X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/af478477605bdf3f5d57562035885cfee905f379..17ef2938f1a30eb959e17d4d1325bd9355ca05c5:/youtube_dl/extractor/imdb.py
diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py
index 7cee505..f29df36 100644
--- a/youtube_dl/extractor/imdb.py
+++ b/youtube_dl/extractor/imdb.py
@@ -4,9 +4,8 @@ import re
import json
from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
compat_urlparse,
- get_element_by_attribute,
)
@@ -17,7 +16,6 @@ class ImdbIE(InfoExtractor):
_TEST = {
'url': 'http://www.imdb.com/video/imdb/vi2524815897',
- 'md5': '9f34fa777ade3a6e57a054fdbcb3a068',
'info_dict': {
'id': '2524815897',
'ext': 'mp4',
@@ -27,10 +25,11 @@ 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)(.*?)',
+ webpage, 'description', fatal=False)
available_formats = re.findall(
r'case \'(?P.*?)\' :$\s+url = \'(?P.*?)\'', webpage,
flags=re.MULTILINE)
@@ -63,11 +62,17 @@ class ImdbListIE(InfoExtractor):
IE_NAME = 'imdb:list'
IE_DESC = 'Internet Movie Database lists'
_VALID_URL = r'http://www\.imdb\.com/list/(?P[\da-zA-Z_-]{11})'
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- list_id = mobj.group('id')
+ _TEST = {
+ 'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
+ 'info_dict': {
+ 'id': 'JFs9NWw6XI0',
+ 'title': 'March 23, 2012 Releases',
+ },
+ 'playlist_count': 7,
+ }
+ def _real_extract(self, url):
+ list_id = self._match_id(url)
webpage = self._download_webpage(url, list_id)
entries = [
self.url_result('http://www.imdb.com' + m, 'Imdb')