Ponysearch/searx/engines/btdigg.py

85 lines
2.5 KiB
Python
Raw Normal View History

"""
BTDigg (Videos, Music, Files)
@website https://btdig.com
@provide-api yes (on demand)
@using-api no
@results HTML (using search portal)
@stable no (HTML can change)
@parse url, title, content, seed, leech, magnetlink
"""
2015-01-21 18:02:29 +01:00
from lxml import html
from operator import itemgetter
from urllib.parse import quote, urljoin
from searx.utils import extract_text, get_torrent_size
2015-01-21 18:02:29 +01:00
# engine dependent config
categories = ['videos', 'music', 'files']
paging = True
# search-url
url = 'https://btdig.com'
2015-01-25 10:21:44 +01:00
search_url = url + '/search?q={search_term}&p={pageno}'
2015-01-21 18:02:29 +01:00
# do search-request
def request(query, params):
params['url'] = search_url.format(search_term=quote(query),
2016-01-18 12:47:31 +01:00
pageno=params['pageno'] - 1)
2015-01-21 18:02:29 +01:00
return params
# get response from search-request
def response(resp):
results = []
2016-11-30 18:43:03 +01:00
dom = html.fromstring(resp.text)
2015-01-21 18:02:29 +01:00
search_res = dom.xpath('//div[@class="one_result"]')
2015-01-21 18:02:29 +01:00
# return empty array if nothing is found
if not search_res:
return []
# parse results
for result in search_res:
link = result.xpath('.//div[@class="torrent_name"]//a')[0]
2015-01-30 19:52:44 +01:00
href = urljoin(url, link.attrib.get('href'))
title = extract_text(link)
2015-01-21 18:02:29 +01:00
excerpt = result.xpath('.//div[@class="torrent_excerpt"]')[0]
content = html.tostring(excerpt, encoding='unicode', method='text', with_tail=False)
# it is better to emit <br/> instead of |, but html tags are verboten
content = content.strip().replace('\n', ' | ')
content = ' '.join(content.split())
2015-01-21 18:02:29 +01:00
filesize = result.xpath('.//span[@class="torrent_size"]/text()')[0].split()[0]
filesize_multiplier = result.xpath('.//span[@class="torrent_size"]/text()')[0].split()[1]
files = (result.xpath('.//span[@class="torrent_files"]/text()') or ['1'])[0]
2015-01-21 18:02:29 +01:00
# convert filesize to byte if possible
filesize = get_torrent_size(filesize, filesize_multiplier)
2015-01-21 18:02:29 +01:00
# convert files to int if possible
try:
2015-01-21 18:02:29 +01:00
files = int(files)
except:
2015-01-21 18:02:29 +01:00
files = None
magnetlink = result.xpath('.//div[@class="torrent_magnet"]//a')[0].attrib['href']
2015-01-21 18:02:29 +01:00
# append result
results.append({'url': href,
'title': title,
'content': content,
'filesize': filesize,
'files': files,
'magnetlink': magnetlink,
'template': 'torrent.html'})
# return results sorted by seeder
return results