Ponysearch/searx/engines/deviantart.py

83 lines
2.4 KiB
Python
Raw Normal View History

"""
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
"""
2014-09-02 16:48:18 +02:00
2014-02-05 20:24:31 +01:00
from lxml import html
import re
from urllib.parse import urlencode
from searx.utils import extract_text
2013-10-20 11:12:10 +02:00
2014-09-02 16:48:18 +02:00
# engine dependent config
2013-10-20 11:12:10 +02:00
categories = ['images']
2014-09-02 16:48:18 +02:00
paging = True
2016-07-19 10:06:47 +02:00
time_range_support = True
2013-10-20 11:12:10 +02:00
2014-09-02 16:48:18 +02:00
# search-url
2013-10-20 11:12:10 +02:00
base_url = 'https://www.deviantart.com/'
2019-10-16 14:42:31 +02:00
search_url = base_url + 'search?page={page}&{query}'
2016-07-19 10:06:47 +02:00
time_range_url = '&order={range}'
time_range_dict = {'day': 11,
'week': 14,
'month': 15}
2014-01-30 00:09:47 +01:00
2014-01-20 02:31:20 +01:00
2014-09-02 16:48:18 +02:00
# do search-request
2013-10-20 11:12:10 +02:00
def request(query, params):
if params['time_range'] and params['time_range'] not in time_range_dict:
return params
2019-10-16 14:42:31 +02:00
params['url'] = search_url.format(page=params['pageno'],
2014-01-30 00:09:47 +01:00
query=urlencode({'q': query}))
2016-07-26 00:22:05 +02:00
if params['time_range'] in time_range_dict:
2016-07-19 10:06:47 +02:00
params['url'] += time_range_url.format(range=time_range_dict[params['time_range']])
2014-09-02 16:48:18 +02:00
2013-10-20 11:12:10 +02:00
return params
2014-09-02 16:48:18 +02:00
# get response from search-request
2013-10-20 11:12:10 +02:00
def response(resp):
results = []
2014-09-02 16:48:18 +02:00
# return empty array if a redirection code is returned
2013-10-20 11:12:10 +02:00
if resp.status_code == 302:
2014-09-02 16:48:18 +02:00
return []
2013-10-20 11:12:10 +02:00
dom = html.fromstring(resp.text)
2015-01-17 19:24:35 +01:00
2014-09-02 16:48:18 +02:00
# parse results
2019-10-16 14:42:31 +02:00
for row in dom.xpath('//div[contains(@data-hook, "content_row")]'):
for result in row.xpath('./div'):
link = result.xpath('.//a[@data-hook="deviation_link"]')[0]
url = link.attrib.get('href')
title = link.attrib.get('title')
thumbnail_src = result.xpath('.//img')[0].attrib.get('src')
img_src = thumbnail_src
# 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)
# append result
results.append({'url': url,
'title': title,
'img_src': img_src,
'thumbnail_src': thumbnail_src,
'template': 'images.html'})
2014-09-02 16:48:18 +02:00
# return results
2013-10-20 11:12:10 +02:00
return results