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
|
# coding: utf-8
from __future__ import unicode_literals
import re
import os.path
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..utils import (
ExtractorError,
)
class PlayedIE(InfoExtractor):
IE_NAME = 'played.to'
_VALID_URL = r'https?://(?:www\.)?played\.to/(?P<id>[a-zA-Z0-9_-]+)'
_TEST = {
'url': 'http://played.to/j2f2sfiiukgt',
'md5': 'c2bd75a368e82980e7257bf500c00637',
'info_dict': {
'id': 'j2f2sfiiukgt',
'ext': 'flv',
'title': 'youtube-dl_test_video.mp4',
},
'skip': 'Removed for copyright infringement.', # oh wow
}
def _real_extract(self, url):
video_id = self._match_id(url)
orig_webpage = self._download_webpage(url, video_id)
m_error = re.search(
r'(?s)Reason for deletion:.*?<b class="err"[^>]*>(?P<msg>[^<]+)</b>', orig_webpage)
if m_error:
raise ExtractorError(m_error.group('msg'), expected=True)
fields = re.findall(
r'type="hidden" name="([^"]+)"\s+value="([^"]+)">', orig_webpage)
data = dict(fields)
self._sleep(2, video_id)
post = compat_urllib_parse.urlencode(data)
headers = {
b'Content-Type': b'application/x-www-form-urlencoded',
}
req = compat_urllib_request.Request(url, post, headers)
webpage = self._download_webpage(
req, video_id, note='Downloading video page ...')
title = os.path.splitext(data['fname'])[0]
video_url = self._search_regex(
r'file: "?(.+?)",', webpage, 'video URL')
return {
'id': video_id,
'title': title,
'url': video_url,
}
|
