forked from Ponysearch/Ponysearch
Merge pull request #1009 from misnyo/torrentz
[fix]torrentz search engine fixed for new version
This commit is contained in:
commit
489bf0f6fd
3 changed files with 42 additions and 34 deletions
|
@ -1,7 +1,7 @@
|
||||||
"""
|
"""
|
||||||
Torrentz.eu (BitTorrent meta-search engine)
|
Torrentz2.eu (BitTorrent meta-search engine)
|
||||||
|
|
||||||
@website https://torrentz.eu/
|
@website https://torrentz2.eu/
|
||||||
@provide-api no
|
@provide-api no
|
||||||
|
|
||||||
@using-api no
|
@using-api no
|
||||||
|
@ -14,24 +14,24 @@
|
||||||
import re
|
import re
|
||||||
from lxml import html
|
from lxml import html
|
||||||
from datetime import datetime
|
from datetime import datetime
|
||||||
from searx.engines.nyaa import int_or_zero, get_filesize_mul
|
|
||||||
from searx.engines.xpath import extract_text
|
from searx.engines.xpath import extract_text
|
||||||
from searx.url_utils import urlencode
|
from searx.url_utils import urlencode
|
||||||
|
from searx.utils import get_torrent_size
|
||||||
|
|
||||||
# engine dependent config
|
# engine dependent config
|
||||||
categories = ['files', 'videos', 'music']
|
categories = ['files', 'videos', 'music']
|
||||||
paging = True
|
paging = True
|
||||||
|
|
||||||
# search-url
|
# search-url
|
||||||
# https://torrentz.eu/search?f=EXAMPLE&p=6
|
# https://torrentz2.eu/search?f=EXAMPLE&p=6
|
||||||
base_url = 'https://torrentz.eu/'
|
base_url = 'https://torrentz2.eu/'
|
||||||
search_url = base_url + 'search?{query}'
|
search_url = base_url + 'search?{query}'
|
||||||
|
|
||||||
|
|
||||||
# do search-request
|
# do search-request
|
||||||
def request(query, params):
|
def request(query, params):
|
||||||
page = params['pageno'] - 1
|
page = params['pageno'] - 1
|
||||||
query = urlencode({'q': query, 'p': page})
|
query = urlencode({'f': query, 'p': page})
|
||||||
params['url'] = search_url.format(query=query)
|
params['url'] = search_url.format(query=query)
|
||||||
return params
|
return params
|
||||||
|
|
||||||
|
@ -54,22 +54,29 @@ def response(resp):
|
||||||
# extract url and remove a slash in the beginning
|
# extract url and remove a slash in the beginning
|
||||||
link = links[0].attrib.get('href').lstrip('/')
|
link = links[0].attrib.get('href').lstrip('/')
|
||||||
|
|
||||||
seed = result.xpath('./dd/span[@class="u"]/text()')[0].replace(',', '')
|
seed = 0
|
||||||
leech = result.xpath('./dd/span[@class="d"]/text()')[0].replace(',', '')
|
leech = 0
|
||||||
|
try:
|
||||||
|
seed = int(result.xpath('./dd/span[4]/text()')[0].replace(',', ''))
|
||||||
|
leech = int(result.xpath('./dd/span[5]/text()')[0].replace(',', ''))
|
||||||
|
except:
|
||||||
|
pass
|
||||||
|
|
||||||
params = {
|
params = {
|
||||||
'url': base_url + link,
|
'url': base_url + link,
|
||||||
'title': title,
|
'title': title,
|
||||||
'seed': int_or_zero(seed),
|
'seed': seed,
|
||||||
'leech': int_or_zero(leech),
|
'leech': leech,
|
||||||
'template': 'torrent.html'
|
'template': 'torrent.html'
|
||||||
}
|
}
|
||||||
|
|
||||||
# let's try to calculate the torrent size
|
# let's try to calculate the torrent size
|
||||||
try:
|
try:
|
||||||
size_str = result.xpath('./dd/span[@class="s"]/text()')[0]
|
filesize_info = result.xpath('./dd/span[3]/text()')[0]
|
||||||
size, suffix = size_str.split()
|
filesize, filesize_multiplier = filesize_info.split()
|
||||||
params['filesize'] = int(size) * get_filesize_mul(suffix)
|
filesize = get_torrent_size(filesize, filesize_multiplier)
|
||||||
|
|
||||||
|
params['filesize'] = filesize
|
||||||
except:
|
except:
|
||||||
pass
|
pass
|
||||||
|
|
||||||
|
@ -80,9 +87,8 @@ def response(resp):
|
||||||
|
|
||||||
# extract and convert creation date
|
# extract and convert creation date
|
||||||
try:
|
try:
|
||||||
date_str = result.xpath('./dd/span[@class="a"]/span')[0].attrib.get('title')
|
date_ts = result.xpath('./dd/span[2]')[0].attrib.get('title')
|
||||||
# Fri, 25 Mar 2016 16:29:01
|
date = datetime.fromtimestamp(float(date_ts))
|
||||||
date = datetime.strptime(date_str, '%a, %d %b %Y %H:%M:%S')
