commit: 16d15268181d536f1cf7126674619e942fc23b99
parent 58a443be29e9fda5273af5118d72ff512ecb9e08
Author: Thomas Pointhuber <thomas.pointhuber@gmx.at>
Date: Tue, 2 Sep 2014 16:48:18 +0200
add comments to deviantart engine
Diffstat:
1 file changed, 29 insertions(+), 3 deletions(-)
diff --git a/searx/engines/deviantart.py b/searx/engines/deviantart.py
@@ -1,35 +1,61 @@
+## 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
+#
+# @todo rewrite to api
+
from urllib import urlencode
from urlparse import urljoin
from lxml import html
+# engine dependent config
categories = ['images']
+paging = True
+# search-url
base_url = 'https://www.deviantart.com/'
search_url = base_url+'search?offset={offset}&{query}'
-paging = True
-
+# do search-request
def request(query, params):
offset = (params['pageno'] - 1) * 24
+
params['url'] = search_url.format(offset=offset,
query=urlencode({'q': query}))
+
return params
+# get response from search-request
def response(resp):
results = []
+
+ # return empty array if a redirection code is returned
if resp.status_code == 302:
- return results
+ return []
+
dom = html.fromstring(resp.text)
+
+ # parse results
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'))
title_links = result.xpath('.//span[@class="details"]//a[contains(@class, "t")]') # noqa
title = ''.join(title_links[0].xpath('.//text()'))
img_src = link.xpath('.//img')[0].attrib['src']
+
+ # append result
results.append({'url': url,
'title': title,
'img_src': img_src,
'template': 'images.html'})
+
+ # return results
return results