Browse Source

[fix] bing images page change

Adam Tauber 9 years ago
parent
commit
71de593a5b
2 changed files with 10 additions and 154 deletions
  1. 1 1
      searx/engines/bing_images.py
  2. 9 153
      tests/unit/engines/test_bing_images.py

+ 1 - 1
searx/engines/bing_images.py

@@ -69,7 +69,7 @@ def response(resp):
     dom = html.fromstring(resp.text)
 
     # parse results
-    for result in dom.xpath('//div[@class="dg_u"]'):
+    for result in dom.xpath('//div[@class="dg_u"]/div'):
         link = result.xpath('./a')[0]
 
         # parse json-data (it is required to add a space, to make it parsable)

+ 9 - 153
tests/unit/engines/test_bing_images.py

@@ -38,12 +38,12 @@ class TestBingImagesEngine(SearxTestCase):
         self.assertEqual(bing_images.response(response), [])
 
         html = """
-        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px"><div>
             <a href="/images/search?q=south&amp;view=detailv2&amp;&amp;id=7E92863981CCFB89FBDD55205C742DFDA3290CF6&amp;selectedIndex=9&amp;ccid=vzvIfv5u&amp;simid=608055786735667000&amp;thid=OIP.Mbf3bc87efe6e0e476be8cc34bf6cd80eH0" ihk="OIP.Mbf3bc87efe6e0e476be8cc34bf6cd80eH0" t1="South Carolina" t2="747 x 589 &#183; 29 kB &#183; gif" t3="www.digital-topo-maps.com/county-map/south-carolina.shtml" hh="236" hw="300" m='{ns:"images",k:"5117",mid:"7E92863981CCFB89FBDD55205C742DFDA3290CF6",md5:"bf3bc87efe6e0e476be8cc34bf6cd80e",surl:"http://www.digital-topo-maps.com/county-map/south-carolina.shtml",imgurl:"http://www.digital-topo-maps.com/county-map/south-carolina-county-map.gif",tid:"OIP.Mbf3bc87efe6e0e476be8cc34bf6cd80eH0",ow:"480",docid:"608055786735667000",oh:"378",tft:"45"}' mid="7E92863981CCFB89FBDD55205C742DFDA3290CF6" h="ID=images,5117.1">
                 <img class="img_hid" src2="https://tse4.mm.bing.net/th?id=OIP.Mbf3bc87efe6e0e476be8cc34bf6cd80eH0&amp;w=210&amp;h=154&amp;c=7&amp;rs=1&amp;qlt=90&amp;o=4&amp;pid=1.1" style="width:210px;height:154px;" width="210" height="154">
             </a>
 
-        </div>
+        </div></div>
         """  # noqa
         html = html.replace('\r\n', '').replace('\n', '').replace('\r', '')
         response = mock.Mock(text=html)
@@ -78,7 +78,7 @@ class TestBingImagesEngine(SearxTestCase):
         self.assertEqual(len(results), 0)
 
