]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/zaq1.py
[extractor/common] Relax interaction count extraction in _json_ld
[youtube-dl] / youtube_dl / extractor / zaq1.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..utils import (
6     int_or_none,
7     unified_timestamp,
8 )
9
10
11 class Zaq1IE(InfoExtractor):
12     _VALID_URL = r'https?://(?:www\.)?zaq1\.pl/video/(?P<id>[^/?#&]+)'
13     _TESTS = [{
14         'url': 'http://zaq1.pl/video/xev0e',
15         'md5': '24a5eb3f052e604ae597c4d0d19b351e',
16         'info_dict': {
17             'id': 'xev0e',
18             'title': 'DJ NA WESELE. TANIEC Z FIGURAMI.węgrów/sokołów podlaski/siedlce/mińsk mazowiecki/warszawa',
19             'description': 'www.facebook.com/weseledjKontakt: 728 448 199 / 505 419 147',
20             'ext': 'mp4',
21             'duration': 511,
22             'timestamp': 1490896361,
23             'uploader': 'Anonim',
24             'upload_date': '20170330',
25             'view_count': int,
26         }
27     }, {
28         # malformed JSON-LD
29         'url': 'http://zaq1.pl/video/x81vn',
30         'info_dict': {
31             'id': 'x81vn',
32             'title': 'SEKRETNE ŻYCIE WALTERA MITTY',
33             'ext': 'mp4',
34             'duration': 6234,
35             'timestamp': 1493494860,
36             'uploader': 'Anonim',
37             'upload_date': '20170429',
38             'view_count': int,
39         },
40         'params': {
41             'skip_download': True,
42         },
43         'expected_warnings': ['Failed to parse JSON'],
44     }]
45
46     def _real_extract(self, url):
47         video_id = self._match_id(url)
48
49         webpage = self._download_webpage(url, video_id)
50
51         video_url = self._search_regex(
52             r'data-video-url=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
53             'video url', group='url')
54
55         info = self._search_json_ld(webpage, video_id, fatal=False)
56
57         def extract_data(field, name, fatal=False):
58             return self._search_regex(
59                 r'data-%s=(["\'])(?P<field>(?:(?!\1).)+)\1' % field,
60                 webpage, field, fatal=fatal, group='field')
61
62         if not info.get('title'):
63             info['title'] = extract_data('file-name', 'title', fatal=True)
64
65         if not info.get('duration'):
66             info['duration'] = int_or_none(extract_data('duration', 'duration'))
67
68         if not info.get('thumbnail'):
69             info['thumbnail'] = extract_data('photo-url', 'thumbnail')
70
71         if not info.get('timestamp'):
72             info['timestamp'] = unified_timestamp(self._html_search_meta(
73                 'uploadDate', webpage, 'timestamp'))
74
75         if not info.get('interactionCount'):
76             info['view_count'] = int_or_none(self._html_search_meta(
77                 'interactionCount', webpage, 'view count'))
78
79         uploader = self._html_search_regex(
80             r'Wideo dodał:\s*<a[^>]*>([^<]+)</a>', webpage, 'uploader',
81             fatal=False)
82
83         width = int_or_none(self._html_search_meta(
84             'width', webpage, fatal=False))
85         height = int_or_none(self._html_search_meta(
86             'height', webpage, fatal=False))
87
88         info.update({
89             'id': video_id,
90             'formats': [{
91                 'url': video_url,
92                 'width': width,
93                 'height': height,
94                 'http_headers': {
95                     'Referer': url,
96                 },
97             }],
98             'uploader': uploader,
99         })
100
101         return info