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
|
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class PinkbikeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?pinkbike\.com/video/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://www.pinkbike.com/video/402811/',
'md5': '4814b8ca7651034cd87e3361d5c2155a',
'info_dict': {
'id': '402811',
'ext': 'mp4',
'title': 'Brandon Semenuk - RAW 100',
'thumbnail': 're:^https?://.*\.jpg$',
'location': 'Victoria, British Columbia, Canada',
'uploader_id': 'revelco',
'upload_date': '20150406',
'description': 'Official release: www.redbull.ca/rupertwalker',
'duration': 100
}
}, {
'url': 'http://www.pinkbike.com/video/406629/',
'md5': 'c7a3e19a2bd5cde5a1cda6b2b46caa74',
'info_dict': {
'id': '406629',
'ext': 'mp4',
'title': 'Chromag: Reece Wallace in Utah',
'thumbnail': 're:^https?://.*\.jpg$',
'location': 'Whistler, British Columbia, Canada',
'uploader_id': 'Chromagbikes',
'upload_date': '20150505',
'description': 'Reece Wallace shredding Virgin, Utah. Video by Virtu Media.',
'duration': 180
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
title = title[:-len(' Video - Pinkbike')]
description = self._html_search_meta('description', webpage, 'description')
description = description[len(title + '. '):]
uploader_id = self._html_search_regex(r'un:\s*"(.*?)"', webpage, 'uploader_id')
upload_date = self._html_search_regex(
r'class="fullTime"\s*title="([0-9]{4}(?:-[0-9]{2}){2})"',
webpage, 'upload_date')
upload_date = upload_date.replace('-', '')
location = self._html_search_regex(
r'<dt>Location</dt>\n?\s*<dd>\n?(.*?)\s*<img',
webpage, 'location')
formats = re.findall(
r'<source data-quality=\\"([0-9]+)p\\" src=\\"(.*?)\\">',
webpage)
formats = [{'url': fmt[1], 'height': fmt[0]} for fmt in formats]
return {
'id': video_id,
'title': title,
'description': description,
'duration': int(self._html_search_meta('video:duration', webpage, 'duration')),
'thumbnail': self._html_search_meta('og:image', webpage, 'thumbnail'),
'uploader_id': uploader_id,
'upload_date': upload_date,
'location': location,
'formats': formats
}
|
