xZero707/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-24 03:41:00 +01:00
Code Issues Packages Projects Releases Wiki Activity

[rts] Use visible id in file names

Browse Source 
Maybe the internal ID is more precise, but it's totally confusing, and the obvious ID still allows a google search.
This commit is contained in:
Philipp Hagemeister 2014-04-04 23:13:52 +02:00
parent e09b8fcd9d
commit f8514f6186
1 changed files with 8 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
youtube_dl/extractor/rts.py
View File

@ -37,7 +37,7 @@ class RTSIE(InfoExtractor):
'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html', 'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
'md5': 'c197f0b2421995c63a64cc73d800f42e', 'md5': 'c197f0b2421995c63a64cc73d800f42e',
'info_dict': { 'info_dict': {
'id': '5738317', 'id': '5624067',
'ext': 'mp4', 'ext': 'mp4',
'duration': 55, 'duration': 55,
'title': 'Bande de lancement de Passe-moi les jumelles', 'title': 'Bande de lancement de Passe-moi les jumelles',
@ -98,17 +98,20 @@ def _real_extract(self, url):
m = re.match(self._VALID_URL, url) m = re.match(self._VALID_URL, url)
video_id = m.group('id') video_id = m.group('id')
def download_json(video_id): def download_json(internal_id):
return self._download_json( return self._download_json(
'http://www.rts.ch/a/%s.html?f=json/article' % video_id, video_id) 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id,
video_id)
all_info = download_json(video_id) all_info = download_json(video_id)
# video_id extracted out of URL is not always a real id # video_id extracted out of URL is not always a real id
if 'video' not in all_info and 'audio' not in all_info: if 'video' not in all_info and 'audio' not in all_info:
page = self._download_webpage(url, video_id) page = self._download_webpage(url, video_id)
video_id = self._html_search_regex(r'<(?:video|audio) data-id="(\d+)"', page, 'video id') internal_id = self._html_search_regex(
all_info = download_json(video_id) r'<(?:video|audio) data-id="([0-9]+)"', page,
'internal video id')
all_info = download_json(internal_id)
info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio'] info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']