]> Raphaël G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/tvplay.py
Update upstream source from tag 'upstream/2020.06.16.1'
[youtubedl] / youtube_dl / extractor / tvplay.py
index 4186e82db170300c6addeb0d0054c75b3d512e48..3c2450dd0c8733d3a96a1a842c54505294b70ca6 100644 (file)
@@ -6,7 +6,6 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,
-    compat_str,
     compat_urlparse,
 )
 from ..utils import (
@@ -17,6 +16,7 @@ from ..utils import (
     qualities,
     try_get,
     update_url_query,
+    url_or_none,
 )
 
 
@@ -29,12 +29,12 @@ class TVPlayIE(InfoExtractor):
                         https?://
                             (?:www\.)?
                             (?:
-                                tvplay(?:\.skaties)?\.lv/parraides|
-                                (?:tv3play|play\.tv3)\.lt/programos|
+                                tvplay(?:\.skaties)?\.lv(?:/parraides)?|
+                                (?:tv3play|play\.tv3)\.lt(?:/programos)?|
                                 tv3play(?:\.tv3)?\.ee/sisu|
                                 (?:tv(?:3|6|8|10)play|viafree)\.se/program|
                                 (?:(?:tv3play|viasat4play|tv6play|viafree)\.no|(?:tv3play|viafree)\.dk)/programmer|
-                                play\.novatv\.bg/programi
+                                play\.nova(?:tv)?\.bg/programi
                             )
                             /(?:[^/]+/)+
                         )
@@ -200,10 +200,18 @@ class TVPlayIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            'url': 'https://play.nova.bg/programi/zdravei-bulgariya/764300?autostart=true',
+            'only_matching': True,
+        },
         {
             'url': 'http://tvplay.skaties.lv/parraides/vinas-melo-labak/418113?autostart=true',
             'only_matching': True,
         },
+        {
+            'url': 'https://tvplay.skaties.lv/vinas-melo-labak/418113/?autostart=true',
+            'only_matching': True,
+        },
         {
             # views is null
             'url': 'http://tvplay.skaties.lv/parraides/tv3-zinas/760183',
@@ -225,7 +233,11 @@ class TVPlayIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
+        geo_country = self._search_regex(
+            r'https?://[^/]+\.([a-z]{2})', url,
+            'geo country', default=None)
+        if geo_country:
+            self._initialize_geo_bypass({'countries': [geo_country.upper()]})
         video = self._download_json(
             'http://playapi.mtgx.tv/v3/videos/%s' % video_id, video_id, 'Downloading video JSON')
 
@@ -244,7 +256,8 @@ class TVPlayIE(InfoExtractor):
         quality = qualities(['hls', 'medium', 'high'])
         formats = []
         for format_id, video_url in streams.get('streams', {}).items():
-            if not video_url or not isinstance(video_url, compat_str):
+            video_url = url_or_none(video_url)
+            if not video_url:
                 continue
             ext = determine_ext(video_url)
             if ext == 'f4m':
@@ -273,6 +286,7 @@ class TVPlayIE(InfoExtractor):
                         'url': m.group('url'),
                         'app': m.group('app'),
                         'play_path': m.group('playpath'),
+                        'preference': -1,
                     })
                 else:
                     fmt.update({
@@ -323,50 +337,176 @@ class ViafreeIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:www\.)?
-                        viafree\.
-                        (?:
-                            (?:dk|no)/programmer|
-                            se/program
-                        )
-                        /(?:[^/]+/)+(?P<id>[^/?#&]+)
+                        viafree\.(?P<country>dk|no|se)
+                        /(?P<id>program(?:mer)?/(?:[^/]+/)+[^/?#&]+)
                     '''
     _TESTS = [{
-        'url': 'http://www.viafree.se/program/livsstil/husraddarna/sasong-2/avsnitt-2',
+        'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1',
         'info_dict': {
-            'id': '395375',
+            'id': '757786',
             'ext': 'mp4',
-            'title': 'Husräddarna S02E02',
-            'description': 'md5:4db5c933e37db629b5a2f75dfb34829e',
-            'series': 'Husräddarna',
-            'season': 'Säsong 2',
+            'title': 'Det beste vorspielet - Sesong 2 - Episode 1',
+            'description': 'md5:b632cb848331404ccacd8cd03e83b4c3',
+            'series': 'Det beste vorspielet',
             'season_number': 2,
-            'duration': 2576,
-            'timestamp': 1400596321,
-            'upload_date': '20140520',
+            'duration': 1116,
+            'timestamp': 1471200600,
+            'upload_date': '20160814',
         },
         'params': {
             'skip_download': True,
         },
-        'add_ie': [TVPlayIE.ie_key()],
     }, {
-        'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1',
+        # with relatedClips
+        'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-1',
+        'only_matching': True,
+    }, {
+        # Different og:image URL schema
+        'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-2',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.viafree.se/program/livsstil/husraddarna/sasong-2/avsnitt-2',
         'only_matching': True,
     }, {
         'url': 'http://www.viafree.dk/programmer/reality/paradise-hotel/saeson-7/episode-5',
         'only_matching': True,
     }]
+    _GEO_BYPASS = False
 
