searxng/searx/engines/doku.py

86 lines
2.2 KiB
Python
Raw Normal View History

2016-04-03 20:03:41 +00:00
# Doku Wiki
#
# @website https://www.dokuwiki.org/
# @provide-api yes
# (https://www.dokuwiki.org/devel:xmlrpc)
#
# @using-api no
# @results HTML
# @stable yes
# @parse (general) url, title, content
from lxml.html import fromstring
from searx.engines.xpath import extract_text
from searx.utils import eval_xpath
2016-11-30 17:43:03 +00:00
from searx.url_utils import urlencode
2016-04-03 20:03:41 +00:00
# engine dependent config
categories = ['general'] # TODO , 'images', 'music', 'videos', 'files'
paging = False
language_support = False
number_of_results = 5
# search-url
# Doku is OpenSearch compatible
base_url = 'http://localhost:8090'
search_url = '/?do=search'\
2016-04-05 11:31:49 +00:00
'&{query}'
2016-04-03 20:03:41 +00:00
# TODO '&startRecord={offset}'\
# TODO '&maximumRecords={limit}'\
2016-04-03 20:03:41 +00:00
# do search-request
def request(query, params):
params['url'] = base_url +\
2016-04-05 11:31:49 +00:00
search_url.format(query=urlencode({'id': query}))
2016-04-03 20:03:41 +00:00
return params
# get response from search-request
def response(resp):
results = []
doc = fromstring(resp.text)
# parse results
# Quickhits
for r in eval_xpath(doc, '//div[@class="search_quickresult"]/ul/li'):
2016-04-03 20:03:41 +00:00
try:
res_url = eval_xpath(r, './/a[@class="wikilink1"]/@href')[-1]
2016-04-03 20:03:41 +00:00
except:
continue
if not res_url:
continue
title = extract_text(eval_xpath(r, './/a[@class="wikilink1"]/@title'))
2016-04-03 20:03:41 +00:00
# append result
results.append({'title': title,
'content': "",
'url': base_url + res_url})
# Search results
for r in eval_xpath(doc, '//dl[@class="search_results"]/*'):
2016-04-03 20:03:41 +00:00
try:
if r.tag == "dt":
res_url = eval_xpath(r, './/a[@class="wikilink1"]/@href')[-1]
title = extract_text(eval_xpath(r, './/a[@class="wikilink1"]/@title'))
2016-04-03 20:03:41 +00:00
elif r.tag == "dd":
content = extract_text(eval_xpath(r, '.'))
2016-04-03 20:03:41 +00:00
# append result
results.append({'title': title,
'content': content,
'url': base_url + res_url})
except:
continue
if not res_url:
continue
# return results
return results