1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-29 12:17:41 +00:00
youtube-dl/youtube_dl/extractor/jeuxvideo.py

57 lines
2 KiB
Python
Raw Normal View History

# coding: utf-8
2014-02-08 17:43:12 +00:00
from __future__ import unicode_literals
2013-08-18 14:11:47 +00:00
import re
from .common import InfoExtractor
2013-08-18 14:11:47 +00:00
class JeuxVideoIE(InfoExtractor):
_VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)\.htm'
2013-08-18 14:11:47 +00:00
_TESTS = [{
2014-02-08 17:43:12 +00:00
'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
'md5': '046e491afb32a8aaac1f44dd4ddd54ee',
'info_dict': {
'id': '114765',
2014-02-08 17:43:12 +00:00
'ext': 'mp4',
'title': 'Tearaway : GC 2013 : Tearaway nous présente ses papiers d\'identité',
'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.',
},
}, {
'url': 'http://www.jeuxvideo.com/videos/chroniques/434220/l-histoire-du-jeu-video-la-saturn.htm',
'only_matching': True,
}]
2013-08-18 14:11:47 +00:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
title = mobj.group(1)
2013-08-18 14:11:47 +00:00
webpage = self._download_webpage(url, title)
title = self._html_search_meta('name', webpage) or self._og_search_title(webpage)
config_url = self._html_search_regex(
r'data-src="(/contenu/medias/video.php.*?)"',
2014-02-08 17:43:12 +00:00
webpage, 'config URL')
config_url = 'http://www.jeuxvideo.com' + config_url
2014-11-23 19:41:03 +00:00
video_id = self._search_regex(
r'id=(\d+)',
config_url, 'video ID')
2013-08-18 14:11:47 +00:00
config = self._download_json(
config_url, title, 'Downloading JSON config')
2014-11-23 19:41:03 +00:00
formats = [{
'url': source['file'],
'format_id': source['label'],
'resolution': source['label'],
} for source in reversed(config['sources'])]
2013-08-18 14:11:47 +00:00
return {
'id': video_id,
'title': title,
'formats': formats,
'description': self._og_search_description(webpage),
'thumbnail': config.get('image'),
}