Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ctvnews.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 orderedSet
   8
   9
  10 class CTVNewsIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?ctvnews\.ca/(?:video\?(?:clip|playlist|bin)Id=|.*?)(?P<id>[0-9.]+)'
  12     _TESTS = [{
  13         'url': 'http://www.ctvnews.ca/video?clipId=901995',
  14         'md5': '10deb320dc0ccb8d01d34d12fc2ea672',
  15         'info_dict': {
  16             'id': '901995',
  17             'ext': 'mp4',
  18             'title': 'Extended: \'That person cannot be me\' Johnson says',
  19             'description': 'md5:958dd3b4f5bbbf0ed4d045c790d89285',
  20             'timestamp': 1467286284,
  21             'upload_date': '20160630',
  22         }
  23     }, {
  24         'url': 'http://www.ctvnews.ca/video?playlistId=1.2966224',
  25         'info_dict':
  26         {
  27             'id': '1.2966224',
  28         },
  29         'playlist_mincount': 19,
  30     }, {
  31         'url': 'http://www.ctvnews.ca/video?binId=1.2876780',
  32         'info_dict':
  33         {
  34             'id': '1.2876780',
  35         },
  36         'playlist_mincount': 100,
  37     }, {
  38         'url': 'http://www.ctvnews.ca/1.810401',
  39         'only_matching': True,
  40     }, {
  41         'url': 'http://www.ctvnews.ca/canadiens-send-p-k-subban-to-nashville-in-blockbuster-trade-1.2967231',
  42         'only_matching': True,
  43     }]
  44
  45     def _real_extract(self, url):
  46         page_id = self._match_id(url)
  47
  48         def ninecninemedia_url_result(clip_id):
  49             return {
  50                 '_type': 'url_transparent',
  51                 'id': clip_id,
  52                 'url': '9c9media:ctvnews_web:%s' % clip_id,
  53                 'ie_key': 'NineCNineMedia',
  54             }
  55
  56         if page_id.isdigit():
  57             return ninecninemedia_url_result(page_id)
  58         else:
  59             webpage = self._download_webpage('http://www.ctvnews.ca/%s' % page_id, page_id, query={
  60                 'ot': 'example.AjaxPageLayout.ot',
  61                 'maxItemsPerPage': 1000000,
  62             })
  63             entries = [ninecninemedia_url_result(clip_id) for clip_id in orderedSet(
  64                 re.findall(r'clip\.id\s*=\s*(\d+);', webpage))]
  65             return self.playlist_result(entries, page_id)