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
109
110
111
112
113
114
115
116
117
118
119
120
121
|
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Nyaa.si (Anime Bittorrent tracker)
"""
from urllib.parse import urlencode
from lxml import html
from searx.utils import (
eval_xpath_getindex,
extract_text,
int_or_zero,
)
# about
about = {
"website": 'https://nyaa.si/',
"wikidata_id": None,
"official_api_documentation": None,
"use_official_api": False,
"require_api_key": False,
"results": 'HTML',
}
# engine dependent config
categories = ['files']
paging = True
# search-url
base_url = 'https://nyaa.si/'
# 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):
args = urlencode(
{
'q': query,
'p': params['pageno'],
}
)
params['url'] = base_url + '?' + args #
logger.debug("query_url --> %s", params['url'])
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
category = eval_xpath_getindex(result, xpath_category, 0, '')
if category:
category = category.attrib.get('title')
# 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
filesize = eval_xpath_getindex(result, xpath_filesize, 0, '')
# 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
|
