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
|
import urllib.parse
from .common import InfoExtractor
from ..utils import (
find_xpath_attr,
int_or_none,
update_url_query,
xpath_text,
)
class NozIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?noz\.de/video/(?P<id>[0-9]+)/'
_TESTS = [{
'url': 'http://www.noz.de/video/25151/32-Deutschland-gewinnt-Badminton-Lnderspiel-in-Melle',
'info_dict': {
'id': '25151',
'ext': 'mp4',
'duration': 215,
'title': '3:2 - Deutschland gewinnt Badminton-Länderspiel in Melle',
'description': 'Vor rund 370 Zuschauern gewinnt die deutsche Badminton-Nationalmannschaft am Donnerstag ein EM-Vorbereitungsspiel gegen Frankreich in Melle. Video Moritz Frankenberg.',
'thumbnail': r're:^http://.*\.jpg',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
description = self._og_search_description(webpage)
edge_url = self._html_search_regex(
r'<script\s+(?:type="text/javascript"\s+)?src="(.*?/videojs_.*?)"',
webpage, 'edge URL')
edge_content = self._download_webpage(edge_url, 'meta configuration')
config_url_encoded = self._search_regex(
r'so\.addVariable\("config_url","[^,]*,(.*?)"',
edge_content, 'config URL',
)
config_url = urllib.parse.unquote(config_url_encoded)
doc = self._download_xml(config_url, 'video configuration')
title = xpath_text(doc, './/title')
thumbnail = xpath_text(doc, './/article/thumbnail/url')
duration = int_or_none(xpath_text(
doc, './/article/movie/file/duration'))
formats = []
for qnode in doc.findall('.//article/movie/file/qualities/qual'):
http_url_ele = find_xpath_attr(
qnode, './html_urls/video_url', 'format', 'video/mp4')
http_url = http_url_ele.text if http_url_ele is not None else None
if http_url:
formats.append({
'url': http_url,
'format_name': xpath_text(qnode, './name'),
'format_id': '{}-{}'.format('http', xpath_text(qnode, './id')),
'height': int_or_none(xpath_text(qnode, './height')),
'width': int_or_none(xpath_text(qnode, './width')),
'tbr': int_or_none(xpath_text(qnode, './bitrate'), scale=1000),
})
else:
f4m_url = xpath_text(qnode, 'url_hd2')
if f4m_url:
formats.extend(self._extract_f4m_formats(
update_url_query(f4m_url, {'hdcore': '3.4.0'}),
video_id, f4m_id='hds', fatal=False))
m3u8_url_ele = find_xpath_attr(
qnode, './html_urls/video_url',
'format', 'application/vnd.apple.mpegurl')
m3u8_url = m3u8_url_ele.text if m3u8_url_ele is not None else None
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
return {
'id': video_id,
'formats': formats,
'title': title,
'duration': duration,
'description': description,
'thumbnail': thumbnail,
}
|
