]>
Commit | Line | Data |
---|---|---|
1 | from .common import InfoExtractor | |
2 | from ..compat import compat_str | |
3 | from ..utils import ( | |
4 | ExtractorError, | |
5 | int_or_none, | |
6 | try_get, | |
7 | unified_strdate, | |
8 | ) | |
9 | ||
10 | ||
11 | class WatIE(InfoExtractor): | |
12 | _VALID_URL = r'(?:wat:|https?://(?:www\.)?wat\.tv/video/.*-)(?P<id>[0-9a-z]+)' | |
13 | IE_NAME = 'wat.tv' | |
14 | _TESTS = [ | |
15 | { | |
16 | 'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html', | |
17 | 'info_dict': { | |
18 | 'id': '11713067', | |
19 | 'ext': 'mp4', | |
20 | 'title': 'Soupe de figues à l\'orange et aux épices', | |
21 | 'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.', | |
22 | 'upload_date': '20140819', | |
23 | 'duration': 120, | |
24 | }, | |
25 | 'params': { | |
26 | # m3u8 download | |
27 | 'skip_download': True, | |
28 | }, | |
29 | 'expected_warnings': ['HTTP Error 404'], | |
30 | 'skip': 'This content is no longer available', | |
31 | }, | |
32 | { | |
33 | 'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html', | |
34 | 'md5': 'b16574df2c3cd1a36ca0098f2a791925', | |
35 | 'info_dict': { | |
36 | 'id': '11713075', | |
37 | 'ext': 'mp4', | |
38 | 'title': 'Grégory Lemarchal, une voix d\'ange depuis 10 ans (1/3)', | |
39 | 'upload_date': '20140816', | |
40 | }, | |
41 | 'expected_warnings': ["Ce contenu n'est pas disponible pour l'instant."], | |
42 | 'skip': 'This content is no longer available', | |
43 | }, | |
44 | { | |
45 | 'url': 'wat:14010600', | |
46 | 'info_dict': { | |
47 | 'id': '14010600', | |
48 | 'title': 'Burger Quiz - S03 EP21 avec Eye Haidara, Anne Depétrini, Jonathan Zaccaï et Pio Marmaï', | |
49 | 'thumbnail': 'https://photos.tf1.fr/1280/720/burger-quiz-11-9adb79-0@1x.jpg', | |
50 | 'upload_date': '20230819', | |
51 | 'duration': 2312, | |
52 | 'ext': 'mp4', | |
53 | }, | |
54 | 'params': {'skip_download': 'm3u8'}, | |
55 | } | |
56 | ] | |
57 | _GEO_BYPASS = False | |
58 | ||
59 | def _real_extract(self, url): | |
60 | video_id = self._match_id(url) | |
61 | video_id = video_id if video_id.isdigit() and len(video_id) > 6 else compat_str(int(video_id, 36)) | |
62 | ||
63 | # 'contentv4' is used in the website, but it also returns the related | |
64 | # videos, we don't need them | |
65 | # video_data = self._download_json( | |
66 | # 'http://www.wat.tv/interface/contentv4s/' + video_id, video_id) | |
67 | video_data = self._download_json( | |
68 | 'https://mediainfo.tf1.fr/mediainfocombo/' + video_id, | |
69 | video_id, query={'pver': '5010000'}) | |
70 | video_info = video_data['media'] | |
71 | ||
72 | error_desc = video_info.get('error_desc') | |
73 | if error_desc: | |
74 | if video_info.get('error_code') == 'GEOBLOCKED': | |
75 | self.raise_geo_restricted(error_desc, video_info.get('geoList')) | |
76 | raise ExtractorError(error_desc, expected=True) | |
77 | ||
78 | title = video_info['title'] | |
79 | ||
80 | formats = [] | |
81 | subtitles = {} | |
82 | ||
83 | def extract_formats(manifest_urls): | |
84 | for f, f_url in manifest_urls.items(): | |
85 | if not f_url: | |
86 | continue | |
87 | if f in ('dash', 'mpd'): | |
88 | fmts, subs = self._extract_mpd_formats_and_subtitles( | |
89 | f_url.replace('://das-q1.tf1.fr/', '://das-q1-ssl.tf1.fr/'), | |
90 | video_id, mpd_id='dash', fatal=False) | |
91 | elif f == 'hls': | |
92 | fmts, subs = self._extract_m3u8_formats_and_subtitles( | |
93 | f_url, video_id, 'mp4', | |
94 | 'm3u8_native', m3u8_id='hls', fatal=False) | |
95 | else: | |
96 | continue | |
97 | formats.extend(fmts) | |
98 | self._merge_subtitles(subs, target=subtitles) | |
99 | ||
100 | delivery = video_data.get('delivery') or {} | |
101 | extract_formats({delivery.get('format'): delivery.get('url')}) | |
102 | if not formats: | |
103 | if delivery.get('drm'): | |
104 | self.report_drm(video_id) | |
105 | manifest_urls = self._download_json( | |
106 | 'http://www.wat.tv/get/webhtml/' + video_id, video_id, fatal=False) | |
107 | if manifest_urls: | |
108 | extract_formats(manifest_urls) | |
109 | ||
110 | return { | |
111 | 'id': video_id, | |
112 | 'title': title, | |
113 | 'thumbnail': video_info.get('preview'), | |
114 | 'upload_date': unified_strdate(try_get( | |
115 | video_data, lambda x: x['mediametrie']['chapters'][0]['estatS4'])), | |
116 | 'duration': int_or_none(video_info.get('duration')), | |
117 | 'formats': formats, | |
118 | 'subtitles': subtitles, | |
119 | } |