mirror of
https://github.com/ytdl-org/youtube-dl
synced 2024-08-24 10:58:50 +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
130 lines
4.7 KiB
Python
130 lines
4.7 KiB
Python
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import (
|
|
compat_urllib_parse_unquote,
|
|
compat_urllib_parse_urlparse,
|
|
)
|
|
from ..utils import (
|
|
sanitized_Request,
|
|
str_to_int,
|
|
unified_strdate,
|
|
)
|
|
from ..aes import aes_decrypt_text
|
|
|
|
|
|
class SpankwireIE(InfoExtractor):
|
|
_VALID_URL = r'https?://(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<id>[0-9]+)/?)'
|
|
_TESTS = [{
|
|
# download URL pattern: */<height>P_<tbr>K_<video_id>.mp4
|
|
'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
|
|
'md5': '8bbfde12b101204b39e4b9fe7eb67095',
|
|
'info_dict': {
|
|
'id': '103545',
|
|
'ext': 'mp4',
|
|
'title': 'Buckcherry`s X Rated Music Video Crazy Bitch',
|
|
'description': 'Crazy Bitch X rated music video.',
|
|
'uploader': 'oreusz',
|
|
'uploader_id': '124697',
|
|
'upload_date': '20070507',
|
|
'age_limit': 18,
|
|
}
|
|
}, {
|
|
# download URL pattern: */mp4_<format_id>_<video_id>.mp4
|
|
'url': 'http://www.spankwire.com/Titcums-Compiloation-I/video1921551/',
|
|
'md5': '09b3c20833308b736ae8902db2f8d7e6',
|
|
'info_dict': {
|
|
'id': '1921551',
|
|
'ext': 'mp4',
|
|
'title': 'Titcums Compiloation I',
|
|
'description': 'cum on tits',
|
|
'uploader': 'dannyh78999',
|
|
'uploader_id': '3056053',
|
|
'upload_date': '20150822',
|
|
'age_limit': 18,
|
|
},
|
|
}]
|
|
|
|
def _real_extract(self, url):
|
|
mobj = re.match(self._VALID_URL, url)
|
|
video_id = mobj.group('id')
|
|
|
|
req = sanitized_Request('http://www.' + mobj.group('url'))
|
|
req.add_header('Cookie', 'age_verified=1')
|
|
webpage = self._download_webpage(req, video_id)
|
|
|
|
title = self._html_search_regex(
|
|
r'<h1>([^<]+)', webpage, 'title')
|
|
description = self._html_search_regex(
|
|
r'(?s)<div\s+id="descriptionContent">(.+?)</div>',
|
|
webpage, 'description', fatal=False)
|
|
thumbnail = self._html_search_regex(
|
|
r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']',
|
|
webpage, 'thumbnail', fatal=False)
|
|
|
|
uploader = self._html_search_regex(
|
|
r'by:\s*<a [^>]*>(.+?)</a>',
|
|
webpage, 'uploader', fatal=False)
|
|
uploader_id = self._html_search_regex(
|
|
r'by:\s*<a href="/(?:user/viewProfile|Profile\.aspx)\?.*?UserId=(\d+).*?"',
|
|
webpage, 'uploader id', fatal=False)
|
|
upload_date = unified_strdate(self._html_search_regex(
|
|
r'</a> on (.+?) at \d+:\d+',
|
|
webpage, 'upload date', fatal=False))
|
|
|
|
view_count = str_to_int(self._html_search_regex(
|
|
r'<div id="viewsCounter"><span>([\d,\.]+)</span> views</div>',
|
|
webpage, 'view count', fatal=False))
|
|
comment_count = str_to_int(self._html_search_regex(
|
|
r'<span\s+id="spCommentCount"[^>]*>([\d,\.]+)</span>',
|
|
webpage, 'comment count', fatal=False))
|
|
|
|
videos = re.findall(
|
|
r'playerData\.cdnPath([0-9]{3,})\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage)
|
|
heights = [int(video[0]) for video in videos]
|
|
video_urls = list(map(compat_urllib_parse_unquote, [video[1] for video in videos]))
|
|
if webpage.find('flashvars\.encrypted = "true"') != -1:
|
|
password = self._search_regex(
|
|
r'flashvars\.video_title = "([^"]+)',
|
|
webpage, 'password').replace('+', ' ')
|
|
video_urls = list(map(
|
|
lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'),
|
|
video_urls))
|
|
|
|
formats = []
|
|
for height, video_url in zip(heights, video_urls):
|
|
path = compat_urllib_parse_urlparse(video_url).path
|
|
_, quality = path.split('/')[4].split('_')[:2]
|
|
f = {
|
|
'url': video_url,
|
|
'height': height,
|
|
}
|
|
tbr = self._search_regex(r'^(\d+)[Kk]$', quality, 'tbr', default=None)
|
|
if tbr:
|
|
f.update({
|
|
'tbr': int(tbr),
|
|
'format_id': '%dp' % height,
|
|
})
|
|
else:
|
|
f['format_id'] = quality
|
|
formats.append(f)
|
|
self._sort_formats(formats)
|
|
|
|
age_limit = self._rta_search(webpage)
|
|
|
|
return {
|
|
'id': video_id,
|
|
'title': title,
|
|
'description': description,
|
|
'thumbnail': thumbnail,
|
|
'uploader': uploader,
|
|
'uploader_id': uploader_id,
|
|
'upload_date': upload_date,
|
|
'view_count': view_count,
|
|
'comment_count': comment_count,
|
|
'formats': formats,
|
|
'age_limit': age_limit,
|
|
}
|