@@ -1,115 +0,0 @@
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− params['url'] = search_url.format(
37− category=type_map[params['category']],
38− q=urlencode({
39− 'q': query,
40− 'page': params['pageno']
41− })
42− )
43− return params
44−
45−
46−def response(resp):
47− dom = html.fromstring(resp.text)
48− results_raw_json = dom.xpath(results_xpath)
49− results_json = loads(extract_text(results_raw_json))
50−
51− if len(results_json['web']['results']) > 0:
52− return _general_results(results_json['web']['results']['webSearch']['results'])
53−
54− if len(results_json['images']['results']) > 0:
55− return _images_results(results_json['images']['results'])
56−
57− if len(results_json['video']['results']) > 0:
58− return _videos_results(results_json['video']['results'])
59−
60− return []
61−
62−
63−def _general_results(general_results):
64− results = []
65− for result in general_results:
66− results.append({
67− 'url': result['url'],
68− 'title': result['title'],
69− 'content': result['sum'],
70− })
71− return results
72−
73−
74−def _images_results(image_results):
75− results = []
76− for result in image_results:
77− results.append({
78− 'url': result['sourceURL'],
79− 'title': result['title'],
80− 'content': result['source'],
81− 'thumbnail_src': _extract_url(result['assets']['thumb']['url']),
82− 'img_src': _extract_url(result['assets']['file']['url']),
83− 'template': 'images.html',
84− })
85− return results
86−
87−
88−def _videos_results(video_results):
89− results = []
90− for result in video_results:
91− if not result['kind'].startswith('youtube'):
92− logger.warn('Unknown video kind in findx: {}'.format(result['kind']))
93− continue
94−
95− description = result['snippet']['description']
96− if len(description) > 300:
97− description = description[:300] + '...'
98−
99− results.append({
100− 'url': base_youtube_url + result['id'],
101− 'title': result['snippet']['title'],
102− 'content': description,
103− 'thumbnail': _extract_url(result['snippet']['thumbnails']['default']['url']),
104− 'publishedDate': parser.parse(result['snippet']['publishedAt']),
105− 'embedded': embedded_url.format(videoid=result['id']),
106− 'template': 'videos.html',
107− })
108− return results
109−
110−
111−def _extract_url(url):
112− matching = re.search('(/https?://[^)]+)', url)
113− if matching:
114− return matching.group(0)[1:]
115− return ''