youtube-dl/youtube_dl/extractor/xfileshare.py

139 lines
4.6 KiB
Python
Raw Normal View History

2015-11-11 16:58:39 +00:00
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
2014-06-17 13:18:46 +00:00
compat_urllib_parse,
compat_urllib_request,
)
from ..utils import (
ExtractorError,
2015-09-06 01:30:02 +00:00
encode_dict,
int_or_none,
2014-06-17 13:18:46 +00:00
)
2015-11-11 16:58:39 +00:00
class XFileShareIE(InfoExtractor):
IE_DESC = 'XFileShare based sites: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me'
_VALID_URL = r'''(?x)
https?://(?P<host>(?:www\.)?
2015-11-11 16:44:03 +00:00
(?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com|vidto.\me))/
(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
'''
2014-06-17 13:18:46 +00:00
_FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<'
2014-06-17 13:18:46 +00:00
_TESTS = [{
'url': 'http://gorillavid.in/06y9juieqpmi',
'md5': '5ae4a3580620380619678ee4875893ba',
'info_dict': {
'id': '06y9juieqpmi',
'ext': 'flv',
'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
2014-06-17 13:18:46 +00:00
'thumbnail': 're:http://.*\.jpg',
},
}, {
'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
'only_matching': True,
}, {
'url': 'http://daclips.in/3rso4kdn6f9m',
'md5': '1ad8fd39bb976eeb66004d3a4895f106',
'info_dict': {
'id': '3rso4kdn6f9m',
'ext': 'mp4',
2014-10-26 23:44:27 +00:00
'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
'thumbnail': 're:http://.*\.jpg',
2014-10-26 23:44:27 +00:00
}
}, {
# video with countdown timeout
'url': 'http://fastvideo.in/1qmdn1lmsmbw',
'md5': '8b87ec3f6564a3108a0e8e66594842ba',
'info_dict': {
'id': '1qmdn1lmsmbw',
'ext': 'mp4',
'title': 'Man of Steel - Trailer',
'thumbnail': 're:http://.*\.jpg',
},
}, {
'url': 'http://realvid.net/ctn2y6p2eviw',
'md5': 'b2166d2cf192efd6b6d764c18fd3710e',
'info_dict': {
'id': 'ctn2y6p2eviw',
'ext': 'flv',
'title': 'rdx 1955',
'thumbnail': 're:http://.*\.jpg',
},
}, {
'url': 'http://movpod.in/0wguyyxi1yca',
'only_matching': True,
}, {
'url': 'http://filehoot.com/3ivfabn7573c.html',
'info_dict': {
'id': '3ivfabn7573c',
'ext': 'mp4',
'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4',
'thumbnail': 're:http://.*\.jpg',
}
}, {
'url': 'http://vidto.me/ku5glz52nqe1.html',
'info_dict': {
'id': 'ku5glz52nqe1',
'ext': 'mp4',
'title': 'test'
}
2014-06-17 13:18:46 +00:00
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
2015-09-06 01:23:53 +00:00
url = 'http://%s/%s' % (mobj.group('host'), video_id)
webpage = self._download_webpage(url, video_id)
if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
fields = self._hidden_inputs(webpage)
2014-11-23 19:41:03 +00:00
2014-06-17 13:18:46 +00:00
if fields['op'] == 'download1':
countdown = int_or_none(self._search_regex(
r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
webpage, 'countdown', default=None))
if countdown:
self._sleep(countdown, video_id)
2015-09-06 01:30:02 +00:00
post = compat_urllib_parse.urlencode(encode_dict(fields))
2014-06-17 13:18:46 +00:00
req = compat_urllib_request.Request(url, post)
req.add_header('Content-type', 'application/x-www-form-urlencoded')
2014-06-17 13:18:46 +00:00
webpage = self._download_webpage(req, video_id, 'Downloading video page')
title = (self._search_regex(
2015-11-11 16:44:03 +00:00
[r'style="z-index: [0-9]+;">([^<]+)</span>',
r'<td nowrap>([^<]+)</td>',
r'>Watch (.+) ',
r'<h2 class="video-page-head">([^<]+)</h2>'],
webpage, 'title', default=None) or self._og_search_title(webpage)).strip()
video_url = self._search_regex(
2015-11-11 16:44:03 +00:00
[r'file\s*:\s*["\'](http[^"\']+)["\'],',
r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)'],
webpage, 'file url')
thumbnail = self._search_regex(
2015-11-11 16:44:03 +00:00
r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)
2014-06-17 13:18:46 +00:00
formats = [{
'format_id': 'sd',
'url': video_url,
2014-06-17 13:18:46 +00:00
'quality': 1,
}]
return {
'id': video_id,
'title': title,
2014-06-17 13:18:46 +00:00
'thumbnail': thumbnail,
'formats': formats,
}