@@ -1,40 +1,89 @@
1+## Yacy (Web, Images, Videos, Music, Files)
2+#
3+# @website http://yacy.net
4+# @provide-api yes (http://www.yacy-websuche.de/wiki/index.php/Dev:APIyacysearch)
5+#
6+# @using-api yes
7+# @results JSON
8+# @stable yes
9+# @parse (general) url, title, content, publishedDate
10+# @parse (images) url, title, img_src
11+#
12+# @todo parse video, audio and file results
13+
114from json import loads
215from urllib import urlencode
16+from dateutil import parser
17+
18+# engine dependent config
19+categories = ['general', 'images'] #TODO , 'music', 'videos', 'files'
20+paging = True
21+language_support = True
22+number_of_results = 5
23+
24+# search-url
25+base_url = 'http://localhost:8090'
26+search_url = '/yacysearch.json?{query}&startRecord={offset}&maximumRecords={limit}&contentdom={search_type}&resource=global'
327
4−url = 'http://localhost:8090'
5−search_url = '/yacysearch.json?{query}&maximumRecords=10'
28+# yacy specific type-definitions
29+search_types = {'general': 'text',
30+ 'images': 'image',
31+ 'files': 'app',
32+ 'music': 'audio',
33+ 'videos': 'video'}
634
735
36+# do search-request
837def request(query, params):
9− params['url'] = url + search_url.format(query=urlencode({'query': query}))
38+ offset = (params['pageno'] - 1) * number_of_results
39+ search_type = search_types.get(params['category'], '0')
40+
41+ params['url'] = base_url + search_url.format(query=urlencode({'query': query}),
42+ offset=offset,
43+ limit=number_of_results,
44+ search_type=search_type)
45+
46+ # add language tag if specified
47+ if params['language'] != 'all':
48+ params['url'] += '&lr=lang_' + params['language'].split('_')[0]
49+
1050 return params
1151
1252
53+# get response from search-request
1354def response(resp):
55+ results = []
56+
1457 raw_search_results = loads(resp.text)
1558
59+ # return empty array if there are no results
1660 if not raw_search_results:
1761 return []
1862
1963 search_results = raw_search_results.get('channels', {})[0].get('items', [])
2064
21− results = []
22−
23− for result in search_results:
24− tmp_result = {}
25− tmp_result['title'] = result['title']
26− tmp_result['url'] = result['link']
27− tmp_result['content'] = ''
28−
29− if result['description']:
30− tmp_result['content'] += result['description'] + "<br/>"
65+ if resp.search_params['category'] == 'general':
66+ # parse general results
67+ for result in search_results:
68+ publishedDate = parser.parse(result['pubDate'])
3169
32− if result['pubDate']:
33− tmp_result['content'] += result['pubDate'] + "<br/>"
70+ # append result
71+ results.append({'url': result['link'],
72+ 'title': result['title'],
73+ 'content': result['description'],
74+ 'publishedDate': publishedDate})
3475
35− if result['size'] != '-1':
36− tmp_result['content'] += result['sizename']
76+ elif resp.search_params['category'] == 'images':
77+ # parse image results
78+ for result in search_results:
79+ # append result
80+ results.append({'url': result['url'],
81+ 'title': result['title'],
82+ 'content': '',
83+ 'img_src': result['image'],
84+ 'template': 'images.html'})
3785
38− results.append(tmp_result)
86+ #TODO parse video, audio and file results
3987
88+ # return results
4089 return results