yt-dlp/youtube_dl/extractor/vodlocker.py

80 lines
2.7 KiB
Python
Raw Normal View History

2016-10-02 13:39:18 +02:00
# coding: utf-8
2014-07-09 18:21:46 +02:00
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
ExtractorError,
NO_DEFAULT,
sanitized_Request,
urlencode_postdata,
)
2014-07-09 18:21:46 +02:00
class VodlockerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?vodlocker\.(?:com|city)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
2014-07-09 18:21:46 +02:00
_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 18:21:46 +02:00
webpage = self._download_webpage(url, video_id)
if any(p in webpage for p in (
'>THIS FILE WAS DELETED<',
'>File Not Found<',
'The file you were looking for could not be found, sorry for any inconvenience.<')):
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
fields = self._hidden_inputs(webpage)
2014-07-09 18:21:46 +02:00
if fields['op'] == 'download1':
self._sleep(3, video_id) # they do detect when requests happen too fast!
post = urlencode_postdata(fields)
Switch codebase to use sanitized_Request instead of 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
2015-11-21 17:18:17 +01:00
req = sanitized_Request(url, post)
2014-07-09 18:21:46 +02:00
req.add_header('Content-type', 'application/x-www-form-urlencoded')
webpage = self._download_webpage(
req, video_id, 'Downloading video page')
2014-07-09 18:21:46 +02:00
def extract_file_url(html, default=NO_DEFAULT):
return self._search_regex(
r'file:\s*"(http[^\"]+)",', html, 'file url', default=default)
video_url = extract_file_url(webpage, default=None)
if not video_url:
embed_url = self._search_regex(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?vodlocker\.(?:com|city)/embed-.+?)\1',
webpage, 'embed url', group='url')
embed_webpage = self._download_webpage(
embed_url, video_id, 'Downloading embed webpage')
video_url = extract_file_url(embed_webpage)
thumbnail_webpage = embed_webpage
else:
thumbnail_webpage = webpage
title = self._search_regex(
r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
thumbnail = self._search_regex(
r'image:\s*"(http[^\"]+)",', thumbnail_webpage, 'thumbnail', fatal=False)
2014-07-09 18:21:46 +02:00
formats = [{
'format_id': 'sd',
'url': video_url,
2014-07-09 18:21:46 +02:00
}]
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}