yt-dlp/youtube_dl/extractor/tube8.py

104 lines
3.7 KiB
Python
Raw Normal View History

2014-04-12 16:56:32 -04:00
from __future__ import unicode_literals
2013-10-26 17:27:30 -04:00
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
2014-04-12 16:56:32 -04:00
int_or_none,
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 11:18:17 -05:00
sanitized_Request,
2014-04-12 16:56:32 -04:00
str_to_int,
2013-10-26 17:27:30 -04:00
)
2014-04-12 16:56:32 -04:00
from ..aes import aes_decrypt_text
2013-10-26 17:27:30 -04:00
class Tube8IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
2016-01-20 09:07:32 -05:00
_TESTS = [{
'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
'md5': '65e20c48e6abff62ed0c3965fff13a39',
'info_dict': {
'id': '229795',
'display_id': 'kasia-music-video',
'ext': 'mp4',
'description': 'hot teen Kasia grinding',
'uploader': 'unknown',
'title': 'Kasia music video',
'age_limit': 18,
'duration': 230,
}
2016-01-20 10:30:29 -05:00
}, {
2016-01-20 09:07:32 -05:00
'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
'only_matching': True,
}]
2013-10-26 17:27:30 -04:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2014-04-12 16:56:32 -04:00
video_id = mobj.group('id')
display_id = mobj.group('display_id')
2013-10-26 17:27:30 -04:00
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 11:18:17 -05:00
req = sanitized_Request(url)
2013-10-26 17:27:30 -04:00
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, display_id)
2013-10-26 17:27:30 -04:00
flashvars = self._parse_json(
self._search_regex(
r'flashvars\s*=\s*({.+?});\r?\n', webpage, 'flashvars'),
video_id)
2014-04-12 16:56:32 -04:00
formats = []
for key, video_url in flashvars.items():
if not isinstance(video_url, compat_str) or not video_url.startswith('http'):
continue
height = self._search_regex(
r'quality_(\d+)[pP]', key, 'height', default=None)
if not height:
continue
if flashvars.get('encrypted') is True:
video_url = aes_decrypt_text(
video_url, flashvars['video_title'], 32).decode('utf-8')
formats.append({
'url': video_url,
'format_id': '%sp' % height,
'height': int(height),
})
self._sort_formats(formats)
2014-04-12 16:56:32 -04:00
thumbnail = flashvars.get('image_url')
title = self._html_search_regex(
2015-05-30 03:30:14 -04:00
r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
2014-04-12 16:56:32 -04:00
description = self._html_search_regex(
2015-05-30 03:30:14 -04:00
r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False)
2014-04-12 16:56:32 -04:00
uploader = self._html_search_regex(
2015-05-30 03:30:14 -04:00
r'<span class="username">\s*(.+?)\s*<',
2014-04-12 16:56:32 -04:00
webpage, 'uploader', fatal=False)
2016-01-20 09:07:32 -05:00
duration = int_or_none(flashvars.get('video_duration'))
2014-04-12 16:56:32 -04:00
2016-01-20 09:07:32 -05:00
like_count = int_or_none(self._search_regex(
2015-05-30 03:30:14 -04:00
r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
2016-01-20 09:07:32 -05:00
dislike_count = int_or_none(self._search_regex(
2015-05-30 03:30:14 -04:00
r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
2016-01-20 09:07:32 -05:00
view_count = str_to_int(self._search_regex(
r'<strong>Views: </strong>([\d,\.]+)\s*</li>',
webpage, 'view count', fatal=False))
comment_count = str_to_int(self._search_regex(
r'<span id="allCommentsCount">(\d+)</span>',
webpage, 'comment count', fatal=False))
2013-10-26 17:27:30 -04:00
return {
'id': video_id,
'display_id': display_id,
2014-04-12 16:56:32 -04:00
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
2016-01-20 09:07:32 -05:00
'duration': duration,
2014-04-12 16:56:32 -04:00
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
'comment_count': comment_count,
'age_limit': 18,
'formats': formats,
2013-10-26 17:27:30 -04:00
}