free
/
searx
关注 1
点赞 0
派生 0
代码 工单 0 合并请求 0 版本发布 11 百科 动态
浏览代码

500px unit test

Cqoicebordel 10 年前
父节点
f18807955b
当前提交
8cf2ee5721
共有 3 个文件被更改，包括 90 次插入 和 5 次删除
分列视图 显示文件统计
  1. 6
    5
      searx/engines/www500px.py
  2. 83
    0
      searx/tests/engines/test_www500px.py
  3. 1
    0
      searx/tests/test_engines.py

+ 6
- 5
searx/engines/www500px.py 查看文件 

@@ -15,6 +15,7 @@ from urllib import urlencode
15 15 
 from urlparse import urljoin
16 16 
 from lxml import html
17 17 
 import re
18 
+from searx.engines.xpath import extract_text
18 19
19 20 
 # engine dependent config
20 21 
 categories = ['images']
 
@@ -22,7 +23,7 @@ paging = True
22 23
23 24 
 # search-url
24 25 
 base_url = 'https://500px.com'
25 
-search_url = base_url+'/search?search?page={pageno}&type=photos&{query}'
26 
+search_url = base_url + '/search?search?page={pageno}&type=photos&{query}'
26 27
27 28
28 29 
 # do search-request
 
@@ -44,11 +45,11 @@ def response(resp):
44 45 
     for result in dom.xpath('//div[@class="photo"]'):
45 46 
         link = result.xpath('.//a')[0]
46 47 
         url = urljoin(base_url, link.attrib.get('href'))
47 
-        title = result.xpath('.//div[@class="title"]//text()')[0]
48 
-        thumbnail_src = link.xpath('.//img')[0].attrib['src']
48 
+        title = extract_text(result.xpath('.//div[@class="title"]'))
49 
+        thumbnail_src = link.xpath('.//img')[0].attrib.get('src')
49 50 
         # To have a bigger thumbnail, uncomment the next line
50 
-        #thumbnail_src = regex.sub('4.jpg', thumbnail_src)
51 
-        content = result.xpath('.//div[@class="info"]//text()')[0]
51 
+        # thumbnail_src = regex.sub('4.jpg', thumbnail_src)
52 
+        content = extract_text(result.xpath('.//div[@class="info"]'))
52 53 
         img_src = regex.sub('2048.jpg', thumbnail_src)
53 54
54 55 
         # append result

+ 83
- 0
searx/tests/engines/test_www500px.py 查看文件 

@@ -0,0 +1,83 @@
1 
+# -*- coding: utf-8 -*-
2 
+from collections import defaultdict
3 
+import mock
4 
+from searx.engines import www500px
5 
+from searx.testing import SearxTestCase
6 
+
7 
+
8 
+class TestWww500pxImagesEngine(SearxTestCase):
9 
+
10 
+    def test_request(self):
11 
+        query = 'test_query'
12 
+        dicto = defaultdict(dict)
13 
+        dicto['pageno'] = 1
14 
+        params = www500px.request(query, dicto)
15 
+        self.assertTrue('url' in params)
16 
+        self.assertTrue(query in params['url'])
17 
+        self.assertTrue('500px.com' in params['url'])
18 
+
19 
+    def test_response(self):
20 
+        self.assertRaises(AttributeError, www500px.response, None)
21 
+        self.assertRaises(AttributeError, www500px.response, [])
22 
+        self.assertRaises(AttributeError, www500px.response, '')
23 
+        self.assertRaises(AttributeError, www500px.response, '[]')
24 
+
25 
+        response = mock.Mock(text='<html></html>')
26 
+        self.assertEqual(www500px.response(response), [])
27 
+
28 
+        html = """
29 
+        <div class="photo">
30 
+            <a href="/this.should.be.the.url" data-ga-category="Photo Thumbnail" data-ga-action="Title">
31 
+                <img src="https://image.url/3.jpg?v=0" />
32 
+            </a>
33 
+            <div class="details">
34 
+                <div class="inside">
35 
+                    <div class="title">
36 
+                        <a href="/photo/64312705/branch-out-by-oliver-turpin?feature=">
37 
+                            This is the title
38 
+                        </a>
39 
+                    </div>
40 
+                    <div class="info">
41 
+                        <a href="/ChronicleUK" data-ga-action="Image" data-ga-category="Photo Thumbnail">
42 
+                            This is the content
43 
+                        </a>
44 
+                    </div>
45 
+                    <div class="rating">44.8</div>
46 
+                </div>
47 
+            </div>
48 
+        </div>
49 
+        """
50 
+        response = mock.Mock(text=html)
51 
+        results = www500px.response(response)
52 
+        self.assertEqual(type(results), list)
53 
+        self.assertEqual(len(results), 1)
54 
+        self.assertEqual(results[0]['title'], 'This is the title')
55 
+        self.assertEqual(results[0]['url'], 'https://500px.com/this.should.be.the.url')
56 
+        self.assertEqual(results[0]['content'], 'This is the content')
57 
+        self.assertEqual(results[0]['thumbnail_src'], 'https://image.url/3.jpg?v=0')
58 
+        self.assertEqual(results[0]['img_src'], 'https://image.url/2048.jpg')
59 
+
60 
+        html = """
61 
+        <a href="/this.should.be.the.url" data-ga-category="Photo Thumbnail" data-ga-action="Title">
62 
+            <img src="https://image.url/3.jpg?v=0" />
63 
+        </a>
64 
+        <div class="details">
65 
+            <div class="inside">
66 
+                <div class="title">
67 
+                    <a href="/photo/64312705/branch-out-by-oliver-turpin?feature=">
68 
+                        This is the title
69 
+                    </a>
70 
+                </div>
71 
+                <div class="info">
72 
+                    <a href="/ChronicleUK" data-ga-action="Image" data-ga-category="Photo Thumbnail">
73 
+                        Oliver Turpin
74 
+                    </a>
75 
+                </div>
76 
+                <div class="rating">44.8</div>
77 
+            </div>
78 
+        </div>
79 
+        """
80 
+        response = mock.Mock(text=html)
81 
+        results = www500px.response(response)
82 
+        self.assertEqual(type(results), list)
83 
+        self.assertEqual(len(results), 0)

+ 1
- 0
searx/tests/test_engines.py 查看文件 

@@ -18,4 +18,5 @@ from searx.tests.engines.test_searchcode_doc import *  # noqa
18 18 
 from searx.tests.engines.test_soundcloud import *  # noqa
19 19 
 from searx.tests.engines.test_stackoverflow import *  # noqa
20 20 
 from searx.tests.engines.test_vimeo import *  # noqa
21 
+from searx.tests.engines.test_www500px import *  # noqa
21 22 
 from searx.tests.engines.test_youtube import *  # noqa