1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-16 17:40:11 +01:00
searxng/searx/engines/framalibre.py
2020-10-02 18:13:56 +02:00

70 lines
2.0 KiB
Python

"""
FramaLibre (It)
@website https://framalibre.org/
@provide-api no
@using-api no
@results HTML
@stable no (HTML can change)
@parse url, title, content, thumbnail, img_src
"""
from html import escape
from urllib.parse import urljoin, urlencode
from lxml import html
from searx.utils import extract_text
# engine dependent config
categories = ['it']
paging = True
# search-url
base_url = 'https://framalibre.org/'
search_url = base_url + 'recherche-par-crit-res?{query}&page={offset}'
# specific xpath variables
results_xpath = '//div[@class="nodes-list-row"]/div[contains(@typeof,"sioc:Item")]'
link_xpath = './/h3[@class="node-title"]/a[@href]'
thumbnail_xpath = './/img[@class="media-object img-responsive"]/@src'
content_xpath = './/div[@class="content"]//p'
# do search-request
def request(query, params):
offset = (params['pageno'] - 1)
params['url'] = search_url.format(query=urlencode({'keys': query}),
offset=offset)
return params
# get response from search-request
def response(resp):
results = []
dom = html.fromstring(resp.text)
# parse results
for result in dom.xpath(results_xpath):
link = result.xpath(link_xpath)[0]
href = urljoin(base_url, link.attrib.get('href'))
# there's also a span (class="rdf-meta element-hidden" property="dc:title")'s content property for this...
title = escape(extract_text(link))
thumbnail_tags = result.xpath(thumbnail_xpath)
thumbnail = None
if len(thumbnail_tags) > 0:
thumbnail = extract_text(thumbnail_tags[0])
if thumbnail[0] == '/':
thumbnail = base_url + thumbnail
content = escape(extract_text(result.xpath(content_xpath)))
# append result
results.append({'url': href,
'title': title,
'img_src': thumbnail,
'content': content})
# return results
return results