mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-05 07:53:18 +00:00
5c2266df4b
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
70 lines
2.2 KiB
Python
70 lines
2.2 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import base64
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..utils import (
|
|
qualities,
|
|
sanitized_Request,
|
|
)
|
|
|
|
|
|
class DumpertIE(InfoExtractor):
|
|
_VALID_URL = r'(?P<protocol>https?)://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
|
|
_TESTS = [{
|
|
'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/',
|
|
'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
|
|
'info_dict': {
|
|
'id': '6646981/951bc60f',
|
|
'ext': 'mp4',
|
|
'title': 'Ik heb nieuws voor je',
|
|
'description': 'Niet schrikken hoor',
|
|
'thumbnail': 're:^https?://.*\.jpg$',
|
|
}
|
|
}, {
|
|
'url': 'http://www.dumpert.nl/embed/6675421/dc440fe7/',
|
|
'only_matching': True,
|
|
}]
|
|
|
|
def _real_extract(self, url):
|
|
mobj = re.match(self._VALID_URL, url)
|
|
video_id = mobj.group('id')
|
|
protocol = mobj.group('protocol')
|
|
|
|
url = '%s://www.dumpert.nl/mediabase/%s' % (protocol, video_id)
|
|
req = sanitized_Request(url)
|
|
req.add_header('Cookie', 'nsfw=1; cpc=10')
|
|
webpage = self._download_webpage(req, video_id)
|
|
|
|
files_base64 = self._search_regex(
|
|
r'data-files="([^"]+)"', webpage, 'data files')
|
|
|
|
files = self._parse_json(
|
|
base64.b64decode(files_base64.encode('utf-8')).decode('utf-8'),
|
|
video_id)
|
|
|
|
quality = qualities(['flv', 'mobile', 'tablet', '720p'])
|
|
|
|
formats = [{
|
|
'url': video_url,
|
|
'format_id': format_id,
|
|
'quality': quality(format_id),
|
|
} for format_id, video_url in files.items() if format_id != 'still']
|
|
self._sort_formats(formats)
|
|
|
|
title = self._html_search_meta(
|
|
'title', webpage) or self._og_search_title(webpage)
|
|
description = self._html_search_meta(
|
|
'description', webpage) or self._og_search_description(webpage)
|
|
thumbnail = files.get('still') or self._og_search_thumbnail(webpage)
|
|
|
|
return {
|
|
'id': video_id,
|
|
'title': title,
|
|
'description': description,
|
|
'thumbnail': thumbnail,
|
|
'formats': formats
|
|
}
|