depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-22 08:47:41 +00:00
Code Issues Releases Wiki Activity

[bbc] Fix BBC Extractor to work with 'School Report'

Browse source
This commit is contained in:
Benjamin Congdon 2016-03-11 09:31:35 -06:00 committed by Sergey M․
parent a42dfa629e
commit 8e4aa7bf18
1 changed files with 8 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
youtube_dl/extractor/bbc.py
View file

@ -10,7 +10,6 @@ from ..utils import (
int_or_none, int_or_none,
parse_duration, parse_duration,
parse_iso8601, parse_iso8601,
remove_end,
unescapeHTML, unescapeHTML,
) )
from ..compat import ( from ..compat import (
@ -796,9 +795,15 @@ class BBCIE(BBCCoUkIE):
entries.append(self._extract_from_playlist_sxml( entries.append(self._extract_from_playlist_sxml(
playlist.get('progressiveDownloadUrl'), playlist_id, timestamp)) playlist.get('progressiveDownloadUrl'), playlist_id, timestamp))
playlist_title = self._og_search_title(webpage, default=None)
playlist_title = playlist_title or self._html_search_regex(
r'<title>(.*?)</title>', webpage, 'playlist title')
playlist_title = self._search_regex(r'(.+)\s*-\s*BBC', playlist_title, 'title', default=playlist_title)
playlist_description = self._og_search_description(webpage, default=None)
if entries: 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) 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) # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
@ -829,10 +834,6 @@ class BBCIE(BBCCoUkIE):
'subtitles': subtitles, 'subtitles': subtitles,
} }
playlist_title = self._html_search_regex(
r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title')
playlist_description = self._og_search_description(webpage, default=None)
def extract_all(pattern): def extract_all(pattern):
return list(filter(None, map( return list(filter(None, map(
lambda s: self._parse_json(s, playlist_id, fatal=False), lambda s: self._parse_json(s, playlist_id, fatal=False),