     @classmethod
     def suitable(cls, url):
         return False if TVPlayIE.suitable(url) else super(ViafreeIE, cls).suitable(url)
 
+    def _real_extract(self, url):
+        country, path = re.match(self._VALID_URL, url).groups()
+        content = self._download_json(
+            'https://viafree-content.mtg-api.com/viafree-content/v1/%s/path/%s' % (country, path), path)
+        program = content['_embedded']['viafreeBlocks'][0]['_embedded']['program']
+        guid = program['guid']
+        meta = content['meta']
+        title = meta['title']
+
+        try:
+            stream_href = self._download_json(
+                program['_links']['streamLink']['href'], guid,
+                headers=self.geo_verification_headers())['embedded']['prioritizedStreams'][0]['links']['stream']['href']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+                self.raise_geo_restricted(countries=[country])
+            raise
+
+        formats = self._extract_m3u8_formats(stream_href, guid, 'mp4')
+        self._sort_formats(formats)
+        episode = program.get('episode') or {}
+
+        return {
+            'id': guid,
+            'title': title,
+            'thumbnail': meta.get('image'),
+            'description': meta.get('description'),
+            'series': episode.get('seriesTitle'),
+            'episode_number': int_or_none(episode.get('episodeNumber')),
+            'season_number': int_or_none(episode.get('seasonNumber')),
+            'duration': int_or_none(try_get(program, lambda x: x['video']['duration']['milliseconds']), 1000),
+            'timestamp': parse_iso8601(try_get(program, lambda x: x['availability']['start'])),
+            'formats': formats,
+        }
+
+
+class TVPlayHomeIE(InfoExtractor):
+    _VALID_URL = r'https?://tvplay\.(?:tv3\.lt|skaties\.lv|tv3\.ee)/[^/]+/[^/?#&]+-(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://tvplay.tv3.lt/aferistai-n-7/aferistai-10047125/',
+        'info_dict': {
+            'id': '366367',
+            'ext': 'mp4',
+            'title': 'Aferistai',
+            'description': 'Aferistai. Kalėdinė pasaka.',
+            'series': 'Aferistai [N-7]',
+            'season': '1 sezonas',
+            'season_number': 1,
+            'duration': 464,
+            'timestamp': 1394209658,
+            'upload_date': '20140307',
+            'age_limit': 18,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': [TVPlayIE.ie_key()],
+    }, {
+        'url': 'https://tvplay.skaties.lv/vinas-melo-labak/vinas-melo-labak-10280317/',
+        'only_matching': True,
+    }, {
+        'url': 'https://tvplay.tv3.ee/cool-d-ga-mehhikosse/cool-d-ga-mehhikosse-10044354/',
+        'only_matching': True,
+    }]
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
 
         video_id = self._search_regex(
-            r'currentVideo["\']\s*:\s*.+?["\']id["\']\s*:\s*["\'](?P<id>\d{6,})',
-            webpage, 'video id')
+            r'data-asset-id\s*=\s*["\'](\d{5,})\b', webpage, 'video id')
+
+        if len(video_id) < 8:
+            return self.url_result(
+                'mtg:%s' % video_id, ie=TVPlayIE.ie_key(), video_id=video_id)
+
+        m3u8_url = self._search_regex(
+            r'data-file\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+            'm3u8 url', group='url')
 
-        return self.url_result('mtg:%s' % video_id, TVPlayIE.ie_key())
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
+            m3u8_id='hls')
+        self._sort_formats(formats)
+
+        title = self._search_regex(
+            r'data-title\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
+            'title', default=None, group='value') or self._html_search_meta(
+            'title', webpage, default=None) or self._og_search_title(
+            webpage)
+
+        description = self._html_search_meta(
+            'description', webpage,
+            default=None) or self._og_search_description(webpage)
+
+        thumbnail = self._search_regex(
+            r'data-image\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+            'thumbnail', default=None, group='url') or self._html_search_meta(
+            'thumbnail', webpage, default=None) or self._og_search_thumbnail(
+            webpage)
+
+        duration = int_or_none(self._search_regex(
+            r'data-duration\s*=\s*["\'](\d+)', webpage, 'duration',
+            fatal=False))
+
+        season = self._search_regex(
+            (r'data-series-title\s*=\s*(["\'])[^/]+/(?P<value>(?:(?!\1).)+)\1',
+             r'\bseason\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
+            'season', default=None, group='value')
+        season_number = int_or_none(self._search_regex(
+            r'(\d+)(?:[.\s]+sezona|\s+HOOAEG)', season or '', 'season number',
+            default=None))
+        episode = self._search_regex(
+            (r'\bepisode\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+             r'data-subtitle\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
+            'episode', default=None, group='value')
+        episode_number = int_or_none(self._search_regex(
+            r'(?:S[eē]rija|Osa)\s+(\d+)', episode or '', 'episode number',
+            default=None))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'season': season,
+            'season_number': season_number,
+            'episode': episode,
+            'episode_number': episode_number,
+            'formats': formats,
+        }