1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-09 06:30:10 +01:00
searxng/searx/engines/acgsou.py

74 lines
2.3 KiB
Python
Raw Normal View History

2018-04-26 21:42:31 +02:00
"""
Acgsou (Japanese Animation/Music/Comics Bittorrent tracker)
@website https://www.acgsou.com/
@provide-api no
@using-api no
@results HTML
@stable no (HTML can change)
@parse url, title, content, seed, leech, torrentfile
"""
from urllib.parse import urlencode
2018-04-26 21:42:31 +02:00
from lxml import html
from searx.utils import extract_text, get_torrent_size
2018-04-26 21:42:31 +02:00
# engine dependent config
categories = ['files', 'images', 'videos', 'music']
paging = True
# search-url
2018-05-03 07:34:21 +02:00
base_url = 'http://www.acgsou.com/'
2018-04-26 21:42:31 +02:00
search_url = base_url + 'search.php?{query}&page={offset}'
# xpath queries
xpath_results = '//table[contains(@class, "list_style table_fixed")]//tr[not(th)]'
xpath_category = './/td[2]/a[1]'
xpath_title = './/td[3]/a[last()]'
xpath_torrent_links = './/td[3]/a'
xpath_filesize = './/td[4]/text()'
2018-04-27 07:29:17 +02:00
2018-04-26 21:42:31 +02:00
def request(query, params):
query = urlencode({'keyword': query})
params['url'] = search_url.format(query=query, offset=params['pageno'])
return params
2018-04-27 07:29:17 +02:00
2018-04-26 21:42:31 +02:00
def response(resp):
2018-04-27 07:36:11 +02:00
results = []
2018-04-26 21:42:31 +02:00
dom = html.fromstring(resp.text)
2018-04-27 07:29:17 +02:00
for result in dom.xpath(xpath_results):
2018-04-26 21:42:31 +02:00
# defaults
filesize = 0
magnet_link = "magnet:?xt=urn:btih:{}&tr=http://tracker.acgsou.com:2710/announce"
try:
category = extract_text(result.xpath(xpath_category)[0])
except:
pass
page_a = result.xpath(xpath_title)[0]
title = extract_text(page_a)
href = base_url + page_a.attrib.get('href')
2018-04-27 07:23:58 +02:00
2018-04-26 21:42:31 +02:00
magnet_link = magnet_link.format(page_a.attrib.get('href')[5:-5])
try:
filesize_info = result.xpath(xpath_filesize)[0]
filesize = filesize_info[:-2]
filesize_multiplier = filesize_info[-2:]
filesize = get_torrent_size(filesize, filesize_multiplier)
2018-04-27 07:29:17 +02:00
except:
2018-04-26 21:42:31 +02:00
pass
2018-04-27 14:36:15 +02:00
# I didn't add download/seed/leech count since as I figured out they are generated randomly everytime
content = 'Category: "{category}".'
2018-04-26 21:42:31 +02:00
content = content.format(category=category)
2018-04-27 07:29:17 +02:00
2018-04-26 21:42:31 +02:00
results.append({'url': href,
'title': title,
'content': content,
'filesize': filesize,
'magnetlink': magnet_link,
'template': 'torrent.html'})
return results