youtube_dl/extractor/malltv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import merge_dicts
   8
   9
  10 class MallTVIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?mall\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
  12     _TESTS = [{
  13         'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
  14         'md5': '1c4a37f080e1f3023103a7b43458e518',
  15         'info_dict': {
  16             'id': 't0zzt0',
  17             'display_id': '18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
  18             'ext': 'mp4',
  19             'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?',
  20             'description': 'md5:25fc0ec42a72ba602b602c683fa29deb',
  21             'duration': 216,
  22             'timestamp': 1538870400,
  23             'upload_date': '20181007',
  24             'view_count': int,
  25         }
  26     }, {
  27         'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
  28         'only_matching': True,
  29     }]
  30
  31     def _real_extract(self, url):
  32         display_id = self._match_id(url)
  33
  34         webpage = self._download_webpage(
  35             url, display_id, headers=self.geo_verification_headers())
  36
  37         SOURCE_RE = r'(<source[^>]+\bsrc=(?:(["\'])(?:(?!\2).)+|[^\s]+)/(?P<id>[\da-z]+)/index)\b'
  38         video_id = self._search_regex(
  39             SOURCE_RE, webpage, 'video id', group='id')
  40
  41         media = self._parse_html5_media_entries(
  42             url, re.sub(SOURCE_RE, r'\1.m3u8', webpage), video_id,
  43             m3u8_id='hls', m3u8_entry_protocol='m3u8_native')[0]
  44
  45         info = self._search_json_ld(webpage, video_id, default={})
  46
  47         return merge_dicts(media, info, {
  48             'id': video_id,
  49             'display_id': display_id,
  50             'title': self._og_search_title(webpage, default=None) or display_id,
  51             'description': self._og_search_description(webpage, default=None),
  52             'thumbnail': self._og_search_thumbnail(webpage, default=None),
  53         })