]> gitweb @ CieloNegro.org - youtube-dl.git/blob - youtube_dl/extractor/allocine.py
[yahoo] add support GYAO episode URLs
[youtube-dl.git] / youtube_dl / extractor / allocine.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..compat import compat_str
6 from ..utils import (
7     int_or_none,
8     qualities,
9     remove_end,
10     try_get,
11     unified_timestamp,
12     url_basename,
13 )
14
15
16 class AllocineIE(InfoExtractor):
17     _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?:article|video|film)/(?:fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?'
18
19     _TESTS = [{
20         'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',
21         'md5': '0c9fcf59a841f65635fa300ac43d8269',
22         'info_dict': {
23             'id': '19546517',
24             'display_id': '18635087',
25             'ext': 'mp4',
26             'title': 'Astérix - Le Domaine des Dieux Teaser VF',
27             'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
28             'thumbnail': r're:http://.*\.jpg',
29             'duration': 39,
30             'timestamp': 1404273600,
31             'upload_date': '20140702',
32             'view_count': int,
33         },
34     }, {
35         'url': 'http://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html',
36         'md5': 'd0cdce5d2b9522ce279fdfec07ff16e0',
37         'info_dict': {
38             'id': '19540403',
39             'display_id': '19540403',
40             'ext': 'mp4',
41             'title': 'Planes 2 Bande-annonce VF',
42             'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway',
43             'thumbnail': r're:http://.*\.jpg',
44             'duration': 69,
45             'timestamp': 1385659800,
46             'upload_date': '20131128',
47             'view_count': int,
48         },
49     }, {
50         'url': 'http://www.allocine.fr/video/player_gen_cmedia=19544709&cfilm=181290.html',
51         'md5': '101250fb127ef9ca3d73186ff22a47ce',
52         'info_dict': {
53             'id': '19544709',
54             'display_id': '19544709',
55             'ext': 'mp4',
56             'title': 'Dragons 2 - Bande annonce finale VF',
57             'description': 'md5:6cdd2d7c2687d4c6aafe80a35e17267a',
58             'thumbnail': r're:http://.*\.jpg',
59             'duration': 144,
60             'timestamp': 1397589900,
61             'upload_date': '20140415',
62             'view_count': int,
63         },
64     }, {
65         'url': 'http://www.allocine.fr/video/video-19550147/',
66         'md5': '3566c0668c0235e2d224fd8edb389f67',
67         'info_dict': {
68             'id': '19550147',
69             'ext': 'mp4',
70             'title': 'Faux Raccord N°123 - Les gaffes de Cliffhanger',
71             'description': 'md5:bc734b83ffa2d8a12188d9eb48bb6354',
72             'thumbnail': r're:http://.*\.jpg',
73         },
74     }]
75
76     def _real_extract(self, url):
77         display_id = self._match_id(url)
78
79         webpage = self._download_webpage(url, display_id)
80
81         formats = []
82         quality = qualities(['ld', 'md', 'hd'])
83
84         model = self._html_search_regex(
85             r'data-model="([^"]+)"', webpage, 'data model', default=None)
86         if model:
87             model_data = self._parse_json(model, display_id)
88             video = model_data['videos'][0]
89             title = video['title']
90             for video_url in video['sources'].values():
91                 video_id, format_id = url_basename(video_url).split('_')[:2]
92                 formats.append({
93                     'format_id': format_id,
94                     'quality': quality(format_id),
95                     'url': video_url,
96                 })
97             duration = int_or_none(video.get('duration'))
98             view_count = int_or_none(video.get('view_count'))
99             timestamp = unified_timestamp(try_get(
100                 video, lambda x: x['added_at']['date'], compat_str))
101         else:
102             video_id = display_id
103             media_data = self._download_json(
104                 'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media=%s' % video_id, display_id)
105             title = remove_end(
106                 self._html_search_regex(
107                     r'(?s)<title>(.+?)</title>', webpage, 'title').strip(),
108                 ' - AlloCiné')
109             for key, value in media_data['video'].items():
110                 if not key.endswith('Path'):
111                     continue
112                 format_id = key[:-len('Path')]
113                 formats.append({
114                     'format_id': format_id,
115                     'quality': quality(format_id),
116                     'url': value,
117                 })
118             duration, view_count, timestamp = [None] * 3
119
120         self._sort_formats(formats)
121
122         return {
123             'id': video_id,
124             'display_id': display_id,
125             'title': title,
126             'description': self._og_search_description(webpage),
127             'thumbnail': self._og_search_thumbnail(webpage),
128             'duration': duration,
129             'timestamp': timestamp,
130             'view_count': view_count,
131             'formats': formats,
132         }