diff options
| author | Remita Amine <remitamine@gmail.com> | 2020-02-03 13:20:20 +0100 | 
|---|---|---|
| committer | Remita Amine <remitamine@gmail.com> | 2020-02-03 13:20:36 +0100 | 
| commit | 705b1cda9981153f4ced3adc025a8bbfea6caff9 (patch) | |
| tree | 5c31ca08bde43fcc35eeef70da10d7932608ddb9 | |
| parent | 7d55b62ff2e9f3666e6cc4daa969647b917331cd (diff) | |
[thisoldhouse] fix extraction(closes #23951)
| -rw-r--r-- | youtube_dl/extractor/thisoldhouse.py | 33 | 
1 files changed, 16 insertions, 17 deletions
diff --git a/youtube_dl/extractor/thisoldhouse.py b/youtube_dl/extractor/thisoldhouse.py index 6ab147ad7..387f955ee 100644 --- a/youtube_dl/extractor/thisoldhouse.py +++ b/youtube_dl/extractor/thisoldhouse.py @@ -2,43 +2,42 @@  from __future__ import unicode_literals  from .common import InfoExtractor -from ..compat import compat_str -from ..utils import try_get  class ThisOldHouseIE(InfoExtractor): -    _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode)/(?P<id>[^/?#]+)' +    _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode|(?:[^/]+/)?\d+)/(?P<id>[^/?#]+)'      _TESTS = [{          'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench', -        'md5': '568acf9ca25a639f0c4ff905826b662f',          'info_dict': { -            'id': '2REGtUDQ', +            'id': '5dcdddf673c3f956ef5db202',              'ext': 'mp4',              'title': 'How to Build a Storage Bench',              'description': 'In the workshop, Tom Silva and Kevin O\'Connor build a storage bench for an entryway.',              'timestamp': 1442548800,              'upload_date': '20150918', -        } +        }, +        'params': { +            'skip_download': True, +        },      }, {          'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins',          'only_matching': True,      }, {          'url': 'https://www.thisoldhouse.com/tv-episode/ask-toh-shelf-rough-electric',          'only_matching': True, +    }, { +        'url': 'https://www.thisoldhouse.com/furniture/21017078/how-to-build-a-storage-bench', +        'only_matching': True, +    }, { +        'url': 'https://www.thisoldhouse.com/21113884/s41-e13-paradise-lost', +        'only_matching': True,      }] +    _ZYPE_TMPL = 'https://player.zype.com/embed/%s.html?api_key=hsOk_yMSPYNrT22e9pu8hihLXjaZf0JW5jsOWv4ZqyHJFvkJn6rtToHl09tbbsbe'      def _real_extract(self, url):          display_id = self._match_id(url)          webpage = self._download_webpage(url, display_id)          video_id = self._search_regex( -            (r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', -             r'id=(["\'])inline-video-player-(?P<id>(?:(?!\1).)+)\1'), -            webpage, 'video id', default=None, group='id') -        if not video_id: -            drupal_settings = self._parse_json(self._search_regex( -                r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', -                webpage, 'drupal settings'), display_id) -            video_id = try_get( -                drupal_settings, lambda x: x['jwplatform']['video_id'], -                compat_str) or list(drupal_settings['comScore'])[0] -        return self.url_result('jwplatform:' + video_id, 'JWPlatform', video_id) +            r'<iframe[^>]+src=[\'"](?:https?:)?//thisoldhouse\.chorus\.build/videos/zype/([0-9a-f]{24})', +            webpage, 'video id') +        return self.url_result(self._ZYPE_TMPL % video_id, 'Zype', video_id)  | 
