Release 2011.12.15

Dailymotion: Use og:title instead of <title> to find title (Closes: #253 )
2011-12-15 20:32:37 +01:00 · 2011-12-15 20:32:05 +01:00
3 changed files with 13 additions and 9 deletions
--- a/2
+++ b/2
@@ -1 +1 @@
-2011.12.08
+2011.12.15
--- a/10
+++ b/10
@@ -18,7 +18,7 @@ __author__  = (
 	)

 __license__ = 'Public Domain'
-__version__ = '2011.12.08'
+__version__ = '2011.12.15'

 UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'

@@ -1591,6 +1591,8 @@ class DailymotionIE(InfoExtractor):
 		self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)

 	def _real_extract(self, url):
+		htmlParser = HTMLParser.HTMLParser()
+		
 		# Extract id and simplified title from URL
 		mobj = re.match(self._VALID_URL, url)
 		if mobj is None:
@@ -1601,7 +1603,6 @@ class DailymotionIE(InfoExtractor):
 		self._downloader.increment_downloads()
 		video_id = mobj.group(1)

-		simple_title = mobj.group(2).decode('utf-8')
 		video_extension = 'flv'

 		# Retrieve video webpage to extract further information
@@ -1631,12 +1632,13 @@ class DailymotionIE(InfoExtractor):

 		video_url = mediaURL

-		mobj = re.search(r'(?im)<title>\s*(.+)\s*-\s*Video\s+Dailymotion</title>', webpage)
+		mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
 		if mobj is None:
 			self._downloader.trouble(u'ERROR: unable to extract title')
 			return
-		video_title = mobj.group(1).decode('utf-8')
+		video_title = htmlParser.unescape(mobj.group('title')).decode('utf-8')
 		video_title = sanitize_title(video_title)
+		simple_title = _simplify_title(video_title)

 		mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
 		if mobj is None:
--- a/youtube_dl/init.py
+++ b/youtube_dl/init.py
@@ -18,7 +18,7 @@ __author__  = (
 	)

 __license__ = 'Public Domain'
-__version__ = '2011.12.08'
+__version__ = '2011.12.15'

 UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'

@@ -1591,6 +1591,8 @@ class DailymotionIE(InfoExtractor):
 		self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)

 	def _real_extract(self, url):
+		htmlParser = HTMLParser.HTMLParser()
+		
 		# Extract id and simplified title from URL
 		mobj = re.match(self._VALID_URL, url)
 		if mobj is None:
@@ -1601,7 +1603,6 @@ class DailymotionIE(InfoExtractor):
 		self._downloader.increment_downloads()
 		video_id = mobj.group(1)

-		simple_title = mobj.group(2).decode('utf-8')
 		video_extension = 'flv'

 		# Retrieve video webpage to extract further information
@@ -1631,12 +1632,13 @@ class DailymotionIE(InfoExtractor):

 		video_url = mediaURL

-		mobj = re.search(r'(?im)<title>\s*(.+)\s*-\s*Video\s+Dailymotion</title>', webpage)
+		mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
 		if mobj is None:
 			self._downloader.trouble(u'ERROR: unable to extract title')
 			return
-		video_title = mobj.group(1).decode('utf-8')
+		video_title = htmlParser.unescape(mobj.group('title')).decode('utf-8')
 		video_title = sanitize_title(video_title)
+		simple_title = _simplify_title(video_title)

 		mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
 		if mobj is None:
Author	SHA1	Message	Date
Philipp Hagemeister	ba5059dd66	Release 2011.12.15	2011-12-15 20:32:37 +01:00
Philipp Hagemeister	bb8abbbbae	Dailymotion: Use og:title instead of <title> to find title (Closes: #253 )	2011-12-15 20:32:05 +01:00
@@ -1 +1 @@
 .12.08
 .12.15