_ Git - youtube-dl/blob - 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?://(?:play|prima|www)\.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
  49     def _real_extract(self, url):
  50         video_id = self._match_id(url)
  51
  52         self._set_cookie('play.iprima.cz', 'ott_adult_confirmed', '1')
  53
  54         webpage = self._download_webpage(url, video_id)
  55
  56         video_id = self._search_regex(
  57             (r'<iframe[^>]+\bsrc=["\'](?:https?:)?//(?:api\.play-backend\.iprima\.cz/prehravac/embedded|prima\.iprima\.cz/[^/]+/[^/]+)\?.*?\bid=(p\d+)',
  58              r'data-product="([^"]+)">'),
  59             webpage, 'real id')
  60
  61         playerpage = self._download_webpage(
  62             'http://play.iprima.cz/prehravac/init',
  63             video_id, note='Downloading player', query={
  64                 '_infuse': 1,
  65                 '_ts': round(time.time()),
  66                 'productId': video_id,
  67             }, headers={'Referer': url})
  68
  69         formats = []
  70
  71         def extract_formats(format_url, format_key=None, lang=None):
  72             ext = determine_ext(format_url)
  73             new_formats = []
  74             if format_key == 'hls' or ext == 'm3u8':
  75                 new_formats = self._extract_m3u8_formats(
  76                     format_url, video_id, 'mp4', entry_protocol='m3u8_native',
  77                     m3u8_id='hls', fatal=False)
  78             elif format_key == 'dash' or ext == 'mpd':
  79                 return
  80                 new_formats = self._extract_mpd_formats(
  81                     format_url, video_id, mpd_id='dash', fatal=False)
  82             if lang:
  83                 for f in new_formats:
  84                     if not f.get('language'):
  85                         f['language'] = lang
  86             formats.extend(new_formats)
  87
  88         options = self._parse_json(
  89             self._search_regex(
  90                 r'(?s)(?:TDIPlayerOptions|playerOptions)\s*=\s*({.+?});\s*\]\]',
  91                 playerpage, 'player options', default='{}'),
  92             video_id, transform_source=js_to_json, fatal=False)
  93         if options:
  94             for key, tracks in options.get('tracks', {}).items():
  95                 if not isinstance(tracks, list):
  96                     continue
  97                 for track in tracks:
  98                     src = track.get('src')
  99                     if src:
 100                         extract_formats(src, key.lower(), track.get('lang'))
 101
 102         if not formats:
 103             for _, src in re.findall(r'src["\']\s*:\s*(["\'])(.+?)\1', playerpage):
 104                 extract_formats(src)
 105
 106         if not formats and '>GEO_IP_NOT_ALLOWED<' in playerpage:
 107             self.raise_geo_restricted(countries=['CZ'])
 108
 109         self._sort_formats(formats)
 110
 111         return {
 112             'id': video_id,
 113             'title': self._og_search_title(webpage),
 114             'thumbnail': self._og_search_thumbnail(webpage),
 115             'formats': formats,
 116             'description': self._og_search_description(webpage),
 117         }