|
|
||||||
params['publishedDate'] = date
|
params['publishedDate'] = date
|
||||||
except:
|
except:
|
||||||
pass
|
pass
|
||||||
|
|
|
@ -552,6 +552,12 @@ engines:
|
||||||
timeout : 6.0
|
timeout : 6.0
|
||||||
disabled : True
|
disabled : True
|
||||||
|
|
||||||
|
- name : torrentz
|
||||||
|
engine : torrentz
|
||||||
|
shortcut : tor
|
||||||
|
url: https://torrentz2.eu/
|
||||||
|
timeout : 3.0
|
||||||
|
|
||||||
- name : twitter
|
- name : twitter
|
||||||
engine : twitter
|
engine : twitter
|
||||||
shortcut : tw
|
shortcut : tw
|
||||||
|
|
|
@ -14,7 +14,7 @@ class TestTorrentzEngine(SearxTestCase):
|
||||||
params = torrentz.request(query, dic)
|
params = torrentz.request(query, dic)
|
||||||
self.assertTrue('url' in params)
|
self.assertTrue('url' in params)
|
||||||
self.assertTrue(query in params['url'])
|
self.assertTrue(query in params['url'])
|
||||||
self.assertTrue('torrentz.eu' in params['url'])
|
self.assertTrue('torrentz2.eu' in params['url'])
|
||||||
|
|
||||||
def test_response(self):
|
def test_response(self):
|
||||||
resp = mock.Mock(text='<html></html>')
|
resp = mock.Mock(text='<html></html>')
|
||||||
|
@ -30,13 +30,11 @@ class TestTorrentzEngine(SearxTestCase):
|
||||||
books ebooks
|
books ebooks
|
||||||
</dt>
|
</dt>
|
||||||
<dd>
|
<dd>
|
||||||
<span class="v">1</span>
|
<span>1</span>
|
||||||
<span class="a">
|
<span title="1503595924">5 hours</span>
|
||||||
<span title="Sun, 22 Nov 2015 03:01:42">4 months</span>
|
<span>30 MB</span>
|
||||||
</span>
|
<span>14</span>
|
||||||
<span class="s">30 MB</span>
|
<span>1</span>
|
||||||
<span class="u">14</span>
|
|
||||||
<span class="d">1</span>
|
|
||||||
</dd>
|
</dd>
|
||||||
</dl>
|
</dl>
|
||||||
|
|
||||||
|
@ -48,13 +46,11 @@ class TestTorrentzEngine(SearxTestCase):
|
||||||
books ebooks
|
books ebooks
|
||||||
</dt>
|
</dt>
|
||||||
<dd>
|
<dd>
|
||||||
<span class="v">1</span>
|
<span>1</span>
|
||||||
<span class="a">
|
<span title="1503595924 aaa">5 hours</span>
|
||||||
<span title="Sun, 2124091j0j190gm42">4 months</span>
|
<span>30MB</span>
|
||||||
</span>
|
<span>5,555</span>
|
||||||
<span class="s">30MB</span>
|
<span>1,234,567</span>
|
||||||
<span class="u">5,555</span>
|
|
||||||
<span class="d">1,234,567</span>
|
|
||||||
</dd>
|
</dd>
|
||||||
</dl>
|
</dl>
|
||||||
</div>
|
</div>
|
||||||
|
@ -68,10 +64,10 @@ class TestTorrentzEngine(SearxTestCase):
|
||||||
|
|
||||||
# testing against the first result
|
# testing against the first result
|
||||||
r = results[0]
|
r = results[0]
|
||||||
self.assertEqual(r['url'], 'https://torrentz.eu/4362e08b1d80e1820fb2550b752f9f3126fe76d6')
|
self.assertEqual(r['url'], 'https://torrentz2.eu/4362e08b1d80e1820fb2550b752f9f3126fe76d6')
|
||||||
self.assertEqual(r['title'], 'Completely valid info books ebooks')
|
self.assertEqual(r['title'], 'Completely valid info books ebooks')
|
||||||
# 22 Nov 2015 03:01:42
|
# 22 Nov 2015 03:01:42
|
||||||
self.assertEqual(r['publishedDate'], datetime(2015, 11, 22, 3, 1, 42))
|
self.assertEqual(r['publishedDate'], datetime.fromtimestamp(1503595924))
|
||||||
self.assertEqual(r['seed'], 14)
|
self.assertEqual(r['seed'], 14)
|
||||||
self.assertEqual(r['leech'], 1)
|
self.assertEqual(r['leech'], 1)
|
||||||
self.assertEqual(r['filesize'], 30 * 1024 * 1024)
|
self.assertEqual(r['filesize'], 30 * 1024 * 1024)
|
||||||
|
@ -79,7 +75,7 @@ class TestTorrentzEngine(SearxTestCase):
|
||||||
|
|
||||||
# testing against the second result
|
# testing against the second result
|
||||||
r = results[1]
|
r = results[1]
|
||||||
self.assertEqual(r['url'], 'https://torrentz.eu/poaskdpokaspod')
|
self.assertEqual(r['url'], 'https://torrentz2.eu/poaskdpokaspod')
|
||||||
self.assertEqual(r['title'], 'Invalid hash and date and filesize books ebooks')
|
self.assertEqual(r['title'], 'Invalid hash and date and filesize books ebooks')
|
||||||
self.assertEqual(r['seed'], 5555)
|
self.assertEqual(r['seed'], 5555)
|
||||||
self.assertEqual(r['leech'], 1234567)
|
self.assertEqual(r['leech'], 1234567)
|
||||||
|
|
Loading…
Reference in a new issue