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

[fix] update devianart engine

This commit is contained in:
Adam Tauber 2019-10-16 14:42:31 +02:00
parent 6ca1622378
commit 7177c9e12f
1 changed files with 19 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
searx/engines/deviantart.py
View File

@ -24,7 +24,7 @@ time_range_support = True
# search-url # search-url
base_url = 'https://www.deviantart.com/' base_url = 'https://www.deviantart.com/'
search_url = base_url + 'browse/all/?offset={offset}&{query}' search_url = base_url + 'search?page={page}&{query}'
time_range_url = '&order={range}' time_range_url = '&order={range}'
time_range_dict = {'day': 11, time_range_dict = {'day': 11,
@ -37,9 +37,8 @@ def request(query, params):
if params['time_range'] and params['time_range'] not in time_range_dict: if params['time_range'] and params['time_range'] not in time_range_dict:
return params return params
offset = (params['pageno'] - 1) * 24
params['url'] = search_url.format(offset=offset, params['url'] = search_url.format(page=params['pageno'],
query=urlencode({'q': query})) query=urlencode({'q': query}))
if params['time_range'] in time_range_dict: if params['time_range'] in time_range_dict:
params['url'] += time_range_url.format(range=time_range_dict[params['time_range']]) params['url'] += time_range_url.format(range=time_range_dict[params['time_range']])
@ -57,28 +56,28 @@ def response(resp):
dom = html.fromstring(resp.text) dom = html.fromstring(resp.text)
regex = re.compile(r'\/200H\/')
# parse results # parse results
for result in dom.xpath('.//span[@class="thumb wide"]'): for row in dom.xpath('//div[contains(@data-hook, "content_row")]'):
link = result.xpath('.//a[@class="torpedo-thumb-link"]')[0] for result in row.xpath('./div'):
url = link.attrib.get('href') link = result.xpath('.//a[@data-hook="deviation_link"]')[0]
title = extract_text(result.xpath('.//span[@class="title"]')) url = link.attrib.get('href')
thumbnail_src = link.xpath('.//img')[0].attrib.get('src') title = link.attrib.get('title')
img_src = regex.sub('/', thumbnail_src) thumbnail_src = result.xpath('.//img')[0].attrib.get('src')
img_src = thumbnail_src
# http to https, remove domain sharding # http to https, remove domain sharding
thumbnail_src = re.sub(r"https?://(th|fc)\d+.", "https://th01.", thumbnail_src) thumbnail_src = re.sub(r"https?://(th|fc)\d+.", "https://th01.", thumbnail_src)
thumbnail_src = re.sub(r"http://", "https://", thumbnail_src) thumbnail_src = re.sub(r"http://", "https://", thumbnail_src)
url = re.sub(r"http://(.*)\.deviantart\.com/", "https://\\1.deviantart.com/", url) url = re.sub(r"http://(.*)\.deviantart\.com/", "https://\\1.deviantart.com/", url)
# append result # append result
results.append({'url': url, results.append({'url': url,
'title': title, 'title': title,
'img_src': img_src, 'img_src': img_src,
'thumbnail_src': thumbnail_src, 'thumbnail_src': thumbnail_src,
'template': 'images.html'}) 'template': 'images.html'})
# return results # return results
return results return results