searxng/searx/engines/btdigg.py

107 lines
3.2 KiB
Python
Raw Normal View History

"""
BTDigg (Videos, Music, Files)
@website https://btdigg.org
@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 17:02:29 +00:00
from urlparse import urljoin
from cgi import escape
from urllib import quote
from lxml import html
from operator import itemgetter
from searx.engines.xpath import extract_text
# engine dependent config
categories = ['videos', 'music', 'files']
paging = True
# search-url
url = 'https://btdigg.org'
2015-01-25 09:21:44 +00:00
search_url = url + '/search?q={search_term}&p={pageno}'
2015-01-21 17:02:29 +00:00
# do search-request
def request(query, params):
params['url'] = search_url.format(search_term=quote(query),
pageno=params['pageno']-1)
return params
# get response from search-request
def response(resp):
results = []
dom = html.fromstring(resp.text)
search_res = dom.xpath('//div[@id="search_res"]/table/tr')
# return empty array if nothing is found
if not search_res:
return []
# parse results
for result in search_res:
link = result.xpath('.//td[@class="torrent_name"]//a')[0]
2015-01-30 18:52:44 +00:00
href = urljoin(url, link.attrib.get('href'))
title = escape(extract_text(link))
2015-01-21 17:02:29 +00:00
content = escape(extract_text(result.xpath('.//pre[@class="snippet"]')[0]))
content = "<br />".join(content.split("\n"))
filesize = result.xpath('.//span[@class="attr_val"]/text()')[0].split()[0]
filesize_multiplier = result.xpath('.//span[@class="attr_val"]/text()')[0].split()[1]
files = result.xpath('.//span[@class="attr_val"]/text()')[1]
seed = result.xpath('.//span[@class="attr_val"]/text()')[2]
# convert seed to int if possible
if seed.isdigit():
seed = int(seed)
else:
seed = 0
leech = 0
# convert filesize to byte if possible
try:
filesize = float(filesize)
# convert filesize to byte
if filesize_multiplier == 'TB':
filesize = int(filesize * 1024 * 1024 * 1024 * 1024)
elif filesize_multiplier == 'GB':
filesize = int(filesize * 1024 * 1024 * 1024)
elif filesize_multiplier == 'MB':
filesize = int(filesize * 1024 * 1024)
2015-01-30 18:52:44 +00:00
elif filesize_multiplier == 'KB':
2015-01-21 17:02:29 +00:00
filesize = int(filesize * 1024)
except:
filesize = None
# convert files to int if possible
if files.isdigit():
files = int(files)
else:
files = None
magnetlink = result.xpath('.//td[@class="ttth"]//a')[0].attrib['href']
# append result
results.append({'url': href,
'title': title,
'content': content,
'seed': seed,
'leech': leech,
'filesize': filesize,
'files': files,
'magnetlink': magnetlink,
'template': 'torrent.html'})
# return results sorted by seeder
return sorted(results, key=itemgetter('seed'), reverse=True)