yt-dlp/youtube_dl/extractor/fourtube.py
Sergey M? 5c2266df4b 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
2015-11-23 21:56:23 +06:00

118 lines
4.4 KiB
Python

from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
parse_duration,
parse_iso8601,
sanitized_Request,
str_to_int,
)
class FourTubeIE(InfoExtractor):
IE_NAME = '4tube'
_VALID_URL = r'https?://(?:www\.)?4tube\.com/videos/(?P<id>\d+)'
_TEST = {
'url': 'http://www.4tube.com/videos/209733/hot-babe-holly-michaels-gets-her-ass-stuffed-by-black',
'md5': '6516c8ac63b03de06bc8eac14362db4f',
'info_dict': {
'id': '209733',
'ext': 'mp4',
'title': 'Hot Babe Holly Michaels gets her ass stuffed by black',
'uploader': 'WCP Club',
'uploader_id': 'wcp-club',
'upload_date': '20131031',
'timestamp': 1383263892,
'duration': 583,
'view_count': int,
'like_count': int,
'categories': list,
'age_limit': 18,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_meta('name', webpage)
timestamp = parse_iso8601(self._html_search_meta(
'uploadDate', webpage))
thumbnail = self._html_search_meta('thumbnailUrl', webpage)
uploader_id = self._html_search_regex(
r'<a class="img-avatar" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">',
webpage, 'uploader id', fatal=False)
uploader = self._html_search_regex(
r'<a class="img-avatar" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">',
webpage, 'uploader', fatal=False)
categories_html = self._search_regex(
r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="list">(.*?)</ul>',
webpage, 'categories', fatal=False)
categories = None
if categories_html:
categories = [
c.strip() for c in re.findall(
r'(?s)<li><a.*?>(.*?)</a>', categories_html)]
view_count = str_to_int(self._search_regex(
r'<meta itemprop="interactionCount" content="UserPlays:([0-9,]+)">',
webpage, 'view count', fatal=False))
like_count = str_to_int(self._search_regex(
r'<meta itemprop="interactionCount" content="UserLikes:([0-9,]+)">',
webpage, 'like count', fatal=False))
duration = parse_duration(self._html_search_meta('duration', webpage))
media_id = self._search_regex(
r'<button[^>]+data-id=(["\'])(?P<id>\d+)\1[^>]+data-quality=', webpage,
'media id', default=None, group='id')
sources = [
quality
for _, quality in re.findall(r'<button[^>]+data-quality=(["\'])(.+?)\1', webpage)]
if not (media_id and sources):
player_js = self._download_webpage(
self._search_regex(
r'<script[^>]id=(["\'])playerembed\1[^>]+src=(["\'])(?P<url>.+?)\2',
webpage, 'player JS', group='url'),
video_id, 'Downloading player JS')
params_js = self._search_regex(
r'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)',
player_js, 'initialization parameters')
params = self._parse_json('[%s]' % params_js, video_id)
media_id = params[0]
sources = ['%s' % p for p in params[2]]
token_url = 'http://tkn.4tube.com/{0}/desktop/{1}'.format(
media_id, '+'.join(sources))
headers = {
b'Content-Type': b'application/x-www-form-urlencoded',
b'Origin': b'http://www.4tube.com',
}
token_req = sanitized_Request(token_url, b'{}', headers)
tokens = self._download_json(token_req, video_id)
formats = [{
'url': tokens[format]['token'],
'format_id': format + 'p',
'resolution': format + 'p',
'quality': int(format),
} for format in sources]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'formats': formats,
'categories': categories,
'thumbnail': thumbnail,
'uploader': uploader,
'uploader_id': uploader_id,
'timestamp': timestamp,
'like_count': like_count,
'view_count': view_count,
'duration': duration,
'age_limit': 18,
}