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
|
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
get_meta_content,
parse_iso8601,
)
class HeiseIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://(?:www\.)?heise\.de/video/artikel/
.+?(?P<id>[0-9]+)\.html(?:$|[?#])
'''
_TEST = {
'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_720',
'timestamp': 1411812600,
'upload_date': '20140927',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
json_url = self._search_regex(
r'json_url:\s*"([^"]+)"', webpage, 'json URL')
config = self._download_json(json_url, video_id)
info = {
'id': video_id,
'thumbnail': config.get('poster'),
'timestamp': parse_iso8601(get_meta_content('date', webpage)),
}
title = get_meta_content('fulltitle', webpage)
if title:
info['title'] = title
elif config.get('title'):
info['title'] = config['title']
else:
info['title'] = self._og_search_title(webpage)
formats = []
for t, rs in config['formats'].items():
if not rs or not hasattr(rs, 'items'):
self._downloader.report_warning(
'formats: {0}: no resolutions'.format(t))
continue
for height_str, obj in rs.items():
format_id = '{0}_{1}'.format(t, height_str)
if not obj or not obj.get('url'):
self._downloader.report_warning(
'formats: {0}: no url'.format(format_id))
continue
formats.append({
'url': obj['url'],
'format_id': format_id,
'height': self._int(height_str, 'height'),
})
self._sort_formats(formats)
info['formats'] = formats
return info
|
