free
/
searx
Watch 1
Star 0
Fork 0
Code Issues 0 Pull Requests 0 Releases 11 Wiki Activity
Browse Source

Duckduckgo unit test

Cqoicebordel 10 years ago
parent
0e6f8393ab
commit
efe6dead55
3 changed files with 96 additions and 5 deletions
Split View Show Diff Stats
  1. 5
    5
      searx/engines/duckduckgo.py
  2. 90
    0
      searx/tests/engines/test_duckduckgo.py
  3. 1
    0
      searx/tests/test_engines.py

+ 5
- 5
searx/engines/duckduckgo.py View File 

@@ -15,7 +15,7 @@
15 15
16 16 
 from urllib import urlencode
17 17 
 from lxml.html import fromstring
18 
-from searx.utils import html_to_text
18 
+from searx.engines.xpath import extract_text
19 19
20 20 
 # engine dependent config
21 21 
 categories = ['general']
 
@@ -28,8 +28,8 @@ url = 'https://duckduckgo.com/html?{query}&s={offset}'
28 28 
 # specific xpath variables
29 29 
 result_xpath = '//div[@class="results_links results_links_deep web-result"]'  # noqa
30 30 
 url_xpath = './/a[@class="large"]/@href'
31 
-title_xpath = './/a[@class="large"]//text()'
32 
-content_xpath = './/div[@class="snippet"]//text()'
31 
+title_xpath = './/a[@class="large"]'
32 
+content_xpath = './/div[@class="snippet"]'
33 33
34 34
35 35 
 # do search-request
 
@@ -64,8 +64,8 @@ def response(resp):
64 64 
         if not res_url:
65 65 
             continue
66 66
67 
-        title = html_to_text(''.join(r.xpath(title_xpath)))
68 
-        content = html_to_text(''.join(r.xpath(content_xpath)))
67 
+        title = extract_text(r.xpath(title_xpath))
68 
+        content = extract_text(r.xpath(content_xpath))
69 69
70 70 
         # append result
71 71 
         results.append({'title': title,

+ 90
- 0
searx/tests/engines/test_duckduckgo.py View File 

@@ -0,0 +1,90 @@
1 
+from collections import defaultdict
2 
+import mock
3 
+from searx.engines import duckduckgo
4 
+from searx.testing import SearxTestCase
5 
+
6 
+
7 
+class TestBingEngine(SearxTestCase):
8 
+
9 
+    def test_request(self):
10 
+        query = 'test_query'
11 
+        dicto = defaultdict(dict)
12 
+        dicto['pageno'] = 1
13 
+        dicto['language'] = 'fr_FR'
14 
+        params = duckduckgo.request(query, dicto)
15 
+        self.assertIn('url', params)
16 
+        self.assertIn(query, params['url'])
17 
+        self.assertIn('duckduckgo.com', params['url'])
18 
+        self.assertIn('fr-fr', params['url'])
19 
+
20 
+        dicto['language'] = 'all'
21 
+        params = duckduckgo.request(query, dicto)
22 
+        self.assertIn('en-us', params['url'])
23 
+
24 
+    def test_response(self):
25 
+        self.assertRaises(AttributeError, duckduckgo.response, None)
26 
+        self.assertRaises(AttributeError, duckduckgo.response, [])
27 
+        self.assertRaises(AttributeError, duckduckgo.response, '')
28 
+        self.assertRaises(AttributeError, duckduckgo.response, '[]')
29 
+
30 
+        response = mock.Mock(text='<html></html>')
31 
+        self.assertEqual(duckduckgo.response(response), [])
32 
+
33 
+        html = """
34 
+        <div class="results_links results_links_deep web-result">
35 
+            <div class="icon_fav" style="display: block;">
36 
+                <a rel="nofollow" href="https://www.test.com/">
37 
+                    <img width="16" height="16" alt=""
38 
+                    src="/i/www.test.com.ico" style="visibility: visible;" name="i15" />
39 
+                </a>
40 
+            </div>
41 
+            <div class="links_main links_deep"> <!-- This is the visible part -->
42 
+                <a rel="nofollow" class="large" href="http://this.should.be.the.link/">
43 
+                    This <b>is</b> <b>the</b> title
44 
+                </a>
45 
+                <div class="snippet"><b>This</b> should be the content.</div>
46 
+                <div class="url">
47 
+                    http://this.should.be.the.link/
48 
+                </div>
49 
+            </div>
50 
+        </div>
51 
+        """
52 
+        response = mock.Mock(text=html)
53 
+        results = duckduckgo.response(response)
54 
+        self.assertEqual(type(results), list)
55 
+        self.assertEqual(len(results), 1)
56 
+        self.assertEqual(results[0]['title'], 'This is the title')
57 
+        self.assertEqual(results[0]['url'], 'http://this.should.be.the.link/')
58 
+        self.assertEqual(results[0]['content'], 'This should be the content.')
59 
+
60 
+        html = """
61 
+        <div class="results_links results_links_deep web-result">
62 
+            <div class="icon_fav" style="display: block;">
63 
+            </div>
64 
+            <div class="links_main links_deep"> <!-- This is the visible part -->
65 
+                <div class="snippet"><b>This</b> should be the content.</div>
66 
+                <div class="url">
67 
+                    http://this.should.be.the.link/
68 
+                </div>
69 
+            </div>
70 
+        </div>
71 
+        <div class="results_links results_links_deep web-result">
72 
+            <div class="icon_fav" style="display: block;">
73 
+                <img width="16" height="16" alt=""
74 
+                src="/i/www.test.com.ico" style="visibility: visible;" name="i15" />
75 
+            </div>
76 
+            <div class="links_main links_deep"> <!-- This is the visible part -->
77 
+                <a rel="nofollow" class="large" href="">
78 
+                    This <b>is</b> <b>the</b> title
79 
+                </a>
80 
+                <div class="snippet"><b>This</b> should be the content.</div>
81 
+                <div class="url">
82 
+                    http://this.should.be.the.link/
83 
+                </div>
84 
+            </div>
85 
+        </div>
86 
+        """
87 
+        response = mock.Mock(text=html)
88 
+        results = duckduckgo.response(response)
89 
+        self.assertEqual(type(results), list)
90 
+        self.assertEqual(len(results), 0)

+ 1
- 0
searx/tests/test_engines.py View File 

@@ -6,6 +6,7 @@ from searx.tests.engines.test_dailymotion import *  # noqa
6 6 
 from searx.tests.engines.test_deezer import *  # noqa
7 7 
 from searx.tests.engines.test_deviantart import *  # noqa
8 8 
 from searx.tests.engines.test_digg import *  # noqa
9 
+from searx.tests.engines.test_duckduckgo import *  # noqa
9 10 
 from searx.tests.engines.test_dummy import *  # noqa
10 11 
 from searx.tests.engines.test_flickr import *  # noqa
11 12 
 from searx.tests.engines.test_flickr_noapi import *  # noqa