1 # -*- coding: utf-8 -*-
3 # gPodder - A media aggregator and podcast client
4 # Copyright (c) 2005-2008 Thomas Perl and the gPodder Team
6 # gPodder is free software; you can redistribute it and/or modify
7 # it under the terms of the GNU General Public License as published by
8 # the Free Software Foundation; either version 3 of the License, or
9 # (at your option) any later version.
11 # gPodder is distributed in the hope that it will be useful,
12 # but WITHOUT ANY WARRANTY; without even the implied warranty of
13 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 # GNU General Public License for more details.
16 # You should have received a copy of the GNU General Public License
17 # along with this program. If not, see <http://www.gnu.org/licenses/>.
19 # resolver.py -- YouTube and related magic
20 # Justin Forest <justin.forest@gmail.com> 2008-10-13
25 # * Support for Vimeo, maybe blip.tv and others.
32 from xml
.sax
import saxutils
33 from gpodder
.liblogger
import log
34 from gpodder
.util
import proxy_request
36 def get_real_download_url(url
, proxy
=None):
37 r1
= re
.compile('http://(?:[a-z]+\.)?youtube\.com/v/(.*)\.swf', re
.IGNORECASE
).match(url
)
39 page
= proxy_request('http://www.youtube.com/watch?v=' + r1
.group(1), proxy
, method
='GET').read()
41 r2
= re
.compile('.*"t"\:\s+"([^"]+)".*').search(page
)
43 next
= 'http://www.youtube.com/get_video?video_id=' + r1
.group(1) + '&t=' + r2
.group(1) + '&fmt=18'
44 log('YouTube link resolved: %s => %s', url
, next
)
49 def get_real_channel_url(url
):
50 r
= re
.compile('http://(?:[a-z]+\.)?youtube\.com/user/([a-z0-9]+)', re
.IGNORECASE
)
54 next
= 'http://www.youtube.com/rss/user/'+ m
.group(1) +'/videos.rss'
55 log('YouTube link resolved: %s => %s', url
, next
)
58 r
= re
.compile('http://(?:[a-z]+\.)?youtube\.com/profile?user=([a-z0-9]+)', re
.IGNORECASE
)
62 next
= 'http://www.youtube.com/rss/user/'+ m
.group(1) +'/videos.rss'
63 log('YouTube link resolved: %s => %s', url
, next
)
68 def get_real_cover(url
):
71 r
= re
.compile('http://www\.youtube\.com/rss/user/([a-z0-9]+)/videos\.rss', re
.IGNORECASE
)
75 data
= urllib2
.urlopen('http://www.youtube.com/user/'+ m
.group(1)).read()
76 data
= data
[data
.find('id="user-profile-image"'):]
77 data
= data
[data
.find('src="') + 5:]
79 next
= data
[:data
.find('"')]
81 if next
.strip() == '':
84 log('YouTube userpic for %s is: %s', url
, next
)
89 def get_real_episode_length(episode
):
90 url
= get_real_download_url(episode
.url
)
92 if url
!= episode
.url
:
94 info
= urllib2
.urlopen(url
).info()
95 if 'content-length' in info
:
96 return info
['content-length']
97 except urllib2
.HTTPError
:
102 def find_youtube_channels(string
):
103 # FIXME: Make proper use of the YouTube API instead
104 # of screen-scraping the YouTube website
105 url
= 'http://www.youtube.com/results?search_query='+ urllib
.quote(string
, '') +'&search_type=search_users&aq=f'
107 r
= re
.compile('>\s+<')
108 data
= r
.sub('><', urllib
.urlopen(url
).read())
110 r1
= re
.compile('<a href="/user/([^"]+)"[^>]*>([^<]+)</a>')
111 m1
= r1
.findall(data
)
113 r2
= re
.compile('\s+')
115 model
= gtk
.ListStore(gobject
.TYPE_BOOLEAN
, gobject
.TYPE_STRING
, gobject
.TYPE_STRING
)
118 for (name
, title
) in m1
:
119 if name
not in found_users
:
120 found_users
.append(name
)
121 link
= 'http://www.youtube.com/rss/user/'+ name
+'/videos.rss'
122 model
.append([False, name
, link
])