diff options
| author | Philipp Hagemeister <phihag@phihag.de> | 2014-11-04 23:26:23 +0100 |
|---|---|---|
| committer | Philipp Hagemeister <phihag@phihag.de> | 2014-11-04 23:26:23 +0100 |
| commit | 11fba1751d5a43491254a3f54fcd0903a40d1a35 (patch) | |
| tree | 2f6356b3152c3aae08d8a7ad5f8da7b990f45688 | |
| parent | 12ea2f30cfcc381eb46cc99a0a4c3d468fe732d1 (diff) | |
[imdb] Simplify
| -rw-r--r-- | youtube_dl/extractor/imdb.py | 12 |
1 files changed, 5 insertions, 7 deletions
diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 4536db3bf..6108ed552 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -6,7 +6,6 @@ import json from .common import InfoExtractor from ..utils import ( compat_urlparse, - get_element_by_attribute, ) @@ -27,10 +26,11 @@ class ImdbIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id) - descr = get_element_by_attribute('itemprop', 'description', webpage) + descr = self._html_search_regex( + r'(?s)<span itemprop="description">(.*?)</span>', + webpage, 'description', fatal=False) available_formats = re.findall( r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage, flags=re.MULTILINE) @@ -73,9 +73,7 @@ class ImdbListIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - list_id = mobj.group('id') - + list_id = self._match_id(url) webpage = self._download_webpage(url, list_id) entries = [ self.url_result('http://www.imdb.com' + m, 'Imdb') |