diff options
| author | Philipp Hagemeister <phihag@phihag.de> | 2015-01-07 11:21:40 +0100 |
|---|---|---|
| committer | Philipp Hagemeister <phihag@phihag.de> | 2015-01-08 16:14:49 +0100 |
| commit | 99673f04bc5b179241d121cf2aa50f25b6b1c7d0 (patch) | |
| tree | 5cea7ad8a6f320349e02bf3d0bc12724b9fa3f81 | |
| parent | e9a537774d8671fd476fd5930bfe3c6f1b17c307 (diff) | |
| download | youtube-dl-99673f04bc5b179241d121cf2aa50f25b6b1c7d0.tar.gz youtube-dl-99673f04bc5b179241d121cf2aa50f25b6b1c7d0.tar.xz youtube-dl-99673f04bc5b179241d121cf2aa50f25b6b1c7d0.zip | |
[washingtonpost] Modernize and correct test case
| -rw-r--r-- | youtube_dl/extractor/washingtonpost.py | 11 |
1 files changed, 5 insertions, 6 deletions
diff --git a/youtube_dl/extractor/washingtonpost.py b/youtube_dl/extractor/washingtonpost.py index 88bbbb219..c17bebd6e 100644 --- a/youtube_dl/extractor/washingtonpost.py +++ b/youtube_dl/extractor/washingtonpost.py @@ -10,14 +10,14 @@ from ..utils import ( class WashingtonPostIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?washingtonpost\.com/.*?/(?P<id>[^/]+)/(?:$|[?#])' + _VALID_URL = r'https?://(?:www\.)?washingtonpost\.com/.*?/(?P<id>[^/]+)/(?:$|[?#])' _TEST = { 'url': 'http://www.washingtonpost.com/sf/national/2014/03/22/sinkhole-of-bureaucracy/', 'info_dict': { 'title': 'Sinkhole of bureaucracy', }, 'playlist': [{ - 'md5': 'c3f4b4922ffa259243f68e928db2db8c', + 'md5': '79132cc09ec5309fa590ae46e4cc31bc', 'info_dict': { 'id': 'fc433c38-b146-11e3-b8b3-44b1d1cd4c1f', 'ext': 'mp4', @@ -29,7 +29,7 @@ class WashingtonPostIE(InfoExtractor): 'upload_date': '20140322', }, }, { - 'md5': 'f645a07652c2950cd9134bb852c5f5eb', + 'md5': 'e1d5734c06865cc504ad99dc2de0d443', 'info_dict': { 'id': '41255e28-b14a-11e3-b8b3-44b1d1cd4c1f', 'ext': 'mp4', @@ -44,10 +44,9 @@ class WashingtonPostIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - page_id = mobj.group('id') - + page_id = self._match_id(url) webpage = self._download_webpage(url, page_id) + title = self._og_search_title(webpage) uuids = re.findall(r'data-video-uuid="([^"]+)"', webpage) entries = [] |