]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/iprima.py
Update upstream source from tag 'upstream/2019.01.17'
[youtubedl] / youtube_dl / extractor / iprima.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5 import time
6
7 from .common import InfoExtractor
8 from ..utils import (
9 determine_ext,
10 js_to_json,
11 )
12
13
14 class IPrimaIE(InfoExtractor):
15 _VALID_URL = r'https?://(?:[^/]+)\.iprima\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)'
16 _GEO_BYPASS = False
17
18 _TESTS = [{
19 'url': 'http://play.iprima.cz/gondici-s-r-o-33',
20 'info_dict': {
21 'id': 'p136534',
22 'ext': 'mp4',
23 'title': 'Gondíci s. r. o. (34)',
24 'description': 'md5:16577c629d006aa91f59ca8d8e7f99bd',
25 },
26 'params': {
27 'skip_download': True, # m3u8 download
28 },
29 }, {
30 'url': 'http://play.iprima.cz/particka/particka-92',
31 'only_matching': True,
32 }, {
33 # geo restricted
34 'url': 'http://play.iprima.cz/closer-nove-pripady/closer-nove-pripady-iv-1',
35 'only_matching': True,
36 }, {
37 # iframe api.play-backend.iprima.cz
38 'url': 'https://prima.iprima.cz/my-little-pony/mapa-znameni-2-2',
39 'only_matching': True,
40 }, {
41 # iframe prima.iprima.cz
42 'url': 'https://prima.iprima.cz/porady/jak-se-stavi-sen/rodina-rathousova-praha',
43 'only_matching': True,
44 }, {
45 'url': 'http://www.iprima.cz/filmy/desne-rande',
46 'only_matching': True,
47 }, {
48 'url': 'https://zoom.iprima.cz/10-nejvetsich-tajemstvi-zahad/posvatna-mista-a-stavby',
49 'only_matching': True,
50 }, {
51 'url': 'https://krimi.iprima.cz/mraz-0/sebevrazdy',
52 'only_matching': True,
53 }, {
54 'url': 'https://cool.iprima.cz/derava-silnice-nevadi',
55 'only_matching': True,
56 }, {
57 'url': 'https://love.iprima.cz/laska-az-za-hrob/slib-dany-bratrovi',
58 'only_matching': True,
59 }, {
60 'url': 'https://autosalon.iprima.cz/motorsport/7-epizoda-1',
61 'only_matching': True,
62 }]
63
64 def _real_extract(self, url):
65 video_id = self._match_id(url)
66
67 self._set_cookie('play.iprima.cz', 'ott_adult_confirmed', '1')
68
69 webpage = self._download_webpage(url, video_id)
70
71 video_id = self._search_regex(
72 (r'<iframe[^>]+\bsrc=["\'](?:https?:)?//(?:api\.play-backend\.iprima\.cz/prehravac/embedded|prima\.iprima\.cz/[^/]+/[^/]+)\?.*?\bid=(p\d+)',
73 r'data-product="([^"]+)">'),
74 webpage, 'real id')
75
76 playerpage = self._download_webpage(
77 'http://play.iprima.cz/prehravac/init',
78 video_id, note='Downloading player', query={
79 '_infuse': 1,
80 '_ts': round(time.time()),
81 'productId': video_id,
82 }, headers={'Referer': url})
83
84 formats = []
85
86 def extract_formats(format_url, format_key=None, lang=None):
87 ext = determine_ext(format_url)
88 new_formats = []
89 if format_key == 'hls' or ext == 'm3u8':
90 new_formats = self._extract_m3u8_formats(
91 format_url, video_id, 'mp4', entry_protocol='m3u8_native',
92 m3u8_id='hls', fatal=False)
93 elif format_key == 'dash' or ext == 'mpd':
94 return
95 new_formats = self._extract_mpd_formats(
96 format_url, video_id, mpd_id='dash', fatal=False)
97 if lang:
98 for f in new_formats:
99 if not f.get('language'):
100 f['language'] = lang
101 formats.extend(new_formats)
102
103 options = self._parse_json(
104 self._search_regex(
105 r'(?s)(?:TDIPlayerOptions|playerOptions)\s*=\s*({.+?});\s*\]\]',
106 playerpage, 'player options', default='{}'),
107 video_id, transform_source=js_to_json, fatal=False)
108 if options:
109 for key, tracks in options.get('tracks', {}).items():
110 if not isinstance(tracks, list):
111 continue
112 for track in tracks:
113 src = track.get('src')
114 if src:
115 extract_formats(src, key.lower(), track.get('lang'))
116
117 if not formats:
118 for _, src in re.findall(r'src["\']\s*:\s*(["\'])(.+?)\1', playerpage):
119 extract_formats(src)
120
121 if not formats and '>GEO_IP_NOT_ALLOWED<' in playerpage:
122 self.raise_geo_restricted(countries=['CZ'])
123
124 self._sort_formats(formats)
125
126 return {
127 'id': video_id,
128 'title': self._og_search_title(webpage),
129 'thumbnail': self._og_search_thumbnail(webpage),
130 'formats': formats,
131 'description': self._og_search_description(webpage),
132 }