1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-05 02:32:44 +01:00
yt-dlp/youtube_dl/extractor/dumpert.py

65 lines
2.1 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import base64
from .common import InfoExtractor
from ..compat import compat_urllib_request
2015-03-30 16:11:51 +02:00
from ..utils import qualities
class DumpertIE(InfoExtractor):
_VALID_URL = r'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',
2015-03-30 16:11:51 +02:00
'description': 'Niet schrikken hoor',
'thumbnail': 're:^https?://.*\.jpg$',
}
}, {
'url': 'http://www.dumpert.nl/embed/6675421/dc440fe7/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
url = 'https://www.dumpert.nl/mediabase/' + video_id
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'nsfw=1; cpc=10')
webpage = self._download_webpage(req, video_id)
2015-03-30 16:11:51 +02:00
files_base64 = self._search_regex(
r'data-files="([^"]+)"', webpage, 'data files')
2015-03-30 16:11:51 +02:00
files = self._parse_json(
base64.b64decode(files_base64.encode('utf-8')).decode('utf-8'),
video_id)
2015-03-30 16:11:51 +02:00
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,
2015-03-30 16:11:51 +02:00
'thumbnail': thumbnail,
'formats': formats
}