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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import js_to_json
   6
   7
   8 class ScreencastOMaticIE(InfoExtractor):
   9     _VALID_URL = r'https?://screencast-o-matic\.com/watch/(?P<id>[0-9a-zA-Z]+)'
  10     _TEST = {
  11         'url': 'http://screencast-o-matic.com/watch/c2lD3BeOPl',
  12         'md5': '483583cb80d92588f15ccbedd90f0c18',
  13         'info_dict': {
  14             'id': 'c2lD3BeOPl',
  15             'ext': 'mp4',
  16             'title': 'Welcome to 3-4 Philosophy @ DECV!',
  17             'thumbnail': r're:^https?://.*\.jpg$',
  18             'description': 'as the title says! also: some general info re 1) VCE philosophy and 2) distance learning.',
  19             'duration': 369.163,
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         video_id = self._match_id(url)
  25         webpage = self._download_webpage(url, video_id)
  26
  27         jwplayer_data = self._parse_json(
  28             self._search_regex(
  29                 r"(?s)jwplayer\('mp4Player'\).setup\((\{.*?\})\);", webpage, 'setup code'),
  30             video_id, transform_source=js_to_json)
  31
  32         info_dict = self._parse_jwplayer_data(jwplayer_data, video_id, require_title=False)
  33         info_dict.update({
  34             'title': self._og_search_title(webpage),
  35             'description': self._og_search_description(webpage),
  36         })
  37         return info_dict