mirror of
https://github.com/searxng/searxng.git
synced 2024-11-23 04:27:46 +01:00
115 lines
3.3 KiB
Python
115 lines
3.3 KiB
Python
# Yacy (Web, Images, Videos, Music, Files)
|
|
#
|
|
# @website http://yacy.net
|
|
# @provide-api yes
|
|
# (http://www.yacy-websuche.de/wiki/index.php/Dev:APIyacysearch)
|
|
#
|
|
# @using-api yes
|
|
# @results JSON
|
|
# @stable yes
|
|
# @parse (general) url, title, content, publishedDate
|
|
# @parse (images) url, title, img_src
|
|
#
|
|
# @todo parse video, audio and file results
|
|
|
|
from json import loads
|
|
from dateutil import parser
|
|
from urllib.parse import urlencode
|
|
|
|
from requests.auth import HTTPDigestAuth
|
|
|
|
from searx.utils import html_to_text
|
|
|
|
# engine dependent config
|
|
categories = ['general', 'images'] # TODO , 'music', 'videos', 'files'
|
|
paging = True
|
|
language_support = True
|
|
number_of_results = 5
|
|
http_digest_auth_user = ""
|
|
http_digest_auth_pass = ""
|
|
|
|
# search-url
|
|
base_url = 'http://localhost:8090'
|
|
search_url = '/yacysearch.json?{query}'\
|
|
'&startRecord={offset}'\
|
|
'&maximumRecords={limit}'\
|
|
'&contentdom={search_type}'\
|
|
'&resource=global'
|
|
|
|
# yacy specific type-definitions
|
|
search_types = {'general': 'text',
|
|
'images': 'image',
|
|
'files': 'app',
|
|
'music': 'audio',
|
|
'videos': 'video'}
|
|
|
|
|
|
# do search-request
|
|
def request(query, params):
|
|
offset = (params['pageno'] - 1) * number_of_results
|
|
search_type = search_types.get(params.get('category'), '0')
|
|
|
|
params['url'] = base_url +\
|
|
search_url.format(query=urlencode({'query': query}),
|
|
offset=offset,
|
|
limit=number_of_results,
|
|
search_type=search_type)
|
|
|
|
if http_digest_auth_user and http_digest_auth_pass:
|
|
params['auth'] = HTTPDigestAuth(http_digest_auth_user, http_digest_auth_pass)
|
|
|
|
# add language tag if specified
|
|
if params['language'] != 'all':
|
|
params['url'] += '&lr=lang_' + params['language'].split('-')[0]
|
|
|
|
return params
|
|
|
|
|
|
# get response from search-request
|
|
def response(resp):
|
|
results = []
|
|
|
|
raw_search_results = loads(resp.text)
|
|
|
|
# return empty array if there are no results
|
|
if not raw_search_results:
|
|
return []
|
|
|
|
search_results = raw_search_results.get('channels', [])
|
|
|
|
if len(search_results) == 0:
|
|
return []
|
|
|
|
for result in search_results[0].get('items', []):
|
|
# parse image results
|
|
if resp.search_params.get('category') == 'images':
|
|
|
|
result_url = ''
|
|
if 'url' in result:
|
|
result_url = result['url']
|
|
elif 'link' in result:
|
|
result_url = result['link']
|
|
else:
|
|
continue
|
|
|
|
# append result
|
|
results.append({'url': result_url,
|
|
'title': result['title'],
|
|
'content': '',
|
|
'img_src': result['image'],
|
|
'template': 'images.html'})
|
|
|
|
# parse general results
|
|
else:
|
|
publishedDate = parser.parse(result['pubDate'])
|
|
|
|
# append result
|
|
results.append({'url': result['link'],
|
|
'title': result['title'],
|
|
'content': html_to_text(result['description']),
|
|
'publishedDate': publishedDate})
|
|
|
|
# TODO parse video, audio and file results
|
|
|
|
return results
|