mirror of
https://github.com/searxng/searxng.git
synced 2024-11-05 12:50:11 +01:00
3a1c5876b1
Unfortunately, it is quite slow so it is disabled. Furthermore, the display of number of files is wrong on digbt.org, so it is not displayed on searx.
59 lines
1.7 KiB
Python
59 lines
1.7 KiB
Python
"""
|
|
DigBT (Videos, Music, Files)
|
|
|
|
@website https://digbt.org
|
|
@provide-api no
|
|
|
|
@using-api no
|
|
@results HTML (using search portal)
|
|
@stable no (HTML can change)
|
|
@parse url, title, content, magnetlink
|
|
"""
|
|
|
|
from urlparse import urljoin
|
|
from lxml import html
|
|
from searx.engines.xpath import extract_text
|
|
from searx.utils import get_torrent_size
|
|
|
|
categories = ['videos', 'music', 'files']
|
|
paging = True
|
|
|
|
URL = 'https://digbt.org'
|
|
SEARCH_URL = URL + '/search/{query}-time-{pageno}'
|
|
FILESIZE = 3
|
|
FILESIZE_MULTIPLIER = 4
|
|
|
|
|
|
def request(query, params):
|
|
params['url'] = SEARCH_URL.format(query=query, pageno=params['pageno'])
|
|
|
|
return params
|
|
|
|
|
|
def response(resp):
|
|
dom = html.fromstring(resp.content)
|
|
search_res = dom.xpath('.//td[@class="x-item"]')
|
|
|
|
if not search_res:
|
|
return list()
|
|
|
|
results = list()
|
|
for result in search_res:
|
|
url = urljoin(URL, result.xpath('.//a[@title]/@href')[0])
|
|
title = result.xpath('.//a[@title]/text()')[0]
|
|
content = extract_text(result.xpath('.//div[@class="files"]'))
|
|
files_data = extract_text(result.xpath('.//div[@class="tail"]')).split()
|
|
filesize = get_torrent_size(files_data[FILESIZE], files_data[FILESIZE_MULTIPLIER])
|
|
magnetlink = result.xpath('.//div[@class="tail"]//a[@class="title"]/@href')[0]
|
|
|
|
results.append({'url': url,
|
|
'title': title,
|
|
'content': content,
|
|
'filesize': filesize,
|
|
'magnetlink': magnetlink,
|
|
'seed': 'N/A',
|
|
'leech': 'N/A',
|
|
'template': 'torrent.html'})
|
|
|
|
return results
|