devol
/
searx
mirror of https://github.com/searx/searx
1
0
Fork 0
Code Issues Releases Wiki Activity

[fix] pep8

This commit is contained in:
Adam Tauber 2014-12-05 20:03:16 +01:00
parent d959cb1c05
commit 611f4e2a86
1 changed files with 22 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
searx/engines/google.py
View File

@ -1,15 +1,15 @@
## Google (Web)
#
# Google (Web)
#
# @website https://www.google.com
# @provide-api yes (https://developers.google.com/custom-search/)
#
#
# @using-api no
# @results HTML
# @stable no (HTML can change)
# @parse url, title, content, suggestion
from urllib import urlencode
from urlparse import unquote,urlparse,parse_qsl
from urlparse import urlparse, parse_qsl
from lxml import html
from searx.engines.xpath import extract_text, extract_url
@ -23,10 +23,13 @@ google_hostname = 'www.google.com'
search_path = '/search'
redirect_path = '/url'
images_path = '/images'
search_url = 'https://' + google_hostname + search_path + '?{query}&start={offset}&gbv=1'
search_url = ('https://' +
google_hostname +
search_path +
'?{query}&start={offset}&gbv=1')
# specific xpath variables
results_xpath= '//li[@class="g"]'
results_xpath = '//li[@class="g"]'
url_xpath = './/h3/a/@href'
title_xpath = './/h3'
content_xpath = './/span[@class="st"]'
@ -36,15 +39,18 @@ images_xpath = './/div/a'
image_url_xpath = './@href'
image_img_src_xpath = './img/@src'
# remove google-specific tracking-url
def parse_url(url_string):
parsed_url = urlparse(url_string)
if parsed_url.netloc in [google_hostname, ''] and parsed_url.path==redirect_path:
if (parsed_url.netloc in [google_hostname, '']
and parsed_url.path == redirect_path):
query = dict(parse_qsl(parsed_url.query))
return query['q']
else:
return url_string
# do search-request
def request(query, params):
offset = (params['pageno'] - 1) * 10
@ -52,7 +58,7 @@ def request(query, params):
if params['language'] == 'all':
language = 'en'
else:
language = params['language'].replace('_','-').lower()
language = params['language'].replace('_', '-').lower()
params['url'] = search_url.format(offset=offset,
query=urlencode({'q': query}))
@ -74,19 +80,21 @@ def response(resp):
try:
url = parse_url(extract_url(result.xpath(url_xpath), search_url))
parsed_url = urlparse(url)
if parsed_url.netloc==google_hostname and parsed_url.path==search_path:
if (parsed_url.netloc == google_hostname
and parsed_url.path == search_path):
# remove the link to google news
continue
if parsed_url.netloc==google_hostname and parsed_url.path==images_path:
if (parsed_url.netloc == google_hostname
and parsed_url.path == images_path):
# images result
results = results + parse_images(result)
else:
# normal result
content = extract_text(result.xpath(content_xpath)[0])
# append result
results.append({'url': url,
'title': title,
results.append({'url': url,
'title': title,
'content': content})
except:
continue
@ -99,12 +107,13 @@ def response(resp):
# return results
return results
def parse_images(result):
results = []
for image in result.xpath(images_xpath):
url = parse_url(extract_text(image.xpath(image_url_xpath)[0]))
img_src = extract_text(image.xpath(image_img_src_xpath)[0])
# append result
results.append({'url': url,
'title': '',