diff options
| -rw-r--r-- | docs/supportedsites.md | 3 | ||||
| -rw-r--r-- | youtube_dl/extractor/bbc.py | 34 | ||||
| -rw-r--r-- | youtube_dl/extractor/generic.py | 8 | ||||
| -rw-r--r-- | youtube_dl/version.py | 2 |
4 files changed, 34 insertions, 13 deletions
diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 73445137f..657935dc6 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -51,6 +51,7 @@ - **bambuser:channel** - **Bandcamp** - **Bandcamp:album** + - **bbc**: BBC - **bbc.co.uk**: BBC iPlayer - **BeatportPro** - **Beeg** @@ -224,6 +225,7 @@ - **InternetVideoArchive** - **IPrima** - **iqiyi**: 爱奇艺 + - **Ir90Tv** - **ivi**: ivi.ru - **ivi:compilation**: ivi.ru compilations - **Izlesene** @@ -252,6 +254,7 @@ - **kuwo:song**: 酷我音乐 - **la7.tv** - **Laola1Tv** + - **Lecture2Go** - **Letv**: 乐视网 - **LetvPlaylist** - **LetvTv** diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 66e52641b..01d07c9c0 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -451,6 +451,14 @@ class BBCIE(BBCCoUkIE): 'playlist_count': 9, 'skip': 'Save time', }, { + # article with multiple videos embedded with `new SMP()` + 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460', + 'info_dict': { + 'id': '3662a707-0af9-3149-963f-47bea720b460', + 'title': 'BBC Blogs - Adam Curtis - BUGGER', + }, + 'playlist_count': 18, + }, { # single video embedded with mediaAssetPage.init() 'url': 'http://www.bbc.com/news/world-europe-32041533', 'info_dict': { @@ -637,12 +645,30 @@ class BBCIE(BBCCoUkIE): playlist_title = self._html_search_regex( r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title') - playlist_description = self._og_search_description(webpage) + playlist_description = self._og_search_description(webpage, default=None) + + def extract_all(pattern): + return list(filter(None, map( + lambda s: self._parse_json(s, playlist_id, fatal=False), + re.findall(pattern, webpage)))) + + # 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[^"]+)?' + entries = [] + for match in extract_all(r'new\s+SMP\(({.+?})\)'): + embed_url = match.get('playerSettings', {}).get('externalEmbedUrl') + if embed_url and re.match(EMBED_URL, embed_url): + entries.append(embed_url) + entries.extend(re.findall( + r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage)) + if entries: + return self.playlist_result( + [self.url_result(entry, 'BBCCoUk') for entry in entries], + playlist_id, playlist_title, playlist_description) # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511) - medias = list(filter(None, map( - lambda s: self._parse_json(s, playlist_id, fatal=False), - re.findall(r"data-media-meta='({[^']+})'", webpage)))) + medias = extract_all(r"data-media-meta='({[^']+})'") if not medias: # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 6d2efb22e..8cef61c3c 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -276,14 +276,6 @@ class GenericIE(InfoExtractor): 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.', }, }, - # BBC iPlayer embeds - { - 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER', - 'info_dict': { - 'title': 'BBC - Blogs - Adam Curtis - BUGGER', - }, - 'playlist_mincount': 18, - }, # RUTV embed { 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html', diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 280afdd7f..fa157cadb 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2015.07.21' +__version__ = '2015.07.28' |