yt_dlp/extractor/screencast.py

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