]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/canalplus.py
Prepare new release.
[youtubedl] / youtube_dl / extractor / canalplus.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..compat import compat_urllib_parse_urlparse
8 from ..utils import (
9 dict_get,
10 ExtractorError,
11 HEADRequest,
12 int_or_none,
13 qualities,
14 remove_end,
15 unified_strdate,
16 )
17
18
19 class CanalplusIE(InfoExtractor):
20 IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
21 _VALID_URL = r'''(?x)
22 https?://
23 (?:
24 (?:
25 (?:(?:www|m)\.)?canalplus\.fr|
26 (?:www\.)?piwiplus\.fr|
27 (?:www\.)?d8\.tv|
28 (?:www\.)?c8\.fr|
29 (?:www\.)?d17\.tv|
30 (?:(?:football|www)\.)?cstar\.fr|
31 (?:www\.)?itele\.fr
32 )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
33 player\.canalplus\.fr/#/(?P<id>\d+)
34 )
35
36 '''
37 _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'
38 _SITE_ID_MAP = {
39 'canalplus': 'cplus',
40 'piwiplus': 'teletoon',
41 'd8': 'd8',
42 'c8': 'd8',
43 'd17': 'd17',
44 'cstar': 'd17',
45 'itele': 'itele',
46 }
47
48 _TESTS = [{
49 'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814',
50 'info_dict': {
51 'id': '1405510',
52 'display_id': 'pid1830-c-zapping',
53 'ext': 'mp4',
54 'title': 'Zapping - 02/07/2016',
55 'description': 'Le meilleur de toutes les chaînes, tous les jours',
56 'upload_date': '20160702',
57 },
58 }, {
59 'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
60 'info_dict': {
61 'id': '1108190',
62 'display_id': 'pid1405-le-labyrinthe-boing-super-ranger',
63 'ext': 'mp4',
64 'title': 'BOING SUPER RANGER - Ep : Le labyrinthe',
65 'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
66 'upload_date': '20140724',
67 },
68 'skip': 'Only works from France',
69 }, {
70 'url': 'http://www.c8.fr/c8-divertissement/ms-touche-pas-a-mon-poste/pid6318-videos-integrales.html',
71 'md5': '4b47b12b4ee43002626b97fad8fb1de5',
72 'info_dict': {
73 'id': '1420213',
74 'display_id': 'pid6318-videos-integrales',
75 'ext': 'mp4',
76 'title': 'TPMP ! Même le matin - Les 35H de Baba - 14/10/2016',
77 'description': 'md5:f96736c1b0ffaa96fd5b9e60ad871799',
78 'upload_date': '20161014',
79 },
80 'skip': 'Only works from France',
81 }, {
82 'url': 'http://www.itele.fr/chroniques/invite-michael-darmon/rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510',
83 'info_dict': {
84 'id': '1420176',
85 'display_id': 'rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510',
86 'ext': 'mp4',
87 'title': 'L\'invité de Michaël Darmon du 14/10/2016 - ',
88 'description': 'Chaque matin du lundi au vendredi, Michaël Darmon reçoit un invité politique à 8h25.',
89 'upload_date': '20161014',
90 },
91 }, {
92 'url': 'http://football.cstar.fr/cstar-minisite-foot/pid7566-feminines-videos.html?vid=1416769',
93 'info_dict': {
94 'id': '1416769',
95 'display_id': 'pid7566-feminines-videos',
96 'ext': 'mp4',
97 'title': 'France - Albanie : les temps forts de la soirée - 20/09/2016',
98 'description': 'md5:c3f30f2aaac294c1c969b3294de6904e',
99 'upload_date': '20160921',
100 },
101 'params': {
102 'skip_download': True,
103 },
104 }, {
105 'url': 'http://m.canalplus.fr/?vid=1398231',
106 'only_matching': True,
107 }, {
108 'url': 'http://www.d17.tv/emissions/pid8303-lolywood.html?vid=1397061',
109 'only_matching': True,
110 }]
111
112 def _real_extract(self, url):
113 mobj = re.match(self._VALID_URL, url)
114
115 site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]]
116
117 # Beware, some subclasses do not define an id group
118 display_id = remove_end(dict_get(mobj.groupdict(), ('display_id', 'id', 'vid')), '.html')
119
120 webpage = self._download_webpage(url, display_id)
121 video_id = self._search_regex(
122 [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)',
123 r'id=["\']canal_video_player(?P<id>\d+)',
124 r'data-video=["\'](?P<id>\d+)'],
125 webpage, 'video id', default=mobj.group('vid'), group='id')
126
127 info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
128 video_data = self._download_json(info_url, video_id, 'Downloading video JSON')
129
130 if isinstance(video_data, list):
131 video_data = [video for video in video_data if video.get('ID') == video_id][0]
132 media = video_data['MEDIA']
133 infos = video_data['INFOS']
134
135 preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD'])
136
137 fmt_url = next(iter(media.get('VIDEOS')))
138 if '/geo' in fmt_url.lower():
139 response = self._request_webpage(
140 HEADRequest(fmt_url), video_id,
141 'Checking if the video is georestricted')
142 if '/blocage' in response.geturl():
143 raise ExtractorError(
144 'The video is not available in your country',
145 expected=True)
146
147 formats = []
148 for format_id, format_url in media['VIDEOS'].items():
149 if not format_url:
150 continue
151 if format_id == 'HLS':
152 formats.extend(self._extract_m3u8_formats(
153 format_url, video_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
154 elif format_id == 'HDS':
155 formats.extend(self._extract_f4m_formats(
156 format_url + '?hdcore=2.11.3', video_id, f4m_id=format_id, fatal=False))
157 else:
158 formats.append({
159 # the secret extracted ya function in http://player.canalplus.fr/common/js/canalPlayer.js
160 'url': format_url + '?secret=pqzerjlsmdkjfoiuerhsdlfknaes',
161 'format_id': format_id,
162 'preference': preference(format_id),
163 })
164 self._sort_formats(formats)
165
166 thumbnails = [{
167 'id': image_id,
168 'url': image_url,
169 } for image_id, image_url in media.get('images', {}).items()]
170
171 titrage = infos['TITRAGE']
172
173 return {
174 'id': video_id,
175 'display_id': display_id,
176 'title': '%s - %s' % (titrage['TITRE'],
177 titrage['SOUS_TITRE']),
178 'upload_date': unified_strdate(infos.get('PUBLICATION', {}).get('DATE')),
179 'thumbnails': thumbnails,
180 'description': infos.get('DESCRIPTION'),
181 'duration': int_or_none(infos.get('DURATION')),
182 'view_count': int_or_none(infos.get('NB_VUES')),
183 'like_count': int_or_none(infos.get('NB_LIKES')),
184 'comment_count': int_or_none(infos.get('NB_COMMENTS')),
185 'formats': formats,
186 }