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/searx/engines/deviantart.py

76 lines
2.1 KiB
Python
Raw Normal View History

2015-09-08 23:05:37 +02:00
"""
Deviantart (Images)
@website https://www.deviantart.com/
@provide-api yes (https://www.deviantart.com/developers/) (RSS)
@using-api no (TODO, rewrite to api)
@results HTML
@stable no (HTML can change)
@parse url, title, thumbnail_src, img_src
@todo rewrite to api
"""
2014-12-01 12:26:38 +01:00
2014-05-10 11:56:19 +02:00
from urllib import urlencode
from urlparse import urljoin
from lxml import html
2015-02-09 13:30:16 +01:00
import re
from searx.engines.xpath import extract_text
2014-05-10 11:56:19 +02:00
2014-12-01 12:26:38 +01:00
# engine dependent config
2014-05-10 11:56:19 +02:00
categories = ['images']
2014-12-01 12:26:38 +01:00
paging = True
2014-05-10 11:56:19 +02:00
2014-12-01 12:26:38 +01:00
# search-url
2014-05-10 11:56:19 +02:00
base_url = 'https://www.deviantart.com/'
2015-09-08 23:05:37 +02:00
search_url = base_url+'browse/all/?offset={offset}&{query}'
2014-05-10 11:56:19 +02:00
2014-12-01 12:26:38 +01:00
# do search-request
2014-05-10 11:56:19 +02:00
def request(query, params):
offset = (params['pageno'] - 1) * 24
2014-12-01 12:26:38 +01:00
2014-05-10 11:56:19 +02:00
params['url'] = search_url.format(offset=offset,
query=urlencode({'q': query}))
2014-12-01 12:26:38 +01:00
2014-05-10 11:56:19 +02:00
return params
2014-12-01 12:26:38 +01:00
# get response from search-request
2014-05-10 11:56:19 +02:00
def response(resp):
results = []
2014-12-01 12:26:38 +01:00
# return empty array if a redirection code is returned
2014-05-10 11:56:19 +02:00
if resp.status_code == 302:
2014-12-01 12:26:38 +01:00
return []
2014-05-10 11:56:19 +02:00
dom = html.fromstring(resp.text)
2014-12-01 12:26:38 +01:00
2015-02-09 13:30:16 +01:00
regex = re.compile('\/200H\/')
2014-12-01 12:26:38 +01:00
# parse results
2014-05-10 11:56:19 +02:00
for result in dom.xpath('//div[contains(@class, "tt-a tt-fh")]'):
link = result.xpath('.//a[contains(@class, "thumb")]')[0]
url = urljoin(base_url, link.attrib.get('href'))
2015-02-09 13:30:16 +01:00
title_links = result.xpath('.//span[@class="details"]//a[contains(@class, "t")]')
title = extract_text(title_links[0])
thumbnail_src = link.xpath('.//img')[0].attrib.get('src')
img_src = regex.sub('/', thumbnail_src)
2014-12-01 12:26:38 +01:00
2015-09-08 23:05:37 +02:00
# http to https, remove domain sharding
thumbnail_src = re.sub(r"https?://(th|fc)\d+.", "https://th01.", thumbnail_src)
thumbnail_src = re.sub(r"http://", "https://", thumbnail_src)
url = re.sub(r"http://(.*)\.deviantart\.com/", "https://\\1.deviantart.com/", url)
2014-12-01 12:26:38 +01:00
# append result
2014-05-10 11:56:19 +02:00
results.append({'url': url,
'title': title,
'img_src': img_src,
2015-02-09 13:30:16 +01:00
'thumbnail_src': thumbnail_src,
2014-05-10 11:56:19 +02:00
'template': 'images.html'})
2014-12-01 12:26:38 +01:00
# return results
2014-05-10 11:56:19 +02:00
return results