1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
youtube-dl/youtube_dl/extractor/vodlocker.py

57 lines
1.7 KiB
Python
Raw Normal View History

2014-07-09 16:21:46 +00:00
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
2014-07-09 16:21:46 +00:00
compat_urllib_parse,
compat_urllib_request,
)
class VodlockerIE(InfoExtractor):
2014-07-22 13:37:33 +00:00
_VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
2014-07-09 16:21:46 +00:00
_TESTS = [{
'url': 'http://vodlocker.com/e8wvyzz4sl42',
'md5': 'ce0c2d18fa0735f1bd91b69b0e54aacf',
'info_dict': {
'id': 'e8wvyzz4sl42',
'ext': 'mp4',
'title': 'Germany vs Brazil',
'thumbnail': 're:http://.*\.jpg',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
2014-07-09 16:21:46 +00:00
webpage = self._download_webpage(url, video_id)
fields = self._hidden_inputs(webpage)
2014-07-09 16:21:46 +00:00
if fields['op'] == 'download1':
self._sleep(3, video_id) # they do detect when requests happen too fast!
2014-07-09 16:21:46 +00:00
post = compat_urllib_parse.urlencode(fields)
req = compat_urllib_request.Request(url, post)
req.add_header('Content-type', 'application/x-www-form-urlencoded')
webpage = self._download_webpage(
req, video_id, 'Downloading video page')
2014-07-09 16:21:46 +00:00
title = self._search_regex(
r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
thumbnail = self._search_regex(
r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail')
url = self._search_regex(
r'file:\s*"(http[^\"]+)",', webpage, 'file url')
2014-07-09 16:21:46 +00:00
formats = [{
'format_id': 'sd',
'url': url,
}]
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}