Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/cartoonnetwork.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .turner import TurnerBaseIE
   5 from ..utils import int_or_none
   6
   7
   8 class CartoonNetworkIE(TurnerBaseIE):
   9     _VALID_URL = r'https?://(?:www\.)?cartoonnetwork\.com/video/(?:[^/]+/)+(?P<id>[^/?#]+)-(?:clip|episode)\.html'
  10     _TEST = {
  11         'url': 'https://www.cartoonnetwork.com/video/ben-10/how-to-draw-upgrade-episode.html',
  12         'info_dict': {
  13             'id': '6e3375097f63874ebccec7ef677c1c3845fa850e',
  14             'ext': 'mp4',
  15             'title': 'How to Draw Upgrade',
  16             'description': 'md5:2061d83776db7e8be4879684eefe8c0f',
  17         },
  18         'params': {
  19             # m3u8 download
  20             'skip_download': True,
  21         },
  22     }
  23
  24     def _real_extract(self, url):
  25         display_id = self._match_id(url)
  26         webpage = self._download_webpage(url, display_id)
  27
  28         def find_field(global_re, name, content_re=None, value_re='[^"]+', fatal=False):
  29             metadata_re = ''
  30             if content_re:
  31                 metadata_re = r'|video_metadata\.content_' + content_re
  32             return self._search_regex(
  33                 r'(?:_cnglobal\.currentVideo\.%s%s)\s*=\s*"(%s)";' % (global_re, metadata_re, value_re),
  34                 webpage, name, fatal=fatal)
  35
  36         media_id = find_field('mediaId', 'media id', 'id', '[0-9a-f]{40}', True)
  37         title = find_field('episodeTitle', 'title', '(?:episodeName|name)', fatal=True)
  38
  39         info = self._extract_ngtv_info(
  40             media_id, {'networkId': 'cartoonnetwork'}, {
  41                 'url': url,
  42                 'site_name': 'CartoonNetwork',
  43                 'auth_required': find_field('authType', 'auth type') != 'unauth',
  44             })
  45
  46         series = find_field(
  47             'propertyName', 'series', 'showName') or self._html_search_meta('partOfSeries', webpage)
  48         info.update({
  49             'id': media_id,
  50             'display_id': display_id,
  51             'title': title,
  52             'description': self._html_search_meta('description', webpage),
  53             'series': series,
  54             'episode': title,
  55         })
  56
  57         for field in ('season', 'episode'):
  58             field_name = field + 'Number'
  59             info[field + '_number'] = int_or_none(find_field(
  60                 field_name, field + ' number', value_re=r'\d+') or self._html_search_meta(field_name, webpage))
  61
  62         return info