1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-19 19:00:10 +01:00

add comments to google-engines

This commit is contained in:
Thomas Pointhuber 2014-09-01 15:10:05 +02:00
parent cdf74fe563
commit 144f89bf78
3 changed files with 77 additions and 17 deletions

View File

@ -1,37 +1,57 @@
#!/usr/bin/env python ## Google (Web)
#
# @website https://www.google.com
# @provide-api yes (https://developers.google.com/web-search/docs/), deprecated!
#
# @using-api yes
# @results JSON
# @stable yes (but deprecated)
# @parse url, title, content
from urllib import urlencode from urllib import urlencode
from json import loads from json import loads
# engine dependent config
categories = ['general'] categories = ['general']
url = 'https://ajax.googleapis.com/'
search_url = url + 'ajax/services/search/web?v=2.0&start={offset}&rsz=large&safe=off&filter=off&{query}&hl={language}' # noqa
paging = True paging = True
language_support = True language_support = True
# search-url
url = 'https://ajax.googleapis.com/'
search_url = url + 'ajax/services/search/web?v=2.0&start={offset}&rsz=large&safe=off&filter=off&{query}&hl={language}' # noqa
# do search-request
def request(query, params): def request(query, params):
offset = (params['pageno'] - 1) * 8 offset = (params['pageno'] - 1) * 8
language = 'en-US' language = 'en-US'
if params['language'] != 'all': if params['language'] != 'all':
language = params['language'].replace('_', '-') language = params['language'].replace('_', '-')
params['url'] = search_url.format(offset=offset, params['url'] = search_url.format(offset=offset,
query=urlencode({'q': query}), query=urlencode({'q': query}),
language=language) language=language)
return params return params
# get response from search-request
def response(resp): def response(resp):
results = [] results = []
search_res = loads(resp.text) search_res = loads(resp.text)
# return empty array if there are no results
if not search_res.get('responseData', {}).get('results'): if not search_res.get('responseData', {}).get('results'):
return [] return []
# parse results
for result in search_res['responseData']['results']: for result in search_res['responseData']['results']:
# append result
results.append({'url': result['unescapedUrl'], results.append({'url': result['unescapedUrl'],
'title': result['titleNoFormatting'], 'title': result['titleNoFormatting'],
'content': result['content']}) 'content': result['content']})
# return results
return results return results

View File

@ -1,37 +1,58 @@
#!/usr/bin/env python ## Google (Images)
#
# @website https://www.google.com
# @provide-api yes (https://developers.google.com/web-search/docs/), deprecated!
#
# @using-api yes
# @results JSON
# @stable yes (but deprecated)
# @parse url, title, img_src
from urllib import urlencode from urllib import urlencode
from json import loads from json import loads
# engine dependent config
categories = ['images'] categories = ['images']
paging = True
# search-url
url = 'https://ajax.googleapis.com/' url = 'https://ajax.googleapis.com/'
search_url = url + 'ajax/services/search/images?v=1.0&start={offset}&rsz=large&safe=off&filter=off&{query}' # noqa search_url = url + 'ajax/services/search/images?v=1.0&start={offset}&rsz=large&safe=off&filter=off&{query}' # noqa
paging = True
# do search-request
def request(query, params): def request(query, params):
offset = (params['pageno'] - 1) * 8 offset = (params['pageno'] - 1) * 8
params['url'] = search_url.format(query=urlencode({'q': query}), params['url'] = search_url.format(query=urlencode({'q': query}),
offset=offset) offset=offset)
return params return params
# get response from search-request
def response(resp): def response(resp):
results = [] results = []
search_res = loads(resp.text) search_res = loads(resp.text)
if not search_res.get('responseData'):
return [] # return empty array if there are no results
if not search_res['responseData'].get('results'): if not search_res.get('responseData', {}).get('results'):
return [] return []
# parse results
for result in search_res['responseData']['results']: for result in search_res['responseData']['results']:
href = result['originalContextUrl'] href = result['originalContextUrl']
title = result['title'] title = result['title']
if not result['url']: if not result['url']:
continue continue
# append result
results.append({'url': href, results.append({'url': href,
'title': title, 'title': title,
'content': '', 'content': '',
'img_src': result['url'], 'img_src': result['url'],
'template': 'images.html'}) 'template': 'images.html'})
# return results
return results return results

View File

@ -1,43 +1,62 @@
#!/usr/bin/env python ## Google (News)
#
# @website https://www.google.com
# @provide-api yes (https://developers.google.com/web-search/docs/), deprecated!
#
# @using-api yes
# @results JSON
# @stable yes (but deprecated)
# @parse url, title, content, publishedDate
from urllib import urlencode from urllib import urlencode
from json import loads from json import loads
from dateutil import parser from dateutil import parser
# search-url
categories = ['news'] categories = ['news']
url = 'https://ajax.googleapis.com/'
search_url = url + 'ajax/services/search/news?v=2.0&start={offset}&rsz=large&safe=off&filter=off&{query}&hl={language}' # noqa
paging = True paging = True
language_support = True language_support = True
# engine dependent config
url = 'https://ajax.googleapis.com/'
search_url = url + 'ajax/services/search/news?v=2.0&start={offset}&rsz=large&safe=off&filter=off&{query}&hl={language}' # noqa
# do search-request
def request(query, params): def request(query, params):
offset = (params['pageno'] - 1) * 8 offset = (params['pageno'] - 1) * 8
language = 'en-US' language = 'en-US'
if params['language'] != 'all': if params['language'] != 'all':
language = params['language'].replace('_', '-') language = params['language'].replace('_', '-')
params['url'] = search_url.format(offset=offset, params['url'] = search_url.format(offset=offset,
query=urlencode({'q': query}), query=urlencode({'q': query}),
language=language) language=language)
return params return params
# get response from search-request
def response(resp): def response(resp):
results = [] results = []
search_res = loads(resp.text) search_res = loads(resp.text)
# return empty array if there are no results
if not search_res.get('responseData', {}).get('results'): if not search_res.get('responseData', {}).get('results'):
return [] return []
# parse results
for result in search_res['responseData']['results']: for result in search_res['responseData']['results']:
# parse publishedDate
# Mon, 10 Mar 2014 16:26:15 -0700
publishedDate = parser.parse(result['publishedDate']) publishedDate = parser.parse(result['publishedDate'])
# append result
results.append({'url': result['unescapedUrl'], results.append({'url': result['unescapedUrl'],
'title': result['titleNoFormatting'], 'title': result['titleNoFormatting'],
'publishedDate': publishedDate, 'publishedDate': publishedDate,
'content': result['content']}) 'content': result['content']})
# return results
return results return results