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
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
|
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
compat_urllib_parse,
)
class PlayvidIE(InfoExtractor):
_VALID_URL = r'^https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
_TEST = {
'url': 'http://www.playvid.com/watch/agbDDi7WZTV',
'md5': '44930f8afa616efdf9482daf4fe53e1e',
'info_dict': {
'id': 'agbDDi7WZTV',
'ext': 'mp4',
'title': 'Michelle Lewin in Miami Beach',
'duration': 240,
'age_limit': 18,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
m_error = re.search(
r'<div class="block-error">\s*<div class="heading">\s*<div>(?P<msg>.+?)</div>\s*</div>', webpage)
if m_error:
raise ExtractorError(clean_html(m_error.group('msg')), expected=True)
video_title = None
duration = None
video_thumbnail = None
formats = []
# most of the information is stored in the flashvars
flashvars = self._html_search_regex(
r'flashvars="(.+?)"', webpage, 'flashvars')
infos = compat_urllib_parse.unquote(flashvars).split(r'&')
for info in infos:
videovars_match = re.match(r'^video_vars\[(.+?)\]=(.+?)$', info)
if videovars_match:
key = videovars_match.group(1)
val = videovars_match.group(2)
if key == 'title':
video_title = compat_urllib_parse.unquote_plus(val)
if key == 'duration':
try:
duration = int(val)
except ValueError:
pass
if key == 'big_thumb':
video_thumbnail = val
videourl_match = re.match(
r'^video_urls\]\[(?P<resolution>[0-9]+)p', key)
if videourl_match:
height = int(videourl_match.group('resolution'))
formats.append({
'height': height,
'url': val,
})
self._sort_formats(formats)
# Extract title - should be in the flashvars; if not, look elsewhere
if video_title is None:
video_title = self._html_search_regex(
r'<title>(.*?)</title', webpage, 'title')
return {
'id': video_id,
'formats': formats,
'title': video_title,
'thumbnail': video_thumbnail,
'duration': duration,
'description': None,
'age_limit': 18
}
|
