1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
|
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from .kaltura import KalturaIE
from .youtube import YoutubeIE
from ..utils import (
determine_ext,
int_or_none,
parse_iso8601,
smuggle_url,
xpath_text,
)
class HeiseIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?heise\.de/(?:[^/]+/)+[^/]+-(?P<id>[0-9]+)\.html'
_TESTS = [{
'url': 'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html',
'md5': 'ffed432483e922e88545ad9f2f15d30e',
'info_dict': {
'id': '2404147',
'ext': 'mp4',
'title': "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / Peilsender Smartphone",
'format_id': 'mp4_720p',
'timestamp': 1411812600,
'upload_date': '20140927',
'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': 'https://www.heise.de/video/artikel/nachgehakt-Wie-sichert-das-c-t-Tool-Restric-tor-Windows-10-ab-3700244.html',
'md5': '4b58058b46625bdbd841fc2804df95fc',
'info_dict': {
'id': '1_ntrmio2s',
'timestamp': 1512470717,
'upload_date': '20171205',
'ext': 'mp4',
'title': 'ct10 nachgehakt hos restrictor',
},
'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,
}, {
'url': 'http://www.heise.de/newsticker/meldung/c-t-uplink-Owncloud-Tastaturen-Peilsender-Smartphone-2404251.html?wt_mc=rss.ho.beitrag.atom',
'only_matching': True,
}, {
'url': 'http://www.heise.de/ct/ausgabe/2016-12-Spiele-3214137.html',
'only_matching': True,
}]
def _real_extract(self, url):
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())
kaltura_url = KalturaIE._extract_url(webpage)
if kaltura_url:
return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
container_id = self._search_regex(
r'<div class="videoplayerjw"[^>]+data-container="([0-9]+)"',
webpage, 'container ID')
sequenz_id = self._search_regex(
r'<div class="videoplayerjw"[^>]+data-sequenz="([0-9]+)"',
webpage, 'sequenz ID')
doc = self._download_xml(
'http://www.heise.de/videout/feed', video_id, query={
'container': container_id,
'sequenz': sequenz_id,
})
formats = []
for source_node in doc.findall('.//{http://rss.jwpcdn.com/}source'):
label = source_node.attrib['label']
height = int_or_none(self._search_regex(
r'^(.*?_)?([0-9]+)p$', label, 'height', default=None))
video_url = source_node.attrib['file']
ext = determine_ext(video_url, '')
formats.append({
'url': video_url,
'format_note': label,
'format_id': '%s_%s' % (ext, label),
'height': height,
})
self._sort_formats(formats)
description = self._og_search_description(
webpage, default=None) or self._html_search_meta(
'description', webpage)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': (xpath_text(doc, './/{http://rss.jwpcdn.com/}image') or
self._og_search_thumbnail(webpage)),
'timestamp': parse_iso8601(
self._html_search_meta('date', webpage)),
'formats': formats,
}
|
