X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fbbc.py;h=c0433eabd5af2130c0e13d83370784f3cab4b036;hb=88ed52aec9f2e622188f304d74f2f5568b0caa1e;hp=66e52641bb8a672c97184fa046f7ef9a0c0adf99;hpb=4c6bd5b5b61adfd912e14f8d704fde47628d164e;p=youtube-dl
diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py
index 66e52641b..c0433eabd 100644
--- a/youtube_dl/extractor/bbc.py
+++ b/youtube_dl/extractor/bbc.py
@@ -450,6 +450,14 @@ 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',
@@ -637,12 +645,30 @@ class BBCIE(BBCCoUkIE):
playlist_title = self._html_search_regex(
r'
(.*?)(?:\s*-\s*BBC [^ ]+)?', 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)