mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-11-27 14:15:37 +01:00
[bbc] fix BBC News videos extraction
This commit is contained in:
parent
579d43951d
commit
6c35de4c6b
|
@ -981,7 +981,7 @@ class BBCIE(BBCCoUkIE):
|
||||||
group_id = self._search_regex(
|
group_id = self._search_regex(
|
||||||
r'<div[^>]+\bclass=["\']video["\'][^>]+\bdata-pid=["\'](%s)' % self._ID_REGEX,
|
r'<div[^>]+\bclass=["\']video["\'][^>]+\bdata-pid=["\'](%s)' % self._ID_REGEX,
|
||||||
webpage, 'group id', default=None)
|
webpage, 'group id', default=None)
|
||||||
if playlist_id:
|
if group_id:
|
||||||
return self.url_result(
|
return self.url_result(
|
||||||
'https://www.bbc.co.uk/programmes/%s' % group_id,
|
'https://www.bbc.co.uk/programmes/%s' % group_id,
|
||||||
ie=BBCCoUkIE.ie_key())
|
ie=BBCCoUkIE.ie_key())
|
||||||
|
@ -1118,6 +1118,39 @@ class BBCIE(BBCCoUkIE):
|
||||||
return self.playlist_result(
|
return self.playlist_result(
|
||||||
entries, playlist_id, playlist_title, playlist_description)
|
entries, playlist_id, playlist_title, playlist_description)
|
||||||
|
|
||||||
|
initial_data = self._parse_json(self._search_regex(
|
||||||
|
r'window\.__INITIAL_DATA__\s*=\s*({.+?});', webpage,
|
||||||
|
'preload state', default='{}'), playlist_id, fatal=False)
|
||||||
|
if initial_data:
|
||||||
|
def parse_media(media):
|
||||||
|
if not media:
|
||||||
|
return
|
||||||
|
for item in (try_get(media, lambda x: x['media']['items'], list) or []):
|
||||||
|
item_id = item.get('id')
|
||||||
|
item_title = item.get('title')
|
||||||
|
if not (item_id and item_title):
|
||||||
|
continue
|
||||||
|
formats, subtitles = self._download_media_selector(item_id)
|
||||||
|
self._sort_formats(formats)
|
||||||
|
entries.append({
|
||||||
|
'id': item_id,
|
||||||
|
'title': item_title,
|
||||||
|
'thumbnail': item.get('holdingImageUrl'),
|
||||||
|
'formats': formats,
|
||||||
|
'subtitles': subtitles,
|
||||||
|
})
|
||||||
|
for resp in (initial_data.get('data') or {}).values():
|
||||||
|
name = resp.get('name')
|
||||||
|
if name == 'media-experience':
|
||||||
|
parse_media(try_get(resp, lambda x: x['data']['initialItem']['mediaItem'], dict))
|
||||||
|
elif name == 'article':
|
||||||
|
for block in (try_get(resp, lambda x: x['data']['blocks'], list) or []):
|
||||||
|
if block.get('type') != 'media':
|
||||||
|
continue
|
||||||
|
parse_media(block.get('model'))
|
||||||
|
return self.playlist_result(
|
||||||
|
entries, playlist_id, playlist_title, playlist_description)
|
||||||
|
|
||||||
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),
|
||||||
|
|
Loading…
Reference in New Issue
Block a user