1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-15 03:47:48 +01:00
youtube-dl/youtube_dl/extractor/hostingbulk.py

81 lines
2.5 KiB
Python
Raw Normal View History

2014-09-09 21:17:33 +02:00
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_request,
)
2014-09-09 21:17:33 +02:00
from ..utils import (
ExtractorError,
int_or_none,
urlencode_postdata,
)
class HostingBulkIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://(?:www\.)?hostingbulk\.com/
(?:embed-)?(?P<id>[A-Za-z0-9]{12})(?:-\d+x\d+)?\.html'''
_FILE_DELETED_REGEX = r'<b>File Not Found</b>'
_TEST = {
'url': 'http://hostingbulk.com/n0ulw1hv20fm.html',
'md5': '6c8653c8ecf7ebfa83b76e24b7b2fe3f',
'info_dict': {
'id': 'n0ulw1hv20fm',
'ext': 'mp4',
'title': 'md5:5afeba33f48ec87219c269e054afd622',
'filesize': 6816081,
'thumbnail': 're:^http://.*\.jpg$',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
2014-09-09 21:17:33 +02:00
url = 'http://hostingbulk.com/{0:}.html'.format(video_id)
# Custom request with cookie to set language to English, so our file
# deleted regex would work.
request = compat_urllib_request.Request(
url, headers={'Cookie': 'lang=english'})
webpage = self._download_webpage(request, video_id)
if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
raise ExtractorError('Video %s does not exist' % video_id,
expected=True)
title = self._html_search_regex(r'<h3>(.*?)</h3>', webpage, 'title')
filesize = int_or_none(
self._search_regex(
r'<small>\((\d+)\sbytes?\)</small>',
webpage,
'filesize',
fatal=False
)
)
thumbnail = self._search_regex(
r'<img src="([^"]+)".+?class="pic"',
webpage, 'thumbnail', fatal=False)
fields = self._hidden_inputs(webpage)
2014-09-10 14:13:22 +02:00
2014-09-09 21:17:33 +02:00
request = compat_urllib_request.Request(url, urlencode_postdata(fields))
request.add_header('Content-type', 'application/x-www-form-urlencoded')
response = self._request_webpage(request, video_id,
'Submiting download request')
video_url = response.geturl()
formats = [{
'format_id': 'sd',
'filesize': filesize,
'url': video_url,
}]
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}