mirror of
https://github.com/searxng/searxng.git
synced 2024-11-29 14:11:02 +00:00
88 lines
2.6 KiB
Python
88 lines
2.6 KiB
Python
"""
|
|
Wikipedia (Web)
|
|
|
|
@website https://en.wikipedia.org/api/rest_v1/
|
|
@provide-api yes
|
|
|
|
@using-api yes
|
|
@results JSON
|
|
@stable yes
|
|
@parse url, infobox
|
|
"""
|
|
|
|
from json import loads
|
|
from lxml.html import fromstring
|
|
from searx.url_utils import quote
|
|
from searx.utils import match_language, searx_useragent
|
|
|
|
# search-url
|
|
search_url = u'https://{language}.wikipedia.org/api/rest_v1/page/summary/{title}'
|
|
supported_languages_url = 'https://meta.wikimedia.org/wiki/List_of_Wikipedias'
|
|
|
|
|
|
# set language in base_url
|
|
def url_lang(lang):
|
|
lang_pre = lang.split('-')[0]
|
|
if lang_pre == 'all' or lang_pre not in supported_languages and lang_pre not in language_aliases:
|
|
return 'en'
|
|
return match_language(lang, supported_languages, language_aliases).split('-')[0]
|
|
|
|
|
|
# do search-request
|
|
def request(query, params):
|
|
if query.islower():
|
|
query = query.title()
|
|
|
|
params['url'] = search_url.format(title=quote(query),
|
|
language=url_lang(params['language']))
|
|
|
|
params['headers']['User-Agent'] = searx_useragent()
|
|
|
|
return params
|
|
|
|
|
|
# get response from search-request
|
|
def response(resp):
|
|
if not resp.ok:
|
|
return []
|
|
|
|
results = []
|
|
api_result = loads(resp.text)
|
|
|
|
# skip disambiguation pages
|
|
if api_result['type'] != 'standard':
|
|
return []
|
|
|
|
title = api_result['title']
|
|
wikipedia_link = api_result['content_urls']['desktop']['page']
|
|
|
|
results.append({'url': wikipedia_link, 'title': title})
|
|
|
|
results.append({'infobox': title,
|
|
'id': wikipedia_link,
|
|
'content': api_result.get('extract', ''),
|
|
'img_src': api_result.get('thumbnail', {}).get('source'),
|
|
'urls': [{'title': 'Wikipedia', 'url': wikipedia_link}]})
|
|
|
|
return results
|
|
|
|
|
|
# get supported languages from their site
|
|
def _fetch_supported_languages(resp):
|
|
supported_languages = {}
|
|
dom = fromstring(resp.text)
|
|
tables = dom.xpath('//table[contains(@class,"sortable")]')
|
|
for table in tables:
|
|
# exclude header row
|
|
trs = table.xpath('.//tr')[1:]
|
|
for tr in trs:
|
|
td = tr.xpath('./td')
|
|
code = td[3].xpath('./a')[0].text
|
|
name = td[2].xpath('./a')[0].text
|
|
english_name = td[1].xpath('./a')[0].text
|
|
articles = int(td[4].xpath('./a/b')[0].text.replace(',', ''))
|
|
# exclude languages with too few articles
|
|
if articles >= 100:
|
|
supported_languages[code] = {"name": name, "english_name": english_name, "articles": articles}
|
|
|
|
return supported_languages
|