projects
/
youtube-dl
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
[downloader/http] Retry download when urlopen times out (#26603) (refs #10935)
[youtube-dl]
/
youtube_dl
/
extractor
/
bbc.py
diff --git
a/youtube_dl/extractor/bbc.py
b/youtube_dl/extractor/bbc.py
index eac9a5a4668961571c9162ca2be93aba3211438a..002c39c394bf5d8bd3b74600d92a594e1a8ca2b2 100644
(file)
--- a/
youtube_dl/extractor/bbc.py
+++ b/
youtube_dl/extractor/bbc.py
@@
-1,8
+1,8
@@
# coding: utf-8
from __future__ import unicode_literals
# coding: utf-8
from __future__ import unicode_literals
-import re
import itertools
import itertools
+import re
from .common import InfoExtractor
from ..utils import (
from .common import InfoExtractor
from ..utils import (
@@
-17,10
+17,12
@@
from ..utils import (
parse_iso8601,
try_get,
unescapeHTML,
parse_iso8601,
try_get,
unescapeHTML,
+ url_or_none,
urlencode_postdata,
urljoin,
)
from ..compat import (
urlencode_postdata,
urljoin,
)
from ..compat import (
+ compat_etree_Element,
compat_HTTPError,
compat_urlparse,
)
compat_HTTPError,
compat_urlparse,
)
@@
-38,6
+40,7
@@
class BBCCoUkIE(InfoExtractor):
iplayer(?:/[^/]+)?/(?:episode/|playlist/)|
music/(?:clips|audiovideo/popular)[/#]|
radio/player/|
iplayer(?:/[^/]+)?/(?:episode/|playlist/)|
music/(?:clips|audiovideo/popular)[/#]|
radio/player/|
+ sounds/play/|
events/[^/]+/play/[^/]+/
)
(?P<id>%s)(?!/(?:episodes|broadcasts|clips))
events/[^/]+/play/[^/]+/
)
(?P<id>%s)(?!/(?:episodes|broadcasts|clips))
@@
-68,7
+71,7
@@
class BBCCoUkIE(InfoExtractor):
'info_dict': {
'id': 'b039d07m',
'ext': 'flv',
'info_dict': {
'id': 'b039d07m',
'ext': 'flv',
- 'title': '
Leonard Cohen, Kaleidoscope - BBC Radio 4
',
+ 'title': '
Kaleidoscope, Leonard Cohen
',
'description': 'The Canadian poet and songwriter reflects on his musical career.',
},
'params': {
'description': 'The Canadian poet and songwriter reflects on his musical career.',
},
'params': {
@@
-206,7
+209,7
@@
class BBCCoUkIE(InfoExtractor):
},
'skip': 'Now it\'s really geo-restricted',
}, {
},
'skip': 'Now it\'s really geo-restricted',
}, {
- # compact player (https://github.com/
rg3
/youtube-dl/issues/8147)
+ # compact player (https://github.com/
ytdl-org
/youtube-dl/issues/8147)
'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player',
'info_dict': {
'id': 'p028bfkj',
'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player',
'info_dict': {
'id': 'p028bfkj',
@@
-218,6
+221,20
@@
class BBCCoUkIE(InfoExtractor):
# rtmp download
'skip_download': True,
},
# rtmp download
'skip_download': True,
},
+ }, {
+ 'url': 'https://www.bbc.co.uk/sounds/play/m0007jzb',
+ 'note': 'Audio',
+ 'info_dict': {
+ 'id': 'm0007jz9',
+ 'ext': 'mp4',
+ 'title': 'BBC Proms, 2019, Prom 34: West–Eastern Divan Orchestra',
+ 'description': "Live BBC Proms. West–Eastern Divan Orchestra with Daniel Barenboim and Martha Argerich.",
+ 'duration': 9840,
+ },
+ 'params': {
+ # rtmp download
+ 'skip_download': True,
+ }
}, {
'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
'only_matching': True,
}, {
'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
'only_matching': True,
@@
-310,7
+327,13
@@
class BBCCoUkIE(InfoExtractor):
def _get_subtitles(self, media, programme_id):
subtitles = {}
for connection in self._extract_connections(media):
def _get_subtitles(self, media, programme_id):
subtitles = {}
for connection in self._extract_connections(media):
- captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
+ cc_url = url_or_none(connection.get('href'))
+ if not cc_url:
+ continue
+ captions = self._download_xml(
+ cc_url, programme_id, 'Downloading captions', fatal=False)
+ if not isinstance(captions, compat_etree_Element):
+ continue
lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
subtitles[lang] = [
{
lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
subtitles[lang] = [
{
@@
-505,7
+528,7
@@
class BBCCoUkIE(InfoExtractor):
def get_programme_id(item):
def get_from_attributes(item):
def get_programme_id(item):
def get_from_attributes(item):
- for p in('identifier', 'group'):
+ for p in
('identifier', 'group'):
value = item.get(p)
if value and re.match(r'^[pb][\da-z]{7}$', value):
return value
value = item.get(p)
if value and re.match(r'^[pb][\da-z]{7}$', value):
return value
@@
-601,7
+624,7
@@
class BBCIE(BBCCoUkIE):
'url': 'http://www.bbc.com/news/world-europe-32668511',
'info_dict': {
'id': 'world-europe-32668511',
'url': 'http://www.bbc.com/news/world-europe-32668511',
'info_dict': {
'id': 'world-europe-32668511',
- 'title': 'Russia stages massive WW2 parade
despite Western boycott
',
+ 'title': 'Russia stages massive WW2 parade',
'description': 'md5:00ff61976f6081841f759a08bf78cc9c',
},
'playlist_count': 2,
'description': 'md5:00ff61976f6081841f759a08bf78cc9c',
},
'playlist_count': 2,