         html = """
-        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px"><div>
             <a href="#" ihk="HN.608003696942779811"
                 m="{ns:&quot;images&quot;,k:&quot;5045&quot;,
 mid:&quot;659EB92C317974F34517A1CCAEBEF76A578E08DEE&quot;,
@@ -89,8 +89,8 @@ oh:&quot;238&quot;,tft:&quot;0&quot;,oi:&quot;http://www.image.url/Images/Test%2
                 <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&amp;o=4&amp;pid=1.7"
                 style="height:144px;" width="178" height="144"/>
             </a>
-        </div>
-        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+        </div></div>
+        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px"><div>
             <a href="#" ihk="HN.608003696942779811"
                 m="{ns:&quot;images&quot;,k:&quot;5045&quot;,
 mid:&quot;659EB92C317974F34517A1CCAEBEF76A578E08DEE&quot;,
@@ -101,8 +101,8 @@ oh:&quot;238&quot;,tft:&quot;0&quot;,oi:&quot;http://www.image.url/Images/Test%2
                 <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&amp;o=4&amp;pid=1.7"
                 style="height:144px;" width="178" height="144"/>
             </a>
-        </div>
-        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+        </div></div>
+        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px"><div>
             <a href="#" ihk="HN.608003696942779811"
                 m="{ns:&quot;images&quot;,k:&quot;5045&quot;,
 mid:&quot;659EB92C317974F34517A1CCAEBEF76A578E08DEE&quot;,
@@ -113,154 +113,10 @@ oh:&quot;238&quot;,tft:&quot;0&quot;,oi:&quot;http://www.image.url/Images/Test%2
                 <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&amp;o=4&amp;pid=1.7"
                 style="height:144px;" width="178" height="144"/>
             </a>
-        </div>
-        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
-            <a href="#" ihk="HN.608003696942779811"
-                m="{ns:&quot;images&quot;,k:&quot;5045&quot;,
-mid:&quot;659EB92C317974F34517A1CCAEBEF76A578E08DEE&quot;,
-surl:&quot;http://www.page.url/&quot;,imgurl:&quot;http://test.url/Test%20Query.jpg&quot;,
-oh:&quot;238&quot;,tft:&quot;0&quot;,oi:&quot;http://www.image.url/Images/Test%20Query.jpg&quot;}"
-                mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
-                t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
-                <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&amp;o=4&amp;pid=1.7"
-                style="height:144px;" width="178" height="144"/>
-            </a>
-        </div>
-        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
-            <a href="#" ihk="HN.608003696942779811"
-                m="{ns:&quot;images&quot;,k:&quot;5045&quot;,
-mid:&quot;659EB92C317974F34517A1CCAEBEF76A578E08DEE&quot;,
-surl:&quot;http://www.page.url/&quot;,imgurl:&quot;http://test.url/Test%20Query.jpg&quot;,
-oh:&quot;238&quot;,tft:&quot;0&quot;,oi:&quot;http://www.image.url/Images/Test%20Query.jpg&quot;}"
-                mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
-                t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
-                <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&amp;o=4&amp;pid=1.7"
-                style="height:144px;" width="178" height="144"/>
-            </a>
-        </div>
-        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
-            <a href="#" ihk="HN.608003696942779811"
-                m="{ns:&quot;images&quot;,k:&quot;5045&quot;,
-mid:&quot;659EB92C317974F34517A1CCAEBEF76A578E08DEE&quot;,
-surl:&quot;http://www.page.url/&quot;,imgurl:&quot;http://test.url/Test%20Query.jpg&quot;,
-oh:&quot;238&quot;,tft:&quot;0&quot;,oi:&quot;http://www.image.url/Images/Test%20Query.jpg&quot;}"
-                mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
-                t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
-                <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&amp;o=4&amp;pid=1.7"
-                style="height:144px;" width="178" height="144"/>
-            </a>
-        </div>
-        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
-            <a href="#" ihk="HN.608003696942779811"
-                m="{ns:&quot;images&quot;,k:&quot;5045&quot;,
-mid:&quot;659EB92C317974F34517A1CCAEBEF76A578E08DEE&quot;,
-surl:&quot;http://www.page.url/&quot;,imgurl:&quot;http://test.url/Test%20Query.jpg&quot;,
-oh:&quot;238&quot;,tft:&quot;0&quot;,oi:&quot;http://www.image.url/Images/Test%20Query.jpg&quot;}"
-                mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
-                t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
-                <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&amp;o=4&amp;pid=1.7"
-                style="height:144px;" width="178" height="144"/>
-            </a>
-        </div>
-        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
-            <a href="#" ihk="HN.608003696942779811"
-                m="{ns:&quot;images&quot;,k:&quot;5045&quot;,
-mid:&quot;659EB92C317974F34517A1CCAEBEF76A578E08DEE&quot;,
-surl:&quot;http://www.page.url/&quot;,imgurl:&quot;http://test.url/Test%20Query.jpg&quot;,
-oh:&quot;238&quot;,tft:&quot;0&quot;,oi:&quot;http://www.image.url/Images/Test%20Query.jpg&quot;}"
-                mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
-                t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
-                <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&amp;o=4&amp;pid=1.7"
-                style="height:144px;" width="178" height="144"/>
-            </a>
-        </div>
-        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
-            <a href="#" ihk="HN.608003696942779811"
-                m="{ns:&quot;images&quot;,k:&quot;5045&quot;,
-mid:&quot;659EB92C317974F34517A1CCAEBEF76A578E08DEE&quot;,
-surl:&quot;http://www.page.url/&quot;,imgurl:&quot;http://test.url/Test%20Query.jpg&quot;,
-oh:&quot;238&quot;,tft:&quot;0&quot;,oi:&quot;http://www.image.url/Images/Test%20Query.jpg&quot;}"
-                mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
-                t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
-                <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&amp;o=4&amp;pid=1.7"
-                style="height:144px;" width="178" height="144"/>
-            </a>
-        </div>
-        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
-            <a href="#" ihk="HN.608003696942779811"
-                m="{ns:&quot;images&quot;,k:&quot;5045&quot;,
-mid:&quot;659EB92C317974F34517A1CCAEBEF76A578E08DEE&quot;,
-surl:&quot;http://www.page.url/&quot;,imgurl:&quot;http://test.url/Test%20Query.jpg&quot;,
-oh:&quot;238&quot;,tft:&quot;0&quot;,oi:&quot;http://www.image.url/Images/Test%20Query.jpg&quot;}"
-                mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
-                t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
-                <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&amp;o=4&amp;pid=1.7"
-                style="height:144px;" width="178" height="144"/>
-            </a>
-        </div>
-        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
-            <a href="#" ihk="HN.608003696942779811"
-                m="{ns:&quot;images&quot;,k:&quot;5045&quot;,
-mid:&quot;659EB92C317974F34517A1CCAEBEF76A578E08DEE&quot;,
-surl:&quot;http://www.page.url/&quot;,imgurl:&quot;http://test.url/Test%20Query.jpg&quot;,
-oh:&quot;238&quot;,tft:&quot;0&quot;,oi:&quot;http://www.image.url/Images/Test