youtube-dl/youtube_dl/extractor/dctp.py

55 lines
2.0 KiB
Python
Raw Normal View History

2016-10-01 01:22:48 -06:00
# coding: utf-8
2015-01-28 00:21:04 -07:00
from __future__ import unicode_literals
from .common import InfoExtractor
2016-10-01 01:22:48 -06:00
from ..utils import unified_strdate
2015-01-28 00:21:04 -07:00
2015-01-28 00:59:58 -07:00
2015-01-28 00:21:04 -07:00
class DctpTvIE(InfoExtractor):
2016-09-08 05:29:05 -06:00
_VALID_URL = r'https?://(?:www\.)?dctp\.tv/(#/)?filme/(?P<id>.+?)/$'
2015-01-28 00:59:58 -07:00
_TEST = {
'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
2016-10-01 01:22:48 -06:00
'md5': '174dd4a8a6225cf5655952f969cfbe24',
2015-01-28 00:59:58 -07:00
'info_dict': {
2016-10-01 01:22:48 -06:00
'id': '95eaa4f33dad413aa17b4ee613cccc6c',
2015-01-29 16:35:53 -07:00
'display_id': 'videoinstallation-fuer-eine-kaufhausfassade',
2016-10-01 01:22:48 -06:00
'ext': 'mp4',
'title': 'Videoinstallation für eine Kaufhausfassade',
'description': 'Kurzfilm',
'upload_date': '20110407',
'thumbnail': 're:^https?://.*\.jpg$',
2015-02-11 09:10:33 -07:00
},
2015-01-29 19:45:06 -07:00
}
2015-01-28 00:21:04 -07:00
def _real_extract(self, url):
video_id = self._match_id(url)
2016-10-01 01:22:48 -06:00
webpage = self._download_webpage(url, video_id)
object_id = self._html_search_meta('DC.identifier', webpage)
2015-01-28 00:21:04 -07:00
2015-01-29 19:15:34 -07:00
servers_json = self._download_json(
2016-10-01 01:22:48 -06:00
'http://www.dctp.tv/elastic_streaming_client/get_streaming_server/',
2015-01-29 19:15:34 -07:00
video_id, note='Downloading server list')
2016-10-01 01:22:48 -06:00
server = servers_json[0]['server']
m3u8_path = self._search_regex(
r'\'([^\'"]+/playlist\.m3u8)"', webpage, 'm3u8 path')
formats = self._extract_m3u8_formats(
'http://%s%s' % (server, m3u8_path), video_id, ext='mp4',
entry_protocol='m3u8_native')
title = self._og_search_title(webpage)
description = self._html_search_meta('DC.description', webpage)
upload_date = unified_strdate(
self._html_search_meta('DC.date.created', webpage))
thumbnail = self._og_search_thumbnail(webpage)
2015-01-28 00:21:04 -07:00
return {
2015-01-29 15:34:56 -07:00
'id': object_id,
2015-01-28 00:21:04 -07:00
'title': title,
2016-10-01 01:22:48 -06:00
'formats': formats,
'display_id': video_id,
'description': description,
'upload_date': upload_date,
'thumbnail': thumbnail,
2015-01-28 00:21:04 -07:00
}