Merge pull request #6963 from remitamine/appledaily

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

diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py
index 9a1b6e3dce7dd3247b0076b36280e7e4e0550c90..cc2f6fed2ccd6ec4b0747fb2f45df4fbf3841e77 100644 (file)
--- a/youtube_dl/extractor/bbc.py
+++ b/youtube_dl/extractor/bbc.py
@@ -21,6 +21,10 @@ class BBCCoUkIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
 
     _MEDIASELECTOR_URLS = [
+        # Provides HQ HLS streams with even better quality that pc mediaset but fails
+        # with geolocation in some cases when it's even not geo restricted at all (e.g.
+        # http://www.bbc.co.uk/programmes/b06bp7lf)
+        'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
         'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s',
     ]
 
@@ -152,6 +156,21 @@ class BBCCoUkIE(InfoExtractor):
                 'skip_download': True,
             },
             'skip': 'geolocation',
+        }, {
+            # iptv-all mediaset fails with geolocation however there is no geo restriction
+            # for this programme at all
+            'url': 'http://www.bbc.co.uk/programmes/b06bp7lf',
+            'info_dict': {
+                'id': 'b06bp7kf',
+                'ext': 'flv',
+                'title': "Annie Mac's Friday Night, B.Traits sits in for Annie",
+                'description': 'B.Traits sits in for Annie Mac with a Mini-Mix from Disclosure.',
+                'duration': 10800,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
         }, {
             'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
             'only_matching': True,
@@ -189,6 +208,12 @@ class BBCCoUkIE(InfoExtractor):
             # Skip DASH until supported
             elif transfer_format == 'dash':
                 pass
+            elif transfer_format == 'hls':
+                m3u8_formats = 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)
             # Direct link
             else:
                 formats.append({
@@ -287,7 +312,7 @@ class BBCCoUkIE(InfoExtractor):
                 return self._download_media_selector_url(
                     mediaselector_url % programme_id, programme_id)
             except BBCCoUkIE.MediaSelectionError as e:
-                if e.id == 'notukerror':
+                if e.id in ('notukerror', 'geolocation'):
                     last_exception = e
                     continue
                 self._raise_extractor_error(e)
@@ -526,6 +551,18 @@ class BBCIE(BBCCoUkIE):
         'params': {
             'skip_download': True,
         }
+    }, {
+        # single video from video playlist embedded with vxp-playlist-data JSON
+        'url': 'http://www.bbc.com/news/video_and_audio/must_see/33376376',
+        'info_dict': {
+            'id': 'p02w6qjc',
+            'ext': 'mp4',
+            'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
+            'duration': 56,
+        },
+        'params': {
+            'skip_download': True,
+        }
     }, {
         # single video story with digitalData
         'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret',
@@ -695,13 +732,36 @@ class BBCIE(BBCCoUkIE):
 
         if not medias:
             # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international)
-            media_asset_page = self._parse_json(
+            media_asset = self._search_regex(
+                r'mediaAssetPage\.init\(\s*({.+?}), "/',
+                webpage, 'media asset', default=None)
+            if media_asset:
+                media_asset_page = self._parse_json(media_asset, playlist_id, fatal=False)
+                medias = []
+                for video in media_asset_page.get('videos', {}).values():
+                    medias.extend(video.values())
+
+        if not medias:
+            # Multiple video playlist with single `now playing` entry (e.g.
+            # http://www.bbc.com/news/video_and_audio/must_see/33767813)
+            vxp_playlist = self._parse_json(
                 self._search_regex(
-                    r'mediaAssetPage\.init\(\s*({.+?}), "/', webpage, 'media asset'),
+                    r'<script[^>]+class="vxp-playlist-data"[^>]+type="application/json"[^>]*>([^<]+)</script>',
+                    webpage, 'playlist data'),
                 playlist_id)
-            medias = []
-            for video in media_asset_page.get('videos', {}).values():
-                medias.extend(video.values())
+            playlist_medias = []
+            for item in vxp_playlist:
+                media = item.get('media')
+                if not media:
+                    continue
+                playlist_medias.append(media)
+                # Download single video if found media with asset id matching the video id from URL
+                if item.get('advert', {}).get('assetId') == playlist_id:
+                    medias = [media]
+                    break
+            # Fallback to the whole playlist
+            if not medias:
+                medias = playlist_medias
 
         entries = []
         for num, media_meta in enumerate(medias, start=1):