s/api/web/asset/%s' % (self._API_DOMAIN, video_id)
 
+        asset = self._download_json(
+            api_base + '.json', video_id,
+            'Downloading metadata JSON')['asset']
+        title = asset.get('subtitle') or asset['title']
+        is_live = asset.get('live') is True
+
         formats = []
         format_urls = []
         for protocol in self._PROTOCOLS:
@@ -81,7 +87,8 @@ class TV2IE(InfoExtractor):
                 elif ext == 'm3u8':
                     if not data.get('drmProtected'):
                         formats.extend(self._extract_m3u8_formats(
-                            video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                            video_url, video_id, 'mp4',
+                            'm3u8' if is_live else 'm3u8_native',
                             m3u8_id=format_id, fatal=False))
                 elif ext == 'mpd':
                     formats.extend(self._extract_mpd_formats(
@@ -99,11 +106,6 @@ class TV2IE(InfoExtractor):
             raise ExtractorError('This video is DRM protected.', expected=True)
         self._sort_formats(formats)
 
-        asset = self._download_json(
-            api_base + '.json', video_id,
-            'Downloading metadata JSON')['asset']
-        title = asset['title']
-
         thumbnails = [{
             'id': thumbnail.get('@type'),
             'url': thumbnail.get('url'),
@@ -112,7 +114,7 @@ class TV2IE(InfoExtractor):
         return {
             'id': video_id,
             'url': video_url,
-            'title': title,
+            'title': self._live_title(title) if is_live else title,
             'description': strip_or_none(asset.get('description')),
             'thumbnails': thumbnails,
             'timestamp': parse_iso8601(asset.get('createTime')),
@@ -120,6 +122,7 @@ class TV2IE(InfoExtractor):
             'view_count': int_or_none(asset.get('views')),
             'categories': asset.get('keywords', '').split(','),
             'formats': formats,
+            'is_live': is_live,
         }
 
 
@@ -168,13 +171,13 @@ class TV2ArticleIE(InfoExtractor):
 
 
 class KatsomoIE(TV2IE):
-    _VALID_URL = r'https?://(?:www\.)?(?:katsomo|mtv)\.fi/(?:#!/)?(?:[^/]+/[0-9a-z-]+-\d+/[0-9a-z-]+-|[^/]+/\d+/[^/]+/)(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:katsomo|mtv(uutiset)?)\.fi/(?:sarja/[0-9a-z-]+-\d+/[0-9a-z-]+-|(?:#!/)?jakso/(?:\d+/[^/]+/)?|video/prog)(?P<id>\d+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://www.mtv.fi/sarja/mtv-uutiset-live-33001002003/lahden-pelicans-teki-kovan-ratkaisun-ville-nieminen-pihalle-1181321',
         'info_dict': {
             'id': '1181321',
             'ext': 'mp4',
-            'title': 'MTV Uutiset Live',
+            'title': 'Lahden Pelicans teki kovan ratkaisun – Ville Nieminen pihalle',
             'description': 'Päätöksen teki Pelicansin hallitus.',
             'timestamp': 1575116484,
             'upload_date': '20191130',
@@ -186,7 +189,60 @@ class KatsomoIE(TV2IE):
             # m3u8 download
             'skip_download': True,
         },
-    }
+    }, {
+        'url': 'http://www.katsomo.fi/#!/jakso/33001005/studio55-fi/658521/jukka-kuoppamaki-tekee-yha-lauluja-vaikka-lentokoneessa',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.mtvuutiset.fi/video/prog1311159',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.katsomo.fi/#!/jakso/1311159',
+        'only_matching': True,
+    }]
     _API_DOMAIN = 'api.katsomo.fi'
     _PROTOCOLS = ('HLS', 'MPD')
     _GEO_COUNTRIES = ['FI']
+
+
+class MTVUutisetArticleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)mtvuutiset\.fi/artikkeli/[^/]+/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.mtvuutiset.fi/artikkeli/tallaisia-vaurioita-viking-amorellassa-on-useamman-osaston-alla-vetta/7931384',
+        'info_dict': {
+            'id': '1311159',
+            'ext': 'mp4',
+            'title': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla',
+            'description': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla',
+            'timestamp': 1600608966,
+            'upload_date': '20200920',
+            'duration': 153.7886666,
+            'view_count': int,
+            'categories': list,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # multiple Youtube embeds
+        'url': 'https://www.mtvuutiset.fi/artikkeli/50-vuotta-subarun-vastaiskua/6070962',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        article_id = self._match_id(url)
+        article = self._download_json(
+            'http://api.mtvuutiset.fi/mtvuutiset/api/json/' + article_id,
+            article_id)
+
+        def entries():
+            for video in (article.get('videos') or []):
+                video_type = video.get('videotype')
+                video_url = video.get('url')
+                if not (video_url and video_type in ('katsomo', 'youtube')):
+                    continue
+                yield self.url_result(
+                    video_url, video_type.capitalize(), video.get('video_id'))
+
+        return self.playlist_result(
+            entries(), article_id, article.get('title'), article.get('description'))

youtube_dl/extractor/tv4.py

@@ -17,7 +17,7 @@ class TV4IE(InfoExtractor):
             tv4\.se/(?:[^/]+)/klipp/(?:.*)-|
             tv4play\.se/
             (?:
-                (?:program|barn)/(?:[^/]+/|(?:[^\?]+)\?video_id=)|
+                (?:program|barn)/(?:(?:[^/]+/){1,2}|(?:[^\?]+)\?video_id=)|
                 iframe/video/|
                 film/|
                 sport/|
@@ -65,6 +65,10 @@ class TV4IE(InfoExtractor):
         {
             'url': 'http://www.tv4play.se/program/farang/3922081',
             'only_matching': True,
+        },
+        {
+            'url': 'https://www.tv4play.se/program/nyheterna/avsnitt/13315940',
+            'only_matching': True,
         }
     ]
 

youtube_dl/extractor/zype.py

@@ -87,11 +87,16 @@ class ZypeIE(InfoExtractor):
                 r'(["\'])(?P<url>(?:(?!\1).)+\.m3u8(?:(?!\1).)*)\1',
                 body, 'm3u8 url', group='url', default=None)
             if not m3u8_url:
-                source = self._parse_json(self._search_regex(
+                source = self._search_regex(
-                    r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', body,
+                    r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', body, 'source')
-                    'source'), video_id, js_to_json)
+
-                if source.get('integration') == 'verizon-media':
+                def get_attr(key):
-                    m3u8_url = 'https://content.uplynk.com/%s.m3u8' % source['id']
+                    return self._search_regex(
+                        r'\b%s\s*:\s*([\'"])(?P<val>(?:(?!\1).)+)\1' % key,
+                        source, key, group='val')
+
+                if get_attr('integration') == 'verizon-media':
+                    m3u8_url = 'https://content.uplynk.com/%s.m3u8' % get_attr('id')
             formats = self._extract_m3u8_formats(
                 m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
             text_tracks = self._search_regex(