pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2025-02-05 18:20:10 +09:00
Code Issues Projects Releases Wiki Activity

Get HD formats for Reel

Browse Source
This commit is contained in:
dirkf 2021-03-03 13:33:33 +00:00 committed by GitHub
parent f68692b004
commit 9c7f8ad7bb
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 25 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
youtube_dl/extractor/bbc.py
View File

@ -995,6 +995,8 @@ class BBCIE(BBCCoUkIE):
} }
# bbc reel (e.g. https://www.bbc.com/reel/video/p07c6sb6/how-positive-thinking-is-harming-your-happiness) # bbc reel (e.g. https://www.bbc.com/reel/video/p07c6sb6/how-positive-thinking-is-harming-your-happiness)
programme_id = self._search_regex(
r'/reel/video/(?P<id>%s)/' % self._ID_REGEX, url, 'Reel pid', default=None)
initial_data = self._parse_json(self._html_search_regex( initial_data = self._parse_json(self._html_search_regex(
r'<script[^>]+id=(["\'])initial-data\1[^>]+data-json=(["\'])(?P<json>(?:(?!\2).)+)', r'<script[^>]+id=(["\'])initial-data\1[^>]+data-json=(["\'])(?P<json>(?:(?!\2).)+)',
webpage, 'initial data', default='{}', group='json'), playlist_id, fatal=False) webpage, 'initial data', default='{}', group='json'), playlist_id, fatal=False)
@ -1005,26 +1007,40 @@ class BBCIE(BBCCoUkIE):
clip_data = try_get(smp_data, lambda x: x['items'][0], dict) or {} clip_data = try_get(smp_data, lambda x: x['items'][0], dict) or {}
version_id = clip_data.get('versionID') version_id = clip_data.get('versionID')
if version_id: if version_id:
title = smp_data['title']
formats, subtitles = self._download_media_selector(version_id)
self._sort_formats(formats)
image_url = smp_data.get('holdingImageURL') image_url = smp_data.get('holdingImageURL')
display_date = init_data.get('displayDate') display_date = init_data.get('displayDate')
topic_title = init_data.get('topicTitle') topic_title = init_data.get('topicTitle')
ret = {
return { 'title': smp_data.get('title', playlist_id),
'id': version_id,
'title': title,
'formats': formats,
'alt_title': init_data.get('shortTitle'), 'alt_title': init_data.get('shortTitle'),
'thumbnail': image_url.replace('$recipe', 'raw') if image_url else None, 'thumbnail': image_url.replace('$recipe', 'raw') if image_url else None,
'description': smp_data.get('summary') or init_data.get('shortSummary'), 'description': smp_data.get('summary') or init_data.get('shortSummary'),
'upload_date': display_date.replace('-', '') if display_date else None, 'upload_date': display_date.replace('-', '') if display_date else None,
'subtitles': subtitles,
'duration': int_or_none(clip_data.get('duration')), 'duration': int_or_none(clip_data.get('duration')),
'categories': [topic_title] if topic_title else None, 'categories': [topic_title] if topic_title else None,
} }
if not programme_id:
# get the formats from the reel page
formats, subtitles = self._download_media_selector(version_id)
self._sort_formats(formats)
ret.update({
'id': version_id,
'formats': formats,
'subtitles': subtitles,
})
else:
# get the formats (including HD) from the programmes page
# avoid https: to help proxying
ret.update({
'_type': 'url_transparent',
'url': 'http://bbc.co.uk/programmes/%s' % programme_id
})
return ret
elif programme_id:
# the Reel page was not as expected: try the programmes page
return self._url_result(programme_id)
# Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975) # Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975)
# There are several setPayload calls may be present but the video # There are several setPayload calls may be present but the video
# seems to be always related to the first one # seems to be always related to the first one