Merge remote-tracking branch 'knagano/master'

pull/2/head
Philipp Hagemeister 13 years ago
commit 50bdd8a9e7

@ -1523,6 +1523,7 @@ class DailymotionIE(InfoExtractor):
# Retrieve video webpage to extract further information # Retrieve video webpage to extract further information
request = urllib2.Request(url) request = urllib2.Request(url)
request.add_header('Cookie', 'family_filter=off')
try: try:
self.report_download_webpage(video_id) self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read() webpage = urllib2.urlopen(request).read()
@ -1532,25 +1533,29 @@ class DailymotionIE(InfoExtractor):
# Extract URL, uploader and title from webpage # Extract URL, uploader and title from webpage
self.report_extraction(video_id) self.report_extraction(video_id)
mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage) mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL') self._downloader.trouble(u'ERROR: unable to extract media URL')
return return
mediaURL = urllib.unquote(mobj.group(1)) sequence = urllib.unquote(mobj.group(1))
mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '')
# if needed add http://www.dailymotion.com/ if relative URL # if needed add http://www.dailymotion.com/ if relative URL
video_url = mediaURL video_url = mediaURL
# '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>' mobj = re.search(r'(?im)<title>Dailymotion\s*-\s*(.+)\s*-\s*[^<]+?</title>', webpage)
mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract title') self._downloader.trouble(u'ERROR: unable to extract title')
return return
video_title = mobj.group(1).decode('utf-8') video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title) video_title = sanitize_title(video_title)
mobj = re.search(r'(?im)<Attribute name="owner">(.+?)</Attribute>', webpage) mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname') self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return return

Loading…
Cancel
Save