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
|
"""
Torrentz.eu (BitTorrent meta-search engine)
@website https://torrentz.eu/
@provide-api no
@using-api no
@results HTML
@stable no (HTML can change, although unlikely,
see https://torrentz.eu/torrentz.btsearch)
@parse url, title, publishedDate, seed, leech, filesize, magnetlink
"""
import re
from lxml import html
from datetime import datetime
from searx.engines.nyaa import int_or_zero, get_filesize_mul
from searx.engines.xpath import extract_text
from searx.url_utils import urlencode
# engine dependent config
categories = ['files', 'videos', 'music']
paging = True
# search-url
# https://torrentz.eu/search?f=EXAMPLE&p=6
base_url = 'https://torrentz.eu/'
search_url = base_url + 'search?{query}'
# do search-request
def request(query, params):
page = params['pageno'] - 1
query = urlencode({'q': query, 'p': page})
params['url'] = search_url.format(query=query)
return params
# get response from search-request
def response(resp):
results = []
dom = html.fromstring(resp.text)
for result in dom.xpath('//div[@class="results"]/dl'):
name_cell = result.xpath('./dt')[0]
title = extract_text(name_cell)
# skip rows that do not contain a link to a torrent
links = name_cell.xpath('./a')
if len(links) != 1:
continue
# extract url and remove a slash in the beginning
link = links[0].attrib.get('href').lstrip('/')
seed = result.xpath('./dd/span[@class="u"]/text()')[0].replace(',', '')
leech = result.xpath('./dd/span[@class="d"]/text()')[0].replace(',', '')
params = {
'url': base_url + link,
'title': title,
'seed': int_or_zero(seed),
'leech': int_or_zero(leech),
'template': 'torrent.html'
}
# let's try to calculate the torrent size
try:
size_str = result.xpath('./dd/span[@class="s"]/text()')[0]
size, suffix = size_str.split()
params['filesize'] = int(size) * get_filesize_mul(suffix)
except:
pass
# does our link contain a valid SHA1 sum?
if re.compile('[0-9a-fA-F]{40}').match(link):
# add a magnet link to the result
params['magnetlink'] = 'magnet:?xt=urn:btih:' + link
# extract and convert creation date
try:
date_str = result.xpath('./dd/span[@class="a"]/span')[0].attrib.get('title')
# Fri, 25 Mar 2016 16:29:01
date = datetime.strptime(date_str, '%a, %d %b %Y %H:%M:%S')
params['publishedDate'] = date
except:
pass
results.append(params)
return results
|
