]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/allocine.py
Drop hash character in downloader output (#4484)
[yt-dlp.git] / youtube_dl / extractor / allocine.py
CommitLineData
49cbe7c8
PP
1# -*- coding: utf-8 -*-
2from __future__ import unicode_literals
3
4import re
5import json
6
7from .common import InfoExtractor
1cc79574 8from ..compat import compat_str
49cbe7c8 9from ..utils import (
49cbe7c8 10 qualities,
49cbe7c8
PP
11)
12
13
14class AllocineIE(InfoExtractor):
15 _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=)(?P<id>[0-9]+)(?:\.html)?'
16
17 _TESTS = [{
18 'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',
19 'md5': '0c9fcf59a841f65635fa300ac43d8269',
20 'info_dict': {
21 'id': '19546517',
22 'ext': 'mp4',
23 'title': 'Astérix - Le Domaine des Dieux Teaser VF',
9d2a4dae 24 'description': 'md5:abcd09ce503c6560512c14ebfdb720d2',
49cbe7c8
PP
25 'thumbnail': 're:http://.*\.jpg',
26 },
27 }, {
28 'url': 'http://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html',
29 'md5': 'd0cdce5d2b9522ce279fdfec07ff16e0',
30 'info_dict': {
31 'id': '19540403',
32 'ext': 'mp4',
33 'title': 'Planes 2 Bande-annonce VF',
a5d524ef 34 'description': 'md5:eeaffe7c2d634525e21159b93acf3b1e',
49cbe7c8
PP
35 'thumbnail': 're:http://.*\.jpg',
36 },
37 }, {
38 'url': 'http://www.allocine.fr/film/fichefilm_gen_cfilm=181290.html',
39 'md5': '101250fb127ef9ca3d73186ff22a47ce',
40 'info_dict': {
41 'id': '19544709',
42 'ext': 'mp4',
43 'title': 'Dragons 2 - Bande annonce finale VF',
a5d524ef 44 'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac',
49cbe7c8
PP
45 'thumbnail': 're:http://.*\.jpg',
46 },
47 }]
48
49 def _real_extract(self, url):
50 mobj = re.match(self._VALID_URL, url)
51 typ = mobj.group('typ')
52 display_id = mobj.group('id')
53
54 webpage = self._download_webpage(url, display_id)
55
56 if typ == 'film':
57 video_id = self._search_regex(r'href="/video/player_gen_cmedia=([0-9]+).+"', webpage, 'video id')
58 else:
59 player = self._search_regex(r'data-player=\'([^\']+)\'>', webpage, 'data player')
60
61 player_data = json.loads(player)
62 video_id = compat_str(player_data['refMedia'])
63
64 xml = self._download_xml('http://www.allocine.fr/ws/AcVisiondataV4.ashx?media=%s' % video_id, display_id)
65
66 video = xml.find('.//AcVisionVideo').attrib
67 quality = qualities(['ld', 'md', 'hd'])
68
69 formats = []
70 for k, v in video.items():
71 if re.match(r'.+_path', k):
72 format_id = k.split('_')[0]
73 formats.append({
74 'format_id': format_id,
75 'quality': quality(format_id),
76 'url': v,
49cbe7c8 77 })
49cbe7c8
PP
78 self._sort_formats(formats)
79
80 return {
81 'id': video_id,
82 'title': video['videoTitle'],
83 'thumbnail': self._og_search_thumbnail(webpage),
84 'formats': formats,
85 'description': self._og_search_description(webpage),
86 }