mirror of https://github.com/searx/searx
[enh] piratebay engine added
This commit is contained in:
parent
8520be3cd6
commit
9ad8013a45
|
@ -0,0 +1,34 @@
|
||||||
|
from lxml import html
|
||||||
|
from urlparse import urljoin
|
||||||
|
from cgi import escape
|
||||||
|
from urllib import quote
|
||||||
|
|
||||||
|
categories = ['videos', 'music']
|
||||||
|
|
||||||
|
base_url = 'https://thepiratebay.sx/'
|
||||||
|
search_url = base_url + 'search/{search_term}/0/99/{search_type}'
|
||||||
|
search_types = {'videos': '200'
|
||||||
|
,'music' : '100'
|
||||||
|
}
|
||||||
|
|
||||||
|
def request(query, params):
|
||||||
|
global search_url, search_types
|
||||||
|
# 200 is the video category
|
||||||
|
params['url'] = search_url.format(search_term=quote(query), search_type=search_types.get(params['category']))
|
||||||
|
return params
|
||||||
|
|
||||||
|
|
||||||
|
def response(resp):
|
||||||
|
global base_url
|
||||||
|
results = []
|
||||||
|
dom = html.fromstring(resp.text)
|
||||||
|
search_res = dom.xpath('//table[@id="searchResult"]//tr')
|
||||||
|
if not search_res:
|
||||||
|
return results
|
||||||
|
for result in search_res[1:]:
|
||||||
|
link = result.xpath('.//div[@class="detName"]//a')[0]
|
||||||
|
url = urljoin(base_url, link.attrib.get('href'))
|
||||||
|
title = ' '.join(link.xpath('.//text()'))
|
||||||
|
content = escape(' '.join(result.xpath('.//font[@class="detDesc"]//text()')))
|
||||||
|
results.append({'url': url, 'title': title, 'content': content})
|
||||||
|
return results
|
Loading…
Reference in New Issue