@@ -0,0 +1,119 @@
1+"""
2+FindX (General, Images, Videos)
3+
4+@website https://www.findx.com
5+@provide-api no
6+@using-api no
7+@results HTML
8+@stable no
9+@parse url, title, content, embedded, img_src, thumbnail_src
10+"""
11+
12+from dateutil import parser
13+from json import loads
14+import re
15+
16+from lxml import html
17+
18+from searx import logger
19+from searx.engines.xpath import extract_text
20+from searx.engines.youtube_noapi import base_youtube_url, embedded_url
21+from searx.url_utils import urlencode
22+
23+
24+paging = True
25+results_xpath = '//script[@id="initial-state"]'
26+search_url = 'https://www.findx.com/{category}?{q}'
27+type_map = {
28+ 'none': 'web',
29+ 'general': 'web',
30+ 'images': 'images',
31+ 'videos': 'videos',
32+}
33+
34+
35+def request(query, params):
36+ category = 'general'
37+ if 'category' in params and len(params['category']) == 1:
38+ category = params['category'][0]
39+
40+ params['url'] = search_url.format(
41+ category=type_map[category],
42+ q=urlencode({
43+ 'q': query,
44+ 'page': params['pageno']
45+ })
46+ )
47+ return params
48+
49+
50+def response(resp):
51+ dom = html.fromstring(resp.text)
52+ results_raw_json = dom.xpath(results_xpath)
53+ results_json = loads(extract_text(results_raw_json))
54+
55+ if len(results_json['web']['results']) > 0:
56+ return _general_results(results_json['web']['results'])
57+
58+ if len(results_json['images']['results']) > 0:
59+ return _images_results(results_json['images']['results'])
60+
61+ if len(results_json['video']['results']) > 0:
62+ return _videos_results(results_json['video']['results'])
63+
64+ return []
65+
66+
67+def _general_results(general_results):
68+ results = []
69+ for result in general_results:
70+ results.append({
71+ 'url': result['url'],
72+ 'title': result['title'],
73+ 'content': result['sum'],
74+ })
75+ return results
76+
77+
78+def _images_results(image_results):
79+ results = []
80+ for result in image_results:
81+ results.append({
82+ 'url': result['sourceURL'],
83+ 'title': result['title'],
84+ 'content': result['source'],
85+ 'thumbnail_src': _extract_url(result['assets']['thumb']['url']),
86+ 'img_src': _extract_url(result['assets']['file']['url']),
87+ 'template': 'images.html',
88+ })
89+ return results
90+
91+
92+def _videos_results(video_results):
93+ results = []
94+ for result in video_results:
95+ if not result['kind'].startswith('youtube'):
96+ logger.warn('Unknown video kind in findx: {}'.format(result['kind']))
97+ continue
98+
99+ description = result['snippet']['description']
100+ if len(description) > 300:
101+ description = description[:300] + '...'
102+
103+ results.append({
104+ 'url': base_youtube_url + result['id'],
105+ 'title': result['snippet']['title'],
106+ 'content': description,
107+ 'thumbnail': _extract_url(result['snippet']['thumbnails']['default']['url']),
108+ 'publishedDate': parser.parse(result['snippet']['publishedAt']),
109+ 'embedded': embedded_url.format(videoid=result['id']),
110+ 'template': 'videos.html',
111+ })
112+ return results
113+
114+
115+def _extract_url(url):
116+ matching = re.search('(/https?://[^)]+)', url)
117+ if matching:
118+ return matching.group(0)[1:]
119+ return ''