]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/heise.py
d41c0413f015e262237f66161d4021c32f56ff0e
[youtubedl] / youtube_dl / extractor / heise.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..utils import (
6 get_meta_content,
7 int_or_none,
8 parse_iso8601,
9 )
10
11
12 class HeiseIE(InfoExtractor):
13 _VALID_URL = r'''(?x)
14 https?://(?:www\.)?heise\.de/video/artikel/
15 .+?(?P<id>[0-9]+)\.html(?:$|[?#])
16 '''
17 _TEST = {
18 'url': (
19 'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html'
20 ),
21 'md5': 'ffed432483e922e88545ad9f2f15d30e',
22 'info_dict': {
23 'id': '2404147',
24 'ext': 'mp4',
25 'title': (
26 "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / Peilsender Smartphone"
27 ),
28 'format_id': 'mp4_720',
29 'timestamp': 1411812600,
30 'upload_date': '20140927',
31 'description': 'In uplink-Episode 3.3 geht es darum, wie man sich von Cloud-Anbietern emanzipieren kann, worauf man beim Kauf einer Tastatur achten sollte und was Smartphones über uns verraten.',
32 'thumbnail': 're:https?://.*\.jpg$',
33 }
34 }
35
36 def _real_extract(self, url):
37 video_id = self._match_id(url)
38 webpage = self._download_webpage(url, video_id)
39
40 container_id = self._search_regex(
41 r'<div class="videoplayerjw".*?data-container="([0-9]+)"',
42 webpage, 'container ID')
43 sequenz_id = self._search_regex(
44 r'<div class="videoplayerjw".*?data-sequenz="([0-9]+)"',
45 webpage, 'sequenz ID')
46 data_url = 'http://www.heise.de/videout/feed?container=%s&sequenz=%s' % (container_id, sequenz_id)
47 doc = self._download_xml(data_url, video_id)
48
49 info = {
50 'id': video_id,
51 'thumbnail': self._og_search_thumbnail(webpage),
52 'timestamp': parse_iso8601(get_meta_content('date', webpage)),
53 'description': self._og_search_description(webpage),
54 }
55
56 title = get_meta_content('fulltitle', webpage)
57 if title:
58 info['title'] = title
59 else:
60 info['title'] = self._og_search_title(webpage)
61
62 formats = []
63 for source_node in doc.findall('.//{http://rss.jwpcdn.com/}source'):
64 label = source_node.attrib['label']
65 height = int_or_none(self._search_regex(
66 r'^(.*?_)?([0-9]+)p$', label, 'height', default=None))
67 formats.append({
68 'url': source_node.attrib['file'],
69 'format_note': label,
70 'height': height,
71 })
72 self._sort_formats(formats)
73 info['formats'] = formats
74
75 return info