yt_dlp/extractor/screencast.py

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