[dctp] Fix extraction (closes #10734)

This commit is contained in:
Yen Chi Hsuan 2016-10-01 15:22:48 +08:00
parent d7753d1948
commit e295618f9e
No known key found for this signature in database
GPG key ID: 3FDDD575826C5C30
2 changed files with 31 additions and 37 deletions

View file

@ -1,6 +1,7 @@
version <unreleased>
Extractors
* [dctp] Fix extraction (#10734)
+ [leeco] Recognize more Le Sports URLs (#10794)

View file

@ -1,61 +1,54 @@
# encoding: utf-8
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import unified_strdate
class DctpTvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dctp\.tv/(#/)?filme/(?P<id>.+?)/$'
_TEST = {
'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
'md5': '174dd4a8a6225cf5655952f969cfbe24',
'info_dict': {
'id': '1324',
'id': '95eaa4f33dad413aa17b4ee613cccc6c',
'display_id': 'videoinstallation-fuer-eine-kaufhausfassade',
'ext': 'flv',
'title': 'Videoinstallation für eine Kaufhausfassade'
'ext': 'mp4',
'title': 'Videoinstallation für eine Kaufhausfassade',
'description': 'Kurzfilm',
'upload_date': '20110407',
'thumbnail': 're:^https?://.*\.jpg$',
},
'params': {
# rtmp download
'skip_download': True,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
base_url = 'http://dctp-ivms2-restapi.s3.amazonaws.com/'
version_json = self._download_json(
base_url + 'version.json',
video_id, note='Determining file version')
version = version_json['version_name']
info_json = self._download_json(
'{0}{1}/restapi/slugs/{2}.json'.format(base_url, version, video_id),
video_id, note='Fetching object ID')
object_id = compat_str(info_json['object_id'])
meta_json = self._download_json(
'{0}{1}/restapi/media/{2}.json'.format(base_url, version, object_id),
video_id, note='Downloading metadata')
uuid = meta_json['uuid']
title = meta_json['title']
wide = meta_json['is_wide']
if wide:
ratio = '16x9'
else:
ratio = '4x3'
play_path = 'mp4:{0}_dctp_0500_{1}.m4v'.format(uuid, ratio)
webpage = self._download_webpage(url, video_id)
object_id = self._html_search_meta('DC.identifier', webpage)
servers_json = self._download_json(
'http://www.dctp.tv/streaming_servers/',
'http://www.dctp.tv/elastic_streaming_client/get_streaming_server/',
video_id, note='Downloading server list')
url = servers_json[0]['endpoint']
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)
return {
'id': object_id,
'title': title,
'format': 'rtmp',
'url': url,
'play_path': play_path,
'rtmp_real_time': True,
'ext': 'flv',
'display_id': video_id
'formats': formats,
'display_id': video_id,
'description': description,
'upload_date': upload_date,
'thumbnail': thumbnail,
}