X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Fbbc.py;h=425f08f2b6bba12f054f13aa0de6eefddcebcfa7;hb=8c7d6e8e2279beccf638cd0fae9d91876e0486b2;hp=7b169881affaffa374a7fe7f327da237395dc977;hpb=3f3343cd3e020b306fcab28d9c400f2c526b2ced;p=youtube-dl.git
diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py
index 7b169881a..425f08f2b 100644
--- a/youtube_dl/extractor/bbc.py
+++ b/youtube_dl/extractor/bbc.py
@@ -10,7 +10,6 @@ from ..utils import (
int_or_none,
parse_duration,
parse_iso8601,
- remove_end,
unescapeHTML,
)
from ..compat import (
@@ -86,7 +85,7 @@ class BBCCoUkIE(InfoExtractor):
'id': 'b00yng1d',
'ext': 'flv',
'title': 'The Voice UK: Series 3: Blind Auditions 5',
- 'description': "Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.",
+ 'description': 'Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.',
'duration': 5100,
},
'params': {
@@ -124,14 +123,14 @@ class BBCCoUkIE(InfoExtractor):
},
'skip': 'Episode is no longer available on BBC iPlayer Radio',
}, {
- 'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
+ 'url': 'http://www.bbc.co.uk/music/clips/p022h44b',
'note': 'Audio',
'info_dict': {
- 'id': 'p02frcch',
+ 'id': 'p022h44j',
'ext': 'flv',
- 'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix',
- 'description': 'French house superstar Madeon takes us out of the club and onto the after party.',
- 'duration': 3507,
+ 'title': 'BBC Proms Music Guides, Rachmaninov: Symphonic Dances',
+ 'description': "In this Proms Music Guide, Andrew McGregor looks at Rachmaninov's Symphonic Dances.",
+ 'duration': 227,
},
'params': {
# rtmp download
@@ -182,13 +181,25 @@ class BBCCoUkIE(InfoExtractor):
}, {
# 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',
+ 'url': 'http://www.bbc.co.uk/programmes/b06rkn85',
'info_dict': {
- 'id': 'b06bp7kf',
+ 'id': 'b06rkms3',
'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,
+ 'title': "Best of the Mini-Mixes 2015: Part 3, Annie Mac's Friday Night - BBC Radio 1",
+ 'description': "Annie has part three in the Best of the Mini-Mixes 2015, plus the year's Most Played!",
+ },
+ 'params': {
+ # rtmp download
+ 'skip_download': True,
+ },
+ }, {
+ # compact player (https://github.com/rg3/youtube-dl/issues/8147)
+ 'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player',
+ 'info_dict': {
+ 'id': 'p028bfkj',
+ 'ext': 'flv',
+ 'title': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
+ 'description': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
},
'params': {
# rtmp download
@@ -317,6 +328,7 @@ class BBCCoUkIE(InfoExtractor):
'format_id': '%s_%s' % (service, format['format_id']),
'abr': abr,
'acodec': acodec,
+ 'vcodec': 'none',
})
formats.extend(conn_formats)
return formats
@@ -483,9 +495,11 @@ class BBCCoUkIE(InfoExtractor):
if programme_id:
formats, subtitles = self._download_media_selector(programme_id)
title = self._og_search_title(webpage, default=None) or self._html_search_regex(
- r'
]+id="parent-title"[^>]*>(.+?)
', webpage, 'title')
+ (r']+id="parent-title"[^>]*>(.+?)
',
+ r']+class="info"[^>]*>\s*
(.+?)
'), webpage, 'title')
description = self._search_regex(
- r'
([^<]+)
',
+ (r'
([^<]+)
',
+ r'
]+class="info_+synopsis"[^>]*>([^<]+)
'),
webpage, 'description', default=None)
if not description:
description = self._html_search_meta('description', webpage)
@@ -547,7 +561,7 @@ class BBCIE(BBCCoUkIE):
'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',
+ 'title': 'BUGGER',
},
'playlist_count': 18,
}, {
@@ -656,9 +670,17 @@ class BBCIE(BBCCoUkIE):
'url': 'http://www.bbc.com/sport/0/football/34475836',
'info_dict': {
'id': '34475836',
- 'title': 'What Liverpool can expect from Klopp',
+ 'title': 'Jurgen Klopp: Furious football from a witty and winning coach',
},
'playlist_count': 3,
+ }, {
+ # school report article with single video
+ 'url': 'http://www.bbc.co.uk/schoolreport/35744779',
+ 'info_dict': {
+ 'id': '35744779',
+ 'title': 'School which breaks down barriers in Jerusalem',
+ },
+ 'playlist_count': 1,
}, {
# single video with playlist URL from weather section
'url': 'http://www.bbc.com/weather/features/33601775',
@@ -667,6 +689,10 @@ class BBCIE(BBCCoUkIE):
# custom redirection to www.bbc.com
'url': 'http://www.bbc.co.uk/news/science-environment-33661876',
'only_matching': True,
+ }, {
+ # single video article embedded with data-media-vpid
+ 'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
+ 'only_matching': True,
}]
@classmethod
@@ -719,19 +745,19 @@ class BBCIE(BBCCoUkIE):
webpage = self._download_webpage(url, playlist_id)
- timestamp = None
- playlist_title = None
- playlist_description = None
+ json_ld_info = self._search_json_ld(webpage, playlist_id, default=None)
+ timestamp = json_ld_info.get('timestamp')
- ld = self._parse_json(
- self._search_regex(
- r'(?s)',
- webpage, 'ld json', default='{}'),
- playlist_id, fatal=False)
- if ld:
- timestamp = parse_iso8601(ld.get('datePublished'))
- playlist_title = ld.get('headline')
- playlist_description = ld.get('articleBody')
+ playlist_title = json_ld_info.get('title')
+ if not playlist_title:
+ playlist_title = self._og_search_title(
+ webpage, default=None) or self._html_search_regex(
+ r'
(.+?)', webpage, 'playlist title', default=None)
+ if playlist_title:
+ playlist_title = re.sub(r'(.+)\s*-\s*BBC.*?$', r'\1', playlist_title).strip()
+
+ playlist_description = json_ld_info.get(
+ 'description') or self._og_search_description(webpage, default=None)
if not timestamp:
timestamp = parse_iso8601(self._search_regex(
@@ -792,13 +818,11 @@ class BBCIE(BBCCoUkIE):
playlist.get('progressiveDownloadUrl'), playlist_id, timestamp))
if entries:
- playlist_title = playlist_title or remove_end(self._og_search_title(webpage), ' - BBC News')
- playlist_description = playlist_description or self._og_search_description(webpage, default=None)
return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
# 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="(%s)"' % self._ID_REGEX,
+ [r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX,
r'
]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX,
r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
webpage, 'vpid', default=None)
@@ -824,10 +848,6 @@ class BBCIE(BBCCoUkIE):
'subtitles': subtitles,
}
- playlist_title = self._html_search_regex(
- r'
(.*?)(?:\s*-\s*BBC [^ ]+)?', webpage, 'playlist title')
- 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),
@@ -927,7 +947,7 @@ class BBCIE(BBCCoUkIE):
class BBCCoUkArticleIE(InfoExtractor):
- _VALID_URL = 'http://www.bbc.co.uk/programmes/articles/(?P
[a-zA-Z0-9]+)'
+ _VALID_URL = r'https?://www.bbc.co.uk/programmes/articles/(?P[a-zA-Z0-9]+)'
IE_NAME = 'bbc.co.uk:article'
IE_DESC = 'BBC articles'