[youtube] fix extraction for embed restricted live streams(fixes #16433)

[youtube-dl] / youtube_dl / extractor / francetv.py

diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py
index e0734d59ac3189ada79eaf98d1461d8c07c47ecb..c02cd03de1c59452ac1ff2432f9e5ea54134e7de 100644 (file)
--- a/youtube_dl/extractor/francetv.py
+++ b/youtube_dl/extractor/francetv.py
@@ -11,21 +11,23 @@ from ..compat import (
 )
 from ..utils import (
     clean_html,
+    determine_ext,
     ExtractorError,
     int_or_none,
     parse_duration,
-    determine_ext,
+    try_get,
 )
 from .dailymotion import DailymotionIE
 
 
 class FranceTVBaseInfoExtractor(InfoExtractor):
-    def _make_url_result(self, video_id, catalog=None):
-        full_id = 'francetv:%s' % video_id
-        if catalog:
+    def _make_url_result(self, video_or_full_id, catalog=None):
+        full_id = 'francetv:%s' % video_or_full_id
+        if '@' not in video_or_full_id and catalog:
             full_id += '@%s' % catalog
         return self.url_result(
-            full_id, ie=FranceTVIE.ie_key(), video_id=video_id)
+            full_id, ie=FranceTVIE.ie_key(),
+            video_id=video_or_full_id.split('@')[0])
 
 
 class FranceTVIE(InfoExtractor):
@@ -76,6 +78,10 @@ class FranceTVIE(InfoExtractor):
     }, {
         'url': 'francetv:NI_657393@Regions',
         'only_matching': True,
+    }, {
+        # france-3 live
+        'url': 'francetv:SIM_France3',
+        'only_matching': True,
     }]
 
     def _extract_video(self, video_id, catalogue=None):
@@ -120,6 +126,8 @@ class FranceTVIE(InfoExtractor):
                     return signed_url
             return manifest_url
 
+        is_live = None
+
         formats = []
         for video in info['videos']:
             if video['statut'] != 'ONLINE':
@@ -127,6 +135,10 @@ class FranceTVIE(InfoExtractor):
             video_url = video['url']
             if not video_url:
                 continue
+            if is_live is None:
+                is_live = (try_get(
+                    video, lambda x: x['plages_ouverture'][0]['direct'],
+                    bool) is True) or '/live.francetv.fr/' in video_url
             format_id = video['format']
             ext = determine_ext(video_url)
             if ext == 'f4m':
@@ -172,11 +184,12 @@ class FranceTVIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'title': title,
+            'title': self._live_title(title) if is_live else title,
             'description': clean_html(info['synopsis']),
             'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
             'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
             'timestamp': int_or_none(info['diffusion']['timestamp']),
+            'is_live': is_live,
             'formats': formats,
             'subtitles': subtitles,
         }
@@ -245,6 +258,10 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
     }, {
         'url': 'https://www.france.tv/142749-rouge-sang.html',
         'only_matching': True,
+    }, {
+        # france-3 live
+        'url': 'https://www.france.tv/france-3/direct.html',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -431,3 +448,43 @@ class CultureboxIE(FranceTVBaseInfoExtractor):
             webpage, 'video id').split('@')
 
         return self._make_url_result(video_id, catalogue)
+
+
+class FranceTVJeunesseIE(FranceTVBaseInfoExtractor):
+    _VALID_URL = r'(?P<url>https?://(?:www\.)?(?:zouzous|ludo)\.fr/heros/(?P<id>[^/?#&]+))'
+
+    _TESTS = [{
+        'url': 'https://www.zouzous.fr/heros/simon',
+        'info_dict': {
+            'id': 'simon',
+        },
+        'playlist_count': 9,
+    }, {
+        'url': 'https://www.ludo.fr/heros/ninjago',
+        'info_dict': {
+            'id': 'ninjago',
+        },
+        'playlist_count': 10,
+    }, {
+        'url': 'https://www.zouzous.fr/heros/simon?abc',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('id')
+
+        playlist = self._download_json(
+            '%s/%s' % (mobj.group('url'), 'playlist'), playlist_id)
+
+        if not playlist.get('count'):
+            raise ExtractorError(
+                '%s is not available' % playlist_id, expected=True)
+
+        entries = []
+        for item in playlist['items']:
+            identity = item.get('identity')
+            if identity and isinstance(identity, compat_str):
+                entries.append(self._make_url_result(identity))
+
+        return self.playlist_result(entries, playlist_id)