mirror of
https://github.com/ytdl-org/youtube-dl
synced 2024-08-29 05:18:49 +09:00
![Sergey M?](/assets/img/avatar_default.png)
compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
137 lines
4.5 KiB
Python
137 lines
4.5 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import compat_urllib_parse
|
|
from ..utils import (
|
|
ExtractorError,
|
|
encode_dict,
|
|
int_or_none,
|
|
sanitized_Request,
|
|
)
|
|
|
|
|
|
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\.)?
|
|
(?: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)?
|
|
'''
|
|
|
|
_FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<'
|
|
|
|
_TESTS = [{
|
|
'url': 'http://gorillavid.in/06y9juieqpmi',
|
|
'md5': '5ae4a3580620380619678ee4875893ba',
|
|
'info_dict': {
|
|
'id': '06y9juieqpmi',
|
|
'ext': 'flv',
|
|
'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
|
|
'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',
|
|
'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
|
|
'thumbnail': 're:http://.*\.jpg',
|
|
}
|
|
}, {
|
|
# 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'
|
|
}
|
|
}]
|
|
|
|
def _real_extract(self, url):
|
|
mobj = re.match(self._VALID_URL, url)
|
|
video_id = mobj.group('id')
|
|
|
|
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)
|
|
|
|
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)
|
|
|
|
post = compat_urllib_parse.urlencode(encode_dict(fields))
|
|
|
|
req = sanitized_Request(url, post)
|
|
req.add_header('Content-type', 'application/x-www-form-urlencoded')
|
|
|
|
webpage = self._download_webpage(req, video_id, 'Downloading video page')
|
|
|
|
title = (self._search_regex(
|
|
[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(
|
|
[r'file\s*:\s*["\'](http[^"\']+)["\'],',
|
|
r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)'],
|
|
webpage, 'file url')
|
|
thumbnail = self._search_regex(
|
|
r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)
|
|
|
|
formats = [{
|
|
'format_id': 'sd',
|
|
'url': video_url,
|
|
'quality': 1,
|
|
}]
|
|
|
|
return {
|
|
'id': video_id,
|
|
'title': title,
|
|
'thumbnail': thumbnail,
|
|
'formats': formats,
|
|
}
|