]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/allocine.py
7d65b81931fb2d9b3acb5dd4ab2961a2aec52bea
1 # -*- coding: utf-8 -*-
2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
8 from ..compat
import compat_str
14 class AllocineIE(InfoExtractor
):
15 _VALID_URL
= r
'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?'
18 'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',
19 'md5': '0c9fcf59a841f65635fa300ac43d8269',
23 'title': 'Astérix - Le Domaine des Dieux Teaser VF',
24 'description': 'md5:abcd09ce503c6560512c14ebfdb720d2',
25 'thumbnail': 're:http://.*\.jpg',
28 'url': 'http://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html',
29 'md5': 'd0cdce5d2b9522ce279fdfec07ff16e0',
33 'title': 'Planes 2 Bande-annonce VF',
34 'description': 'md5:eeaffe7c2d634525e21159b93acf3b1e',
35 'thumbnail': 're:http://.*\.jpg',
38 'url': 'http://www.allocine.fr/film/fichefilm_gen_cfilm=181290.html',
39 'md5': '101250fb127ef9ca3d73186ff22a47ce',
43 'title': 'Dragons 2 - Bande annonce finale VF',
44 'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac',
45 'thumbnail': 're:http://.*\.jpg',
48 'url': 'http://www.allocine.fr/video/video-19550147/',
49 'only_matching': True,
52 def _real_extract(self
, url
):
53 mobj
= re
.match(self
._VALID
_URL
, url
)
54 typ
= mobj
.group('typ')
55 display_id
= mobj
.group('id')
57 webpage
= self
._download
_webpage
(url
, display_id
)
60 video_id
= self
._search
_regex
(r
'href="/video/player_gen_cmedia=([0-9]+).+"', webpage
, 'video id')
62 player
= self
._search
_regex
(r
'data-player=\'([^
\']+)\'>', webpage, 'data player
')
64 player_data = json.loads(player)
65 video_id = compat_str(player_data['refMedia
'])
67 xml = self._download_xml('http
://www
.allocine
.fr
/ws
/AcVisiondataV4
.ashx?media
=%s' % video_id, display_id)
69 video = xml.find('.//AcVisionVideo
').attrib
70 quality = qualities(['ld
', 'md
', 'hd
'])
73 for k, v in video.items():
74 if re.match(r'.+_path
', k):
75 format_id = k.split('_
')[0]
77 'format_id
': format_id,
78 'quality
': quality(format_id),
81 self._sort_formats(formats)
85 'title
': video['videoTitle
'],
86 'thumbnail
': self._og_search_thumbnail(webpage),
88 'description
': self._og_search_description(webpage),