Merge branch 'srgssr' of https://github.com/remitamine/youtube-dl into remitamine...

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

diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py
index 33b296eafc0776d50edbc964170b1026b223bb71..923273fb2f1cc5b775f1c130235d21f683ffeb64 100644 (file)
--- a/youtube_dl/extractor/bbc.py
+++ b/youtube_dl/extractor/bbc.py
@@ -22,7 +22,8 @@ from ..compat import (
 class BBCCoUkIE(InfoExtractor):
     IE_NAME = 'bbc.co.uk'
     IE_DESC = 'BBC iPlayer'
-    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>[\da-z]{8})'
+    _ID_REGEX = r'[pb][\da-z]{7}'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>%s)' % _ID_REGEX
 
     _MEDIASELECTOR_URLS = [
         # Provides HQ HLS streams with even better quality that pc mediaset but fails
@@ -46,9 +47,8 @@ class BBCCoUkIE(InfoExtractor):
             'info_dict': {
                 'id': 'b039d07m',
                 'ext': 'flv',
-                'title': 'Kaleidoscope, Leonard Cohen',
+                'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4',
                 'description': 'The Canadian poet and songwriter reflects on his musical career.',
-                'duration': 1740,
             },
             'params': {
                 # rtmp download
@@ -111,7 +111,8 @@ class BBCCoUkIE(InfoExtractor):
             'params': {
                 # rtmp download
                 'skip_download': True,
-            }
+            },
+            'skip': 'Episode is no longer available on BBC iPlayer Radio',
         }, {
             'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
             'note': 'Audio',
@@ -222,11 +223,9 @@ class BBCCoUkIE(InfoExtractor):
             elif transfer_format == 'dash':
                 pass
             elif transfer_format == 'hls':
-                m3u8_formats = self._extract_m3u8_formats(
+                formats.extend(self._extract_m3u8_formats(
                     href, programme_id, ext='mp4', entry_protocol='m3u8_native',
-                    m3u8_id=supplier, fatal=False)
-                if m3u8_formats:
-                    formats.extend(m3u8_formats)
+                    m3u8_id=supplier, fatal=False))
             # Direct link
             else:
                 formats.append({
@@ -453,6 +452,7 @@ class BBCCoUkIE(InfoExtractor):
         webpage = self._download_webpage(url, group_id, 'Downloading video page')
 
         programme_id = None
+        duration = None
 
         tviplayer = self._search_regex(
             r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById',
@@ -465,14 +465,16 @@ class BBCCoUkIE(InfoExtractor):
 
         if not programme_id:
             programme_id = self._search_regex(
-                r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
+                r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None)
 
         if programme_id:
             formats, subtitles = self._download_media_selector(programme_id)
             title = self._og_search_title(webpage)
             description = self._search_regex(
                 r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
-                webpage, 'description', fatal=False)
+                webpage, 'description', default=None)
+            if not description:
+                description = self._html_search_meta('description', webpage)
         else:
             programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
 
@@ -586,6 +588,7 @@ class BBCIE(BBCCoUkIE):
             'ext': 'mp4',
             'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
             'duration': 56,
+            'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
         },
         'params': {
             'skip_download': True,
@@ -728,6 +731,7 @@ class BBCIE(BBCCoUkIE):
         # article with multiple videos embedded with playlist.sxml (e.g.
         # http://www.bbc.com/sport/0/football/34475836)
         playlists = re.findall(r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage)
+        playlists.extend(re.findall(r'data-media-id="([^"]+/playlist\.sxml)"', webpage))
         if playlists:
             entries = [
                 self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp)
@@ -780,8 +784,9 @@ class BBCIE(BBCCoUkIE):
 
         # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
         programme_id = self._search_regex(
-            [r'data-video-player-vpid="([\da-z]{8})"',
-             r'<param[^>]+name="externalIdentifier"[^>]+value="([\da-z]{8})"'],
+            [r'data-video-player-vpid="(%s)"' % self._ID_REGEX,
+             r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX,
+             r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
             webpage, 'vpid', default=None)
 
         if programme_id:
@@ -816,7 +821,7 @@ class BBCIE(BBCCoUkIE):
 
         # Multiple video article (e.g.
         # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
-        EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?'
+        EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX
         entries = []
         for match in extract_all(r'new\s+SMP\(({.+?})\)'):
             embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')