2019-05-04 22:38:06 +03:00
|
|
|
from . import Searcher, urljoin_partial, ResultItem
|
|
|
|
|
|
|
|
|
|
class SearchEngine(Searcher):
|
2019-05-05 10:16:32 +03:00
|
|
|
#base_url = 'http://new-tor.top'
|
|
|
|
|
base_url = 'http://rutor.info'
|
2019-05-04 22:38:06 +03:00
|
|
|
search_path = '/search/0/0/100/2/{}'
|
|
|
|
|
name = 'RuTor.org'
|
|
|
|
|
icon = 'searcher_rutor.png'
|
|
|
|
|
def process(self, body):
|
|
|
|
|
url_constructor = urljoin_partial(self.base_url)
|
|
|
|
|
rows = list(filter(lambda x: len(x.findall('.//a')) == 3, body.findall('.//tr')))
|
|
|
|
|
for r in rows:
|
|
|
|
|
links = r.findall('.//a')
|
|
|
|
|
url = url_constructor(links[0].get('href').strip())
|
|
|
|
|
title = links[2].text
|
|
|
|
|
seeders = int(list(r.findall('.//span[@class="green"]')[0].itertext())[0].strip())
|
|
|
|
|
leachers = int(list(r.findall('.//span[@class="red"]')[0].itertext())[0].strip())
|
|
|
|
|
size = list(
|
|
|
|
|
list(filter(lambda x: len(list(x.itertext())) == 1 and list(x.itertext())[0].strip().endswith(('GB', 'MB')),
|
|
|
|
|
r.findall('.//td'))
|
|
|
|
|
)[0].itertext()
|
|
|
|
|
)[0].strip()
|
|
|
|
|
yield ResultItem(url, title, size, seeders, leachers, self.icon, self.cookies, self.base_url)
|
