]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/sixplay.py
Prepare to upload.
[youtubedl] / youtube_dl / extractor / sixplay.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 (
8 compat_parse_qs,
9 compat_str,
10 compat_urllib_parse_urlparse,
11 )
12 from ..utils import (
13 determine_ext,
14 int_or_none,
15 try_get,
16 qualities,
17 )
18
19
20 class SixPlayIE(InfoExtractor):
21 IE_NAME = '6play'
22 _VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P<domain>6play\.fr|rtlplay\.be|play\.rtl\.hr|rtlmost\.hu)/.+?-c_)(?P<id>[0-9]+)'
23 _TESTS = [{
24 'url': 'https://www.6play.fr/minute-par-minute-p_9533/le-but-qui-a-marque-lhistoire-du-football-francais-c_12041051',
25 'md5': '31fcd112637baa0c2ab92c4fcd8baf27',
26 'info_dict': {
27 'id': '12041051',
28 'ext': 'mp4',
29 'title': 'Le but qui a marqué l\'histoire du football français !',
30 'description': 'md5:b59e7e841d646ef1eb42a7868eb6a851',
31 },
32 }, {
33 'url': 'https://www.rtlplay.be/rtl-info-13h-p_8551/les-titres-du-rtlinfo-13h-c_12045869',
34 'only_matching': True,
35 }, {
36 'url': 'https://play.rtl.hr/pj-masks-p_9455/epizoda-34-sezona-1-catboyevo-cudo-na-dva-kotaca-c_11984989',
37 'only_matching': True,
38 }, {
39 'url': 'https://www.rtlmost.hu/megtorve-p_14167/megtorve-6-resz-c_12397787',
40 'only_matching': True,
41 }]
42
43 def _real_extract(self, url):
44 domain, video_id = re.search(self._VALID_URL, url).groups()
45 service, consumer_name = {
46 '6play.fr': ('6play', 'm6web'),
47 'rtlplay.be': ('rtlbe_rtl_play', 'rtlbe'),
48 'play.rtl.hr': ('rtlhr_rtl_play', 'rtlhr'),
49 'rtlmost.hu': ('rtlhu_rtl_most', 'rtlhu'),
50 }.get(domain, ('6play', 'm6web'))
51
52 data = self._download_json(
53 'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/%s/videos/clip_%s' % (service, video_id),
54 video_id, headers={
55 'x-customer-name': consumer_name
56 }, query={
57 'csa': 5,
58 'with': 'clips',
59 })
60
61 clip_data = data['clips'][0]
62 title = clip_data['title']
63
64 urls = []
65 quality_key = qualities(['lq', 'sd', 'hq', 'hd'])
66 formats = []
67 subtitles = {}
68 assets = clip_data.get('assets') or []
69 for asset in assets:
70 asset_url = asset.get('full_physical_path')
71 protocol = asset.get('protocol')
72 if not asset_url or ((protocol == 'primetime' or asset.get('type') == 'usp_hlsfp_h264') and not ('_drmnp.ism/' in asset_url or '_unpnp.ism/' in asset_url)) or asset_url in urls:
73 continue
74 urls.append(asset_url)
75 container = asset.get('video_container')
76 ext = determine_ext(asset_url)
77 if protocol == 'http_subtitle' or ext == 'vtt':
78 subtitles.setdefault('fr', []).append({'url': asset_url})
79 continue
80 if container == 'm3u8' or ext == 'm3u8':
81 if protocol == 'usp':
82 if compat_parse_qs(compat_urllib_parse_urlparse(asset_url).query).get('token', [None])[0]:
83 urlh = self._request_webpage(
84 asset_url, video_id, fatal=False,
85 headers=self.geo_verification_headers())
86 if not urlh:
87 continue
88 asset_url = urlh.geturl()
89 asset_url = asset_url.replace('_drmnp.ism/', '_unpnp.ism/')
90 for i in range(3, 0, -1):
91 asset_url = asset_url = asset_url.replace('_sd1/', '_sd%d/' % i)
92 m3u8_formats = self._extract_m3u8_formats(
93 asset_url, video_id, 'mp4', 'm3u8_native',
94 m3u8_id='hls', fatal=False)
95 formats.extend(m3u8_formats)
96 formats.extend(self._extract_mpd_formats(
97 asset_url.replace('.m3u8', '.mpd'),
98 video_id, mpd_id='dash', fatal=False))
99 if m3u8_formats:
100 break
101 else:
102 formats.extend(self._extract_m3u8_formats(
103 asset_url, video_id, 'mp4', 'm3u8_native',
104 m3u8_id='hls', fatal=False))
105 elif container == 'mp4' or ext == 'mp4':
106 quality = asset.get('video_quality')
107 formats.append({
108 'url': asset_url,
109 'format_id': quality,
110 'quality': quality_key(quality),
111 'ext': ext,
112 })
113 self._sort_formats(formats)
114
115 def get(getter):
116 for src in (data, clip_data):
117 v = try_get(src, getter, compat_str)
118 if v:
119 return v
120
121 return {
122 'id': video_id,
123 'title': title,
124 'description': get(lambda x: x['description']),
125 'duration': int_or_none(clip_data.get('duration')),
126 'series': get(lambda x: x['program']['title']),
127 'formats': formats,
128 'subtitles': subtitles,
129 }