on master help sign in
Merge pull request #1669 from dalf/engine-fixes

Engine fixes

commit12f891da8496fad1f1fa24eeb52b1b19f03f8678 authorAlexandre Flament <alex@al-f.net> dateMon 5 Aug 2019, 15:57 (7 years ago) parent91a59ff1cee2c1
7 files changed+58−50
searx/engines/arxiv.py+1−1 searx/engines/bing.py−2 searx/engines/dictzone.py+1−1 searx/engines/fdroid.py+14−15 searx/settings.yml+8−8 tests/unit/engines/test_arxiv.py+1−1 tests/unit/engines/test_fdroid.py+33−22
searx/engines/arxiv.py+1−1
@@ -29,7 +29,7 @@ def request(query, params):
2929 # basic search
3030 offset = (params['pageno'] - 1) * number_of_results
3131
32− string_args = dict(query=query,
32+ string_args = dict(query=query.decode('utf-8'),
3333 offset=offset,
3434 number_of_results=number_of_results)
3535
searx/engines/bing.py−2
@@ -47,8 +47,6 @@ def request(query, params):
4747
4848 params['url'] = base_url + search_path
4949
50− params['headers']['User-Agent'] = gen_useragent('Windows NT 6.3; WOW64')
51−
5250 return params
5351
5452
searx/engines/dictzone.py+1−1
@@ -15,7 +15,7 @@ from searx.utils import is_valid_lang
1515from searx.url_utils import urljoin
1616
1717categories = ['general']
18−url = u'http://dictzone.com/{from_lang}-{to_lang}-dictionary/{query}'
18+url = u'https://dictzone.com/{from_lang}-{to_lang}-dictionary/{query}'
1919weight = 100
2020
2121parser_re = re.compile(b'.*?([a-z]+)-([a-z]+) ([^ ]+)$', re.I)
searx/engines/fdroid.py+14−15
@@ -18,13 +18,13 @@ categories = ['files']
1818paging = True
1919
2020# search-url
21−base_url = 'https://f-droid.org/'
22−search_url = base_url + 'repository/browse/?{query}'
21+base_url = 'https://search.f-droid.org/'
22+search_url = base_url + '?{query}'
2323
2424
2525# do search-request
2626def request(query, params):
27− query = urlencode({'fdfilter': query, 'fdpage': params['pageno']})
27+ query = urlencode({'q': query, 'page': params['pageno'], 'lang': ''})
2828 params['url'] = search_url.format(query=query)
2929 return params
3030
@@ -35,17 +35,16 @@ def response(resp):
3535
3636 dom = html.fromstring(resp.text)
3737
38− for app in dom.xpath('//div[@id="appheader"]'):
39− url = app.xpath('./ancestor::a/@href')[0]
40− title = app.xpath('./p/span/text()')[0]
41− img_src = app.xpath('.//img/@src')[0]
42−
43− content = extract_text(app.xpath('./p')[0])
44− content = content.replace(title, '', 1).strip()
45−
46− results.append({'url': url,
47− 'title': title,
48− 'content': content,
49− 'img_src': img_src})
38+ for app in dom.xpath('//a[@class="package-header"]'):
39+ app_url = app.xpath('./@href')[0]
40+ app_title = extract_text(app.xpath('./div/h4[@class="package-name"]/text()'))
41+ app_content = extract_text(app.xpath('./div/div/span[@class="package-summary"]')).strip() \
42+ + ' - ' + extract_text(app.xpath('./div/div/span[@class="package-license"]')).strip()
43+ app_img_src = app.xpath('./img[@class="package-icon"]/@src')[0]
44+
45+ results.append({'url': app_url,
46+ 'title': app_title,
47+ 'content': app_content,
48+ 'img_src': app_img_src})
5049
5150 return results
searx/settings.yml+8−8
@@ -204,11 +204,11 @@ engines:
204204 - name : etymonline
205205 engine : xpath
206206 paging : True
207− search_url : http://etymonline.com/?search={query}&p={pageno}
208− url_xpath : //a[contains(@class, "word--")]/@href
209− title_xpath : //p[contains(@class, "word__name--")]/text()
210− content_xpath : //section[contains(@class, "word__defination")]/object
211− first_page_num : 0
207+ search_url : https://etymonline.com/search?page={pageno}&q={query}
