aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/criterion.py
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-07-13 12:18:03 +0200
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-07-13 12:18:03 +0200
commit7fd930c0c8a33d452027f3844962ab83ee08d807 (patch)
tree29142133f627e30e192b2fa2d517925ff5fcc536 /youtube_dl/extractor/criterion.py
parent2e78b2beadcdb1fc2cfa60789bb501cccd5dbce5 (diff)
parent2d5a8b55129b1dc10f9e789875b46742c8f303af (diff)
Merge pull request #1036 from yasoob/master
Added an IE and test for Criterion videos (closes #1035).
Diffstat (limited to 'youtube_dl/extractor/criterion.py')
-rw-r--r--youtube_dl/extractor/criterion.py40
1 files changed, 40 insertions, 0 deletions
diff --git a/youtube_dl/extractor/criterion.py b/youtube_dl/extractor/criterion.py
new file mode 100644
index 000000000..a149d2900
--- /dev/null
+++ b/youtube_dl/extractor/criterion.py
@@ -0,0 +1,40 @@
+# -*- coding: utf-8 -*-
+
+import re
+
+from .common import InfoExtractor
+
+class CriterionIE(InfoExtractor):
+ _VALID_URL = r'http://www.criterion.com/films/(.*)'
+ _TEST = {
+ u'url': u'http://www.criterion.com/films/184-le-samourai',
+ u'file': u'184.mp4',
+ u'md5': u'bc51beba55685509883a9a7830919ec3',
+ u'info_dict': {
+ u"title": u"Le Samouraï",
+ u"description" : u"In a career-defining performance, Alain Delon plays a contract killer with samurai instincts. A razor-sharp cocktail of 1940s American gangster cinema and 1960s French pop culture, maverick director Jean-Pierre Melville&#x27;s masterpiece _Le Samouraï_ defines cool. "
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group(1).split('-')[0]
+ webpage = self._download_webpage(url, video_id)
+
+ final_url = self._search_regex(r'so.addVariable\("videoURL", "(.+?)"\)\;',
+ webpage, 'video url')
+ title = self._search_regex(r'<meta content="(.+?)" property="og:title" />',
+ webpage, 'video title')
+ description = self._search_regex(r'<meta name="description" content="(.+?)" />',
+ webpage, 'video description')
+ thumbnail = self._search_regex(r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
+ webpage, 'thumbnail url')
+ ext = final_url.split('.')[-1]
+
+ return {'id': video_id,
+ 'url' : final_url,
+ 'title': title,
+ 'ext': ext,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ }