1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-21 17:51:51 +00:00

[heise] Add support for YouTube embeds

This commit is contained in:
kayb94 2017-09-17 15:46:52 +00:00 committed by Sergey M
parent 9c2a17f2ce
commit 4d8c4b46d5

View file

@ -2,6 +2,7 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..utils import (
determine_ext,
int_or_none,
@ -25,6 +26,22 @@ class HeiseIE(InfoExtractor):
'description': 'md5:c934cbfb326c669c2bcabcbe3d3fcd20',
'thumbnail': r're:^https?://.*/gallery/$',
}
}, {
# YouTube embed
'url': 'http://www.heise.de/newsticker/meldung/Netflix-In-20-Jahren-vom-Videoverleih-zum-TV-Revolutionaer-3814130.html',
'md5': 'e403d2b43fea8e405e88e3f8623909f1',
'info_dict': {
'id': '6kmWbXleKW4',
'ext': 'mp4',
'title': 'NEU IM SEPTEMBER | Netflix',
'description': 'md5:2131f3c7525e540d5fd841de938bd452',
'upload_date': '20170830',
'uploader': 'Netflix Deutschland, Österreich und Schweiz',
'uploader_id': 'netflixdach',
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.heise.de/ct/artikel/c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2403911.html',
'only_matching': True,
@ -40,6 +57,16 @@ class HeiseIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_meta('fulltitle', webpage, default=None)
if not title or title == "c't":
title = self._search_regex(
r'<div[^>]+class="videoplayerjw"[^>]+data-title="([^"]+)"',
webpage, 'title')
yt_urls = YoutubeIE._extract_urls(webpage)
if yt_urls:
return self.playlist_from_matches(yt_urls, video_id, title, ie=YoutubeIE.ie_key())
container_id = self._search_regex(
r'<div class="videoplayerjw"[^>]+data-container="([0-9]+)"',
webpage, 'container ID')
@ -47,12 +74,6 @@ class HeiseIE(InfoExtractor):
r'<div class="videoplayerjw"[^>]+data-sequenz="([0-9]+)"',
webpage, 'sequenz ID')
title = self._html_search_meta('fulltitle', webpage, default=None)
if not title or title == "c't":
title = self._search_regex(
r'<div[^>]+class="videoplayerjw"[^>]+data-title="([^"]+)"',
webpage, 'title')
doc = self._download_xml(
'http://www.heise.de/videout/feed', video_id, query={
'container': container_id,