208+ url_xpath : //a[contains(@class, "word__name--")]/@href
209+ title_xpath : //a[contains(@class, "word__name--")]
210+ content_xpath : //section[contains(@class, "word__defination")]
211+ first_page_num : 1
212212 shortcut : et
213213 disabled : True
214214
@@ -703,9 +703,9 @@ engines:
703703 shortcut: vo
704704 categories: social media
705705 search_url : https://searchvoat.co/?t={query}
706− url_xpath : //div[@class="entry"]/p/a[@class="title"]/@href
707− title_xpath : //div[@class="entry"]/p/a[@class="title"]
708− content_xpath : //div[@class="entry"]/p/span[@class="domain"]
706+ url_xpath : //div[@class="entry"]/p/a[contains(@class, "title")]/@href
707+ title_xpath : //div[@class="entry"]/p/a[contains(@class, "title")]
708+ content_xpath : //div[@class="entry"]/p/span[@class="domain"]/a/text()
709709 timeout : 10.0
710710 disabled : True
711711
tests/unit/engines/test_arxiv.py+1−1
@@ -8,7 +8,7 @@ from searx.testing import SearxTestCase
88class TestBaseEngine(SearxTestCase):
99
1010 def test_request(self):
11− query = 'test_query'
11+ query = 'test_query'.encode('utf-8')
1212 dicto = defaultdict(dict)
1313 dicto['pageno'] = 1
1414 params = arxiv.request(query, dicto)
tests/unit/engines/test_fdroid.py+33−22
@@ -13,29 +13,40 @@ class TestFdroidEngine(SearxTestCase):
1313 params = fdroid.request(query, dic)
1414 self.assertTrue('url' in params)
1515 self.assertTrue(query in params['url'])
16− self.assertTrue('f-droid.org' in params['url'])
16+ self.assertTrue('search.f-droid.org' in params['url'])
1717
18− def test_response(self):
18+ def test_response_empty(self):
1919 resp = mock.Mock(text='<html></html>')
2020 self.assertEqual(fdroid.response(resp), [])
2121
22+ def test_response_oneresult(self):
2223 html = """
23− <a href="https://google.com/qwerty">
24− <div id="appheader">
25− <div style="float:left;padding-right:10px;">
26− <img src="http://example.com/image.png"
27− style="width:48px;border:none;">
28− </div>
29− <div style="float:right;">
30− <p>Details...</p>
31− </div>
32− <p style="color:#000000;">
33− <span style="font-size:20px;">Sample title</span>
34− <br>
35− Sample content
36− </p>
37− </div>
38− </a>
24+<!DOCTYPE html>
25+<html>
26+<head>
27+ <title>test</title>
28+</head>
29+<body>
30+ <div class="site-wrapper">
31+ <div class="main-content">
32+ <a class="package-header" href="https://example.com/app.url">
33+ <img class="package-icon" src="https://example.com/appexample.logo.png" />
34+
35+ <div class="package-info">
36+ <h4 class="package-name">
37+ App Example 1
38+ </h4>
39+
40+ <div class="package-desc">
41+ <span class="package-summary">Description App Example 1</span>
42+ <span class="package-license">GPL-3.0-only</span>
43+ </div>
44+ </div>
45+ </a>
46+ </div>
47+ </div>
48+</body>
49+</html>
3950 """
4051
4152 resp = mock.Mock(text=html)
@@ -43,7 +54,7 @@ class TestFdroidEngine(SearxTestCase):
4354
4455 self.assertEqual(type(results), list)
4556 self.assertEqual(len(results), 1)
46− self.assertEqual(results[0]['url'], 'https://google.com/qwerty')
47− self.assertEqual(results[0]['title'], 'Sample title')
48− self.assertEqual(results[0]['content'], 'Sample content')
49− self.assertEqual(results[0]['img_src'], 'http://example.com/image.png')
57+ self.assertEqual(results[0]['url'], 'https://example.com/app.url')
58+ self.assertEqual(results[0]['title'], 'App Example 1')
59+ self.assertEqual(results[0]['content'], 'Description App Example 1 - GPL-3.0-only')
60+ self.assertEqual(results[0]['img_src'], 'https://example.com/appexample.logo.png')