@@ -0,0 +1,67 @@
1+## Digg (News, Social media)
2+#
3+# @website https://digg.com/
4+# @provide-api no
5+#
6+# @using-api no
7+# @results HTML (using search portal)
8+# @stable no (HTML can change)
9+# @parse url, title, content, publishedDate, thumbnail
10+
11+from urllib import quote_plus
12+from json import loads
13+from lxml import html
14+from cgi import escape
15+from dateutil import parser
16+
17+# engine dependent config
18+categories = ['news', 'social media']
19+paging = True
20+
21+# search-url
22+base_url = 'https://digg.com/'
23+search_url = base_url+'api/search/{query}.json?position={position}&format=html'
24+
25+# specific xpath variables
26+results_xpath = '//article'
27+link_xpath = './/small[@class="time"]//a'
28+title_xpath = './/h2//a//text()'
29+content_xpath = './/p//text()'
30+pubdate_xpath = './/time'
31+
32+
33+# do search-request
34+def request(query, params):
35+ offset = (params['pageno'] - 1) * 10
36+ params['url'] = search_url.format(position=offset,
37+ query=quote_plus(query))
38+ return params
39+
40+
41+# get response from search-request
42+def response(resp):
43+ results = []
44+
45+ search_result = loads(resp.text)
46+
47+ dom = html.fromstring(search_result['html'])
48+
49+ # parse results
50+ for result in dom.xpath(results_xpath):
51+ url = result.attrib.get('data-contenturl')
52+ thumbnail = result.xpath('.//img')[0].attrib.get('src')
53+ title = ''.join(result.xpath(title_xpath))
54+ content = escape(''.join(result.xpath(content_xpath)))
55+ pubdate = result.xpath(pubdate_xpath)[0].attrib.get('datetime')
56+ publishedDate = parser.parse(pubdate)
57+
58+ # append result
59+ results.append({'url': url,
60+ 'title': title,
61+ 'content': content,
62+ 'template': 'videos.html',
63+ 'publishedDate': publishedDate,
64+ 'thumbnail': thumbnail})
65+
66+ # return results
67+ return results