Merge branch 'vimeo' of ssh://github.com/rbrito/youtube-dl into vimeo

[youtube-dl] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index 5a68a2ee9a169039b4ced962d12b5511af7844d7..782372688918ba638206e8a755e849f1ee7527bd 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -1724,7 +1724,7 @@ class VimeoIE(InfoExtractor):
        """Information extractor for vimeo.com."""
 
        # _VALID_URL matches Vimeo URLs
-       _VALID_URL = r'(?:http://)?vimeo\.com/([0-9]+)'
+       _VALID_URL = r'(?:http://)?(?:(?:www|player).)?vimeo\.com/(?:video/)?([0-9]+)'
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
@@ -1765,8 +1765,12 @@ class VimeoIE(InfoExtractor):
                        self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
                        return
 
-               # Extract uploader and title from webpage
+               # Now we begin extracting as much information as we can from what we
+               # retrieved. First we extract the information common to all extractors,
+               # and latter we extract those that are Vimeo specific.
                self.report_extraction(video_id)
+
+               # Extract title
                mobj = re.search(r'<caption>(.*?)</caption>', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract video title')
@@ -1774,6 +1778,7 @@ class VimeoIE(InfoExtractor):
                video_title = mobj.group(1).decode('utf-8')
                simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
 
+               # Extract uploader
                mobj = re.search(r'<uploader_url>http://vimeo.com/(.*?)</uploader_url>', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract video uploader')
@@ -1796,14 +1801,14 @@ class VimeoIE(InfoExtractor):
                # if not video_description: video_description = 'No description available.'
                video_description = 'Foo.'
 
-               # Extract request signature
+               # Vimeo specific: extract request signature
                mobj = re.search(r'<request_signature>(.*?)</request_signature>', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract request signature')
                        return
                sig = mobj.group(1).decode('utf-8')
 
-               # Extract request signature expiration
+               # Vimeo specific: Extract request signature expiration
                mobj = re.search(r'<request_signature_expires>(.*?)</request_signature_expires>', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract request signature expiration')