1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import ExtractorError
class TinyPicIE(InfoExtractor):
IE_NAME = 'tinypic'
IE_DESC = 'tinypic.com videos'
_VALID_URL = r'https?://(?:.+?\.)?tinypic\.com/player\.php\?v=(?P<id>[^&]+)&s=\d+'
_TESTS = [
{
'url': 'http://tinypic.com/player.php?v=6xw7tc%3E&s=5#.UtqZmbRFCM8',
'md5': '609b74432465364e72727ebc6203f044',
'info_dict': {
'id': '6xw7tc',
'ext': 'flv',
'title': 'shadow phenomenon weird',
},
},
{
'url': 'http://de.tinypic.com/player.php?v=dy90yh&s=8',
'only_matching': True,
}
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id, 'Downloading page')
mobj = re.search(r'(?m)fo\.addVariable\("file",\s"(?P<fileid>[\da-z]+)"\);\n'
r'\s+fo\.addVariable\("s",\s"(?P<serverid>\d+)"\);', webpage)
if mobj is None:
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
file_id = mobj.group('fileid')
server_id = mobj.group('serverid')
KEYWORDS_SUFFIX = ', Video, images, photos, videos, myspace, ebay, video hosting, photo hosting'
keywords = self._html_search_meta('keywords', webpage, 'title')
title = keywords[:-len(KEYWORDS_SUFFIX)] if keywords.endswith(KEYWORDS_SUFFIX) else ''
video_url = 'http://v%s.tinypic.com/%s.flv' % (server_id, file_id)
thumbnail = 'http://v%s.tinypic.com/%s_th.jpg' % (server_id, file_id)
return {
'id': file_id,
'url': video_url,
'thumbnail': thumbnail,
'title': title
}
|
