1
0
Fork 0
mirror of https://github.com/YunoHost-Apps/searx_ynh.git synced 2024-09-03 20:16:30 +02:00
searx_ynh/sources/engines/www500px.py

65 lines
1.8 KiB
Python
Raw Normal View History

2015-02-16 19:07:27 +01:00
## 500px (Images)
#
# @website https://500px.com
# @provide-api yes (https://developers.500px.com/)
#
# @using-api no
# @results HTML
# @stable no (HTML can change)
# @parse url, title, thumbnail, img_src, content
#
# @todo rewrite to api
from urllib import urlencode
from urlparse import urljoin
from lxml import html
import re
from searx.engines.xpath import extract_text
# engine dependent config
categories = ['images']
paging = True
# search-url
base_url = 'https://500px.com'
search_url = base_url + '/search?search?page={pageno}&type=photos&{query}'
# do search-request
def request(query, params):
params['url'] = search_url.format(pageno=params['pageno'],
query=urlencode({'q': query}))
return params
# get response from search-request
def response(resp):
results = []
dom = html.fromstring(resp.text)
regex = re.compile('3\.jpg.*$')
# parse results
for result in dom.xpath('//div[@class="photo"]'):
link = result.xpath('.//a')[0]
url = urljoin(base_url, link.attrib.get('href'))
title = extract_text(result.xpath('.//div[@class="title"]'))
thumbnail_src = link.xpath('.//img')[0].attrib.get('src')
# To have a bigger thumbnail, uncomment the next line
# thumbnail_src = regex.sub('4.jpg', thumbnail_src)
content = extract_text(result.xpath('.//div[@class="info"]'))
img_src = regex.sub('2048.jpg', thumbnail_src)
# append result
results.append({'url': url,
'title': title,
'img_src': img_src,
'content': content,
'thumbnail_src': thumbnail_src,
'template': 'images.html'})
# return results
return results