youtube-dl/youtube_dl/extractor/dctp.py

87 lines
2.8 KiB
Python
Raw Normal View History

2016-10-01 07:22:48 +00:00
# coding: utf-8
2015-01-28 07:21:04 +00:00
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
float_or_none,
unified_strdate,
)
2015-01-28 07:21:04 +00:00
2015-01-28 07:59:58 +00:00
2015-01-28 07:21:04 +00:00
class DctpTvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dctp\.tv/(?:#/)?filme/(?P<id>[^/?#&]+)'
2015-01-28 07:59:58 +00:00
_TEST = {
'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
'info_dict': {
2016-10-01 07:22:48 +00:00
'id': '95eaa4f33dad413aa17b4ee613cccc6c',
2015-01-29 23:35:53 +00:00
'display_id': 'videoinstallation-fuer-eine-kaufhausfassade',
'ext': 'flv',
2016-10-01 07:22:48 +00:00
'title': 'Videoinstallation für eine Kaufhausfassade',
'description': 'Kurzfilm',
'upload_date': '20110407',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 71.24,
},
'params': {
# rtmp download
'skip_download': True,
2015-02-11 16:10:33 +00:00
},
2015-01-30 02:45:06 +00:00
}
2015-01-28 07:21:04 +00:00
def _real_extract(self, url):
display_id = self._match_id(url)
2016-10-01 07:22:48 +00:00
webpage = self._download_webpage(url, display_id)
2015-01-28 07:21:04 +00:00
video_id = self._html_search_meta(
'DC.identifier', webpage, 'video id',
default=None) or self._search_regex(
r'id=["\']uuid[^>]+>([^<]+)<', webpage, 'video id')
2016-10-01 07:22:48 +00:00
title = self._og_search_title(webpage)
servers = self._download_json(
'http://www.dctp.tv/streaming_servers/', display_id,
note='Downloading server list', fatal=False)
if servers:
endpoint = next(
server['endpoint']
for server in servers
if isinstance(server.get('endpoint'), compat_str) and
'cloudfront' in server['endpoint'])
else:
endpoint = 'rtmpe://s2pqqn4u96e4j8.cloudfront.net/cfx/st/'
app = self._search_regex(
r'^rtmpe?://[^/]+/(?P<app>.*)$', endpoint, 'app')
formats = [{
'url': endpoint,
'app': app,
'play_path': 'mp4:%s_dctp_0500_4x3.m4v' % video_id,
'page_url': url,
'player_url': 'http://svm-prod-dctptv-static.s3.amazonaws.com/dctptv-relaunch2012-109.swf',
'ext': 'flv',
}]
2016-10-01 07:22:48 +00:00
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)
duration = float_or_none(self._search_regex(
r'id=["\']duration_in_ms[^+]>(\d+)', webpage, 'duration',
default=None), scale=1000)
2015-01-28 07:21:04 +00:00
return {
'id': video_id,
2015-01-28 07:21:04 +00:00
'title': title,
2016-10-01 07:22:48 +00:00
'formats': formats,
'display_id': display_id,
2016-10-01 07:22:48 +00:00
'description': description,
'upload_date': upload_date,
'thumbnail': thumbnail,
'duration': duration,
2015-01-28 07:21:04 +00:00
}