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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import (
   6     compat_parse_qs,
   7     compat_urllib_request,
   8 )
   9 from ..utils import (
  10     ExtractorError,
  11 )
  12
  13
  14 class ScreencastIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?screencast\.com/t/(?P<id>[a-zA-Z0-9]+)'
  16     _TESTS = [{
  17         'url': 'http://www.screencast.com/t/3ZEjQXlT',
  18         'md5': '917df1c13798a3e96211dd1561fded83',
  19         'info_dict': {
  20             'id': '3ZEjQXlT',
  21             'ext': 'm4v',
  22             'title': 'Color Measurement with Ocean Optics Spectrometers',
  23             'description': 'md5:240369cde69d8bed61349a199c5fb153',
  24             'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
  25         }
  26     }, {
  27         'url': 'http://www.screencast.com/t/V2uXehPJa1ZI',
  28         'md5': 'e8e4b375a7660a9e7e35c33973410d34',
  29         'info_dict': {
  30             'id': 'V2uXehPJa1ZI',
  31             'ext': 'mov',
  32             'title': 'The Amadeus Spectrometer',
  33             'description': 're:^In this video, our friends at.*To learn more about Amadeus, visit',
  34             'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
  35         }
  36     }, {
  37         'url': 'http://www.screencast.com/t/aAB3iowa',
  38         'md5': 'dedb2734ed00c9755761ccaee88527cd',
  39         'info_dict': {
  40             'id': 'aAB3iowa',
  41             'ext': 'mp4',
  42             'title': 'Google Earth Export',
  43             'description': 'Provides a demo of a CommunityViz export to Google Earth, one of the 3D viewing options.',
  44             'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
  45         }
  46     }, {
  47         'url': 'http://www.screencast.com/t/X3ddTrYh',
  48         'md5': '669ee55ff9c51988b4ebc0877cc8b159',
  49         'info_dict': {
  50             'id': 'X3ddTrYh',
  51             'ext': 'wmv',
  52             'title': 'Toolkit 6 User Group Webinar (2014-03-04) - Default Judgment and First Impression',
  53             'description': 'md5:7b9f393bc92af02326a5c5889639eab0',
  54             'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
  55         }
  56     }, {
  57         'url': 'http://screencast.com/t/aAB3iowa',
  58         'only_matching': True,
  59     }]
  60
  61     def _real_extract(self, url):
  62         video_id = self._match_id(url)
  63         webpage = self._download_webpage(url, video_id)
  64
  65         video_url = self._html_search_regex(
  66             r'<embed name="Video".*?src="([^"]+)"', webpage,
  67             'QuickTime embed', default=None)
  68
  69         if video_url is None:
  70             flash_vars_s = self._html_search_regex(
  71                 r'<param name="flashVars" value="([^"]+)"', webpage, 'flash vars',
  72                 default=None)
  73             if not flash_vars_s:
  74                 flash_vars_s = self._html_search_regex(
  75                     r'<param name="initParams" value="([^"]+)"', webpage, 'flash vars',
  76                     default=None)
  77                 if flash_vars_s:
  78                     flash_vars_s = flash_vars_s.replace(',', '&')
  79             if flash_vars_s:
  80                 flash_vars = compat_parse_qs(flash_vars_s)
  81                 video_url_raw = compat_urllib_request.quote(
  82                     flash_vars['content'][0])
  83                 video_url = video_url_raw.replace('http%3A', 'http:')
  84
  85         if video_url is None:
  86             video_meta = self._html_search_meta(
  87                 'og:video', webpage, default=None)
  88             if video_meta:
  89                 video_url = self._search_regex(
  90                     r'src=(.*?)(?:$|&)', video_meta,
  91                     'meta tag video URL', default=None)
  92
  93         if video_url is None:
  94             video_url = self._html_search_regex(
  95                 r'MediaContentUrl["\']\s*:(["\'])(?P<url>(?:(?!\1).)+)\1',
  96                 webpage, 'video url', default=None, group='url')
  97
  98         if video_url is None:
  99             video_url = self._html_search_meta(
 100                 'og:video', webpage, default=None)
 101
 102         if video_url is None:
 103             raise ExtractorError('Cannot find video')
 104
 105         title = self._og_search_title(webpage, default=None)
 106         if title is None:
 107             title = self._html_search_regex(
 108                 [r'<b>Title:</b> ([^<]+)</div>',
 109                  r'class="tabSeperator">></span><span class="tabText">(.+?)<',
 110                  r'<title>([^<]+)</title>'],
 111                 webpage, 'title')
 112         thumbnail = self._og_search_thumbnail(webpage)
 113         description = self._og_search_description(webpage, default=None)
 114         if description is None:
 115             description = self._html_search_meta('description', webpage)
 116
 117         return {
 118             'id': video_id,
 119             'url': video_url,
 120             'title': title,
 121             'description': description,
 122             'thumbnail': thumbnail,
 123         }