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
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
|
"""
Nyaa.si (Anime Bittorrent tracker)
@website http://www.nyaa.si/
@provide-api no
@using-api no
@results HTML
@stable no (HTML can change)
@parse url, title, content, seed, leech, torrentfile
"""
from lxml import html
from searx.engines.xpath import extract_text
from searx.url_utils import urlencode
from searx.utils import get_torrent_size, int_or_zero
# engine dependent config
categories = ['files', 'images', 'videos', 'music']
paging = True
# search-url
base_url = 'http://www.nyaa.si/'
search_url = base_url + '?page=search&{query}&offset={offset}'
# xpath queries
xpath_results = '//table[contains(@class, "torrent-list")]//tr[not(th)]'
xpath_category = './/td[1]/a[1]'
xpath_title = './/td[2]/a[last()]'
xpath_torrent_links = './/td[3]/a'
xpath_filesize = './/td[4]/text()'
xpath_seeds = './/td[6]/text()'
xpath_leeches = './/td[7]/text()'
xpath_downloads = './/td[8]/text()'
# do search-request
def request(query, params):
query = urlencode({'term': query})
params['url'] = search_url.format(query=query, offset=params['pageno'])
return params
# get response from search-request
def response(resp):
results = []
dom = html.fromstring(resp.text)
for result in dom.xpath(xpath_results):
# defaults
filesize = 0
magnet_link = ""
torrent_link = ""
# category in which our torrent belongs
try:
category = result.xpath(xpath_category)[0].attrib.get('title')
except:
pass
# torrent title
page_a = result.xpath(xpath_title)[0]
title = extract_text(page_a)
# link to the page
href = base_url + page_a.attrib.get('href')
for link in result.xpath(xpath_torrent_links):
url = link.attrib.get('href')
if 'magnet' in url:
# link to the magnet
magnet_link = url
else:
# link to the torrent file
torrent_link = url
# seed count
seed = int_or_zero(result.xpath(xpath_seeds))
# leech count
leech = int_or_zero(result.xpath(xpath_leeches))
# torrent downloads count
downloads = int_or_zero(result.xpath(xpath_downloads))
# let's try to calculate the torrent size
try:
filesize_info = result.xpath(xpath_filesize)[0]
filesize, filesize_multiplier = filesize_info.split()
filesize = get_torrent_size(filesize, filesize_multiplier)
except:
pass
# content string contains all information not included into template
content = 'Category: "{category}". Downloaded {downloads} times.'
content = content.format(category=category, downloads=downloads)
results.append({'url': href,
'title': title,
'content': content,
'seed': seed,
'leech': leech,
'filesize': filesize,
'torrentfile': torrent_link,
'magnetlink': magnet_link,
'template': 'torrent.html'})
return results
|
