Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-02-03 18:32:52 +08:00
Code Issues Releases Wiki Activity

Changed GenericIE so all regex matches on a page are used to find video urls

Browse Source
This commit is contained in:
Jonathon Padfield 2012-02-11 16:17:23 +11:00
parent 99d46e8c27
commit 0269764b07
1 changed files with 34 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

66
youtube-dl
View File

@ -2170,27 +2170,15 @@ class GenericIE(InfoExtractor):
self.report_extraction(video_id)
# Start with something easy: JW Player in SWFObject
mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
if mobj is None:
matches = [mobj for mobj in re.finditer(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)]
if len(matches) == 0:
# Broaden the search a little bit
mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
if mobj is None:
matches = [mobj for mobj in re.finditer(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)]
if len(matches) == 0:
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
# It's possible that one of the regexes
# matched, but returned an empty group:
if mobj.group(1) is None:
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
video_url = urllib.unquote(mobj.group(1))
video_id = os.path.basename(video_url)
# here's a fun little line of code for you:
video_extension = os.path.splitext(video_id)[1][1:]
video_id = os.path.splitext(video_id)[0]
# it's tempting to parse this further, but you would
# have to take into account all the variations like
# Video Title - Site Name
@ -2212,21 +2200,35 @@ class GenericIE(InfoExtractor):
return
video_uploader = mobj.group(1).decode('utf-8')
try:
# Process video information
self._downloader.process_info({
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader,
'upload_date': u'NA',
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
'format': u'NA',
'player_url': None,
})
except UnavailableVideoError, err:
self._downloader.trouble(u'\nERROR: unable to download video')
for mobj in matches:
# It's possible that one of the regexes
# matched, but returned an empty group:
if mobj.group(1) is None:
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
continue
video_url = urllib.unquote(mobj.group(1))
video_id = os.path.basename(video_url)
# here's a fun little line of code for you:
video_extension = os.path.splitext(video_id)[1][1:]
video_id = os.path.splitext(video_id)[0]
try:
# Process video information
self._downloader.process_info({
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader,
'upload_date': u'NA',
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
'format': u'NA',
'player_url': None,
})
except UnavailableVideoError, err:
self._downloader.trouble(u'\nERROR: unable to download video')
class YoutubeSearchIE(InfoExtractor):