xZero707/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 19:33:59 +01:00
Code Issues Packages Projects Releases Wiki Activity

[arte:+7] Fix extraction for react-based layout

Browse Source
This commit is contained in:
Sergey M․ 2016-02-17 21:49:15 +06:00
parent 0f425e65ec
commit 9654fc875b
1 changed files with 14 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
youtube_dl/extractor/arte.py
View File

@ -102,10 +102,20 @@ def find_iframe_url(webpage, default=NO_DEFAULT):
iframe_url = find_iframe_url(webpage, None) iframe_url = find_iframe_url(webpage, None)
if not iframe_url: if not iframe_url:
embed_url = self._html_search_regex( embed_url = self._html_search_regex(
r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url') r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url', default=None)
player = self._download_json( if embed_url:
embed_url, video_id, 'Downloading player page') player = self._download_json(
iframe_url = find_iframe_url(player['html']) embed_url, video_id, 'Downloading player page')
iframe_url = find_iframe_url(player['html'])
# en and es URLs produce react-based pages with different layout (e.g.
# http://www.arte.tv/guide/en/053330-002-A/carnival-italy?zone=world)
if not iframe_url:
embed_html = self._parse_json(
self._search_regex(
r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n',
webpage, 'program'),
video_id)['embed_html']
iframe_url= find_iframe_url(embed_html)
json_url = compat_parse_qs( json_url = compat_parse_qs(
compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0] compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
return self._extract_from_json_url(json_url, video_id, lang) return self._extract_from_json_url(json_url, video_id, lang)