1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-05 04:40:11 +01:00
searxng/searx/engines/www1x.py

59 lines
1.4 KiB
Python
Raw Normal View History

"""
1x (Images)
@website http://1x.com/
@provide-api no
@using-api no
@results HTML
@stable no (HTML can change)
@parse url, title, thumbnail, img_src, content
"""
from lxml import html
from urllib.parse import urlencode, urljoin
2019-10-16 13:27:05 +02:00
from searx.engines.xpath import extract_text
# engine dependent config
categories = ['images']
paging = False
# search-url
base_url = 'https://1x.com'
2016-01-18 12:47:31 +01:00
search_url = base_url + '/backend/search.php?{query}'
# do search-request
def request(query, params):
params['url'] = search_url.format(query=urlencode({'q': query}))
return params
# get response from search-request
def response(resp):
results = []
2019-10-16 13:27:05 +02:00
dom = html.fromstring(resp.text)
for res in dom.xpath('//div[@class="List-item MainListing"]'):
# processed start and end of link
2019-10-16 13:27:05 +02:00
link = res.xpath('//a')[0]
url = urljoin(base_url, link.attrib.get('href'))
2019-10-16 13:27:05 +02:00
title = extract_text(link)
2019-10-16 13:27:05 +02:00
thumbnail_src = urljoin(base_url, res.xpath('.//img')[0].attrib['src'])
# TODO: get image with higher resolution
img_src = thumbnail_src
# append result
results.append({'url': url,
'title': title,
'img_src': img_src,
'content': '',
'thumbnail_src': thumbnail_src,
'template': 'images.html'})
# return results
return results