]> jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/netzkino.py
[ie/orf:on] Improve extraction (#9677)
[yt-dlp.git] / yt_dlp / extractor / netzkino.py
1 from .common import InfoExtractor
2 from ..utils import (
3 clean_html,
4 int_or_none,
5 js_to_json,
6 parse_iso8601,
7 )
8
9
10 class NetzkinoIE(InfoExtractor):
11 _WORKING = False
12 _VALID_URL = r'https?://(?:www\.)?netzkino\.de/\#!/[^/]+/(?P<id>[^/]+)'
13
14 _TESTS = [{
15 'url': 'https://www.netzkino.de/#!/scifikino/rakete-zum-mond',
16 'md5': '92a3f8b76f8d7220acce5377ea5d4873',
17 'info_dict': {
18 'id': 'rakete-zum-mond',
19 'ext': 'mp4',
20 'title': 'Rakete zum Mond \u2013 Jules Verne',
21 'description': 'md5:f0a8024479618ddbfa450ff48ffa6c60',
22 'upload_date': '20120813',
23 'thumbnail': r're:https?://.*\.jpg$',
24 'timestamp': 1344858571,
25 'age_limit': 12,
26 },
27 'params': {
28 'skip_download': 'Download only works from Germany',
29 }
30 }, {
31 'url': 'https://www.netzkino.de/#!/filme/dr-jekyll-mrs-hyde-2',
32 'md5': 'c7728b2dadd04ff6727814847a51ef03',
33 'info_dict': {
34 'id': 'dr-jekyll-mrs-hyde-2',
35 'ext': 'mp4',
36 'title': 'Dr. Jekyll & Mrs. Hyde 2',
37 'description': 'md5:c2e9626ebd02de0a794b95407045d186',
38 'upload_date': '20190130',
39 'thumbnail': r're:https?://.*\.jpg$',
40 'timestamp': 1548849437,
41 'age_limit': 18,
42 },
43 'params': {
44 'skip_download': 'Download only works from Germany',
45 }
46 }]
47
48 def _real_extract(self, url):
49 mobj = self._match_valid_url(url)
50 video_id = mobj.group('id')
51
52 api_url = 'https://api.netzkino.de.simplecache.net/capi-2.0a/movies/%s.json?d=www' % video_id
53 info = self._download_json(api_url, video_id)
54 custom_fields = info['custom_fields']
55
56 production_js = self._download_webpage(
57 'http://www.netzkino.de/beta/dist/production.min.js', video_id,
58 note='Downloading player code')
59 avo_js = self._search_regex(
60 r'var urlTemplate=(\{.*?"\})',
61 production_js, 'URL templates')
62 templates = self._parse_json(
63 avo_js, video_id, transform_source=js_to_json)
64
65 suffix = {
66 'hds': '.mp4/manifest.f4m',
67 'hls': '.mp4/master.m3u8',
68 'pmd': '.mp4',
69 }
70 film_fn = custom_fields['Streaming'][0]
71 formats = [{
72 'format_id': key,
73 'ext': 'mp4',
74 'url': tpl.replace('{}', film_fn) + suffix[key],
75 } for key, tpl in templates.items()]
76
77 return {
78 'id': video_id,
79 'formats': formats,
80 'title': info['title'],
81 'age_limit': int_or_none(custom_fields.get('FSK')[0]),
82 'timestamp': parse_iso8601(info.get('date'), delimiter=' '),
83 'description': clean_html(info.get('content')),
84 'thumbnail': info.get('thumbnail'),
85 }