youtube-dl

Another place where youtube-dl lives on
git clone git://git.oshgnacknak.de/youtube-dl.git
Log | Files | Refs | README | LICENSE

archiveorg.py (3712B)

      1 from __future__ import unicode_literals
      2 
      3 from .common import InfoExtractor
      4 from ..utils import (
      5     clean_html,
      6     extract_attributes,
      7     unified_strdate,
      8     unified_timestamp,
      9 )
     10 
     11 
     12 class ArchiveOrgIE(InfoExtractor):
     13     IE_NAME = 'archive.org'
     14     IE_DESC = 'archive.org videos'
     15     _VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#&]+)'
     16     _TESTS = [{
     17         'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
     18         'md5': '8af1d4cf447933ed3c7f4871162602db',
     19         'info_dict': {
     20             'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect',
     21             'ext': 'ogg',
     22             'title': '1968 Demo - FJCC Conference Presentation Reel #1',
     23             'description': 'md5:da45c349df039f1cc8075268eb1b5c25',
     24             'creator': 'SRI International',
     25             'release_date': '19681210',
     26             'uploader': 'SRI International',
     27             'timestamp': 1268695290,
     28             'upload_date': '20100315',
     29         }
     30     }, {
     31         'url': 'https://archive.org/details/Cops1922',
     32         'md5': '0869000b4ce265e8ca62738b336b268a',
     33         'info_dict': {
     34             'id': 'Cops1922',
     35             'ext': 'mp4',
     36             'title': 'Buster Keaton\'s "Cops" (1922)',
     37             'description': 'md5:43a603fd6c5b4b90d12a96b921212b9c',
     38             'timestamp': 1387699629,
     39             'upload_date': '20131222',
     40         }
     41     }, {
     42         'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
     43         'only_matching': True,
     44     }, {
     45         'url': 'https://archive.org/details/MSNBCW_20131125_040000_To_Catch_a_Predator/',
     46         'only_matching': True,
     47     }]
     48 
     49     def _real_extract(self, url):
     50         video_id = self._match_id(url)
     51         webpage = self._download_webpage(
     52             'http://archive.org/embed/' + video_id, video_id)
     53 
     54         playlist = None
     55         play8 = self._search_regex(
     56             r'(<[^>]+\bclass=["\']js-play8-playlist[^>]+>)', webpage,
     57             'playlist', default=None)
     58         if play8:
     59             attrs = extract_attributes(play8)
     60             playlist = attrs.get('value')
     61         if not playlist:
     62             # Old jwplayer fallback
     63             playlist = self._search_regex(
     64                 r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\)",
     65                 webpage, 'jwplayer playlist', default='[]')
     66         jwplayer_playlist = self._parse_json(playlist, video_id, fatal=False)
     67         if jwplayer_playlist:
     68             info = self._parse_jwplayer_data(
     69                 {'playlist': jwplayer_playlist}, video_id, base_url=url)
     70         else:
     71             # HTML5 media fallback
     72             info = self._parse_html5_media_entries(url, webpage, video_id)[0]
     73             info['id'] = video_id
     74 
     75         def get_optional(metadata, field):
     76             return metadata.get(field, [None])[0]
     77 
     78         metadata = self._download_json(
     79             'http://archive.org/details/' + video_id, video_id, query={
     80                 'output': 'json',
     81             })['metadata']
     82         info.update({
     83             'title': get_optional(metadata, 'title') or info.get('title'),
     84             'description': clean_html(get_optional(metadata, 'description')),
     85         })
     86         if info.get('_type') != 'playlist':
     87             creator = get_optional(metadata, 'creator')
     88             info.update({
     89                 'creator': creator,
     90                 'release_date': unified_strdate(get_optional(metadata, 'date')),
     91                 'uploader': get_optional(metadata, 'publisher') or creator,
     92                 'timestamp': unified_timestamp(get_optional(metadata, 'publicdate')),
     93                 'language': get_optional(metadata, 'language'),
     94             })
     95         return info