]>
Commit | Line | Data |
---|---|---|
a14001a5 DR |
1 | from __future__ import unicode_literals |
2 | ||
be069839 RA |
3 | import re |
4 | ||
a14001a5 | 5 | from .common import InfoExtractor |
be069839 | 6 | from ..utils import int_or_none |
a14001a5 DR |
7 | |
8 | ||
9 | class TwentyThreeVideoIE(InfoExtractor): | |
10 | IE_NAME = '23video' | |
be069839 RA |
11 | _VALID_URL = r'https?://video\.(?P<domain>twentythree\.net|23video\.com|filmweb\.no)/v\.ihtml/player\.html\?(?P<query>.*?\bphoto(?:_|%5f)id=(?P<id>\d+).*)' |
12 | _TEST = { | |
13 | 'url': 'https://video.twentythree.net/v.ihtml/player.html?showDescriptions=0&source=site&photo%5fid=20448876&autoPlay=1', | |
14 | 'md5': '75fcf216303eb1dae9920d651f85ced4', | |
15 | 'info_dict': { | |
16 | 'id': '20448876', | |
17 | 'ext': 'mp4', | |
18 | 'title': 'Video Marketing Minute: Personalized Video', | |
19 | 'timestamp': 1513855354, | |
20 | 'upload_date': '20171221', | |
21 | 'uploader_id': '12258964', | |
22 | 'uploader': 'Rasmus Bysted', | |
a14001a5 DR |
23 | } |
24 | } | |
25 | ||
be069839 RA |
26 | def _real_extract(self, url): |
27 | domain, query, photo_id = re.match(self._VALID_URL, url).groups() | |
28 | base_url = 'https://video.%s' % domain | |
29 | photo_data = self._download_json( | |
30 | base_url + '/api/photo/list?' + query, photo_id, query={ | |
31 | 'format': 'json', | |
32 | }, transform_source=lambda s: self._search_regex(r'(?s)({.+})', s, 'photo data'))['photo'] | |
33 | title = photo_data['title'] | |
a14001a5 DR |
34 | |
35 | formats = [] | |
be069839 RA |
36 | |
37 | audio_path = photo_data.get('audio_download') | |
38 | if audio_path: | |
a14001a5 | 39 | formats.append({ |
be069839 RA |
40 | 'format_id': 'audio', |
41 | 'url': base_url + audio_path, | |
42 | 'filesize': int_or_none(photo_data.get('audio_size')), | |
43 | 'vcodec': 'none', | |
44 | }) | |
45 | ||
46 | def add_common_info_to_list(l, template, id_field, id_value): | |
47 | f_base = template % id_value | |
48 | f_path = photo_data.get(f_base + 'download') | |
49 | if not f_path: | |
50 | return | |
51 | l.append({ | |
52 | id_field: id_value, | |
53 | 'url': base_url + f_path, | |
54 | 'width': int_or_none(photo_data.get(f_base + 'width')), | |
55 | 'height': int_or_none(photo_data.get(f_base + 'height')), | |
56 | 'filesize': int_or_none(photo_data.get(f_base + 'size')), | |
a14001a5 DR |
57 | }) |
58 | ||
be069839 RA |
59 | for f in ('mobile_high', 'medium', 'hd', '1080p', '4k'): |
60 | add_common_info_to_list(formats, 'video_%s_', 'format_id', f) | |
a14001a5 | 61 | |
be069839 RA |
62 | thumbnails = [] |
63 | for t in ('quad16', 'quad50', 'quad75', 'quad100', 'small', 'portrait', 'standard', 'medium', 'large', 'original'): | |
64 | add_common_info_to_list(thumbnails, '%s_', 'id', t) | |
65 | ||
66 | return { | |
67 | 'id': photo_id, | |
68 | 'title': title, | |
69 | 'timestamp': int_or_none(photo_data.get('creation_date_epoch')), | |
70 | 'duration': int_or_none(photo_data.get('video_length')), | |
71 | 'view_count': int_or_none(photo_data.get('view_count')), | |
72 | 'comment_count': int_or_none(photo_data.get('number_of_comments')), | |
73 | 'uploader_id': photo_data.get('user_id'), | |
74 | 'uploader': photo_data.get('display_name'), | |
75 | 'thumbnails': thumbnails, | |
76 | 'formats': formats, | |
77 | } |