_ Git - youtube-dl/blob - youtube_dl/extractor/screencast.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 (
   8     compat_parse_qs,
   9     compat_urllib_request,
  10 )
  11
  12
  13 class ScreencastIE(InfoExtractor):
  14     _VALID_URL = r'https?://www\.screencast\.com/t/(?P<id>[a-zA-Z0-9]+)'
  15     _TEST = {
  16         'url': 'http://www.screencast.com/t/3ZEjQXlT',
  17         'md5': '917df1c13798a3e96211dd1561fded83',
  18         'info_dict': {
  19             'id': '3ZEjQXlT',
  20             'ext': 'm4v',
  21             'title': 'Color Measurement with Ocean Optics Spectrometers',
  22             'description': 'md5:240369cde69d8bed61349a199c5fb153',
  23             'thumbnail': 're:^https?://.*\.jpg$'
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         video_id = mobj.group('id')
  30         webpage = self._download_webpage(url, video_id)
  31
  32         flash_vars_s = self._html_search_regex(
  33             r'<param name="flashVars" value="([^"]+)"', webpage, 'flash vars')
  34         flash_vars = compat_parse_qs(flash_vars_s)
  35
  36         thumbnail = flash_vars.get('thumb', [None])[0]
  37         video_url_raw = compat_urllib_request.quote(flash_vars['content'][0])
  38         video_url = video_url_raw.replace('http%3A', 'http:')
  39         title = self._og_search_title(webpage)
  40         description = self._og_search_description(webpage)
  41
  42         return {
  43             'id': video_id,
  44             'url': video_url,
  45             'title': title,
  46             'description': description,
  47             'thumbnail': thumbnail,
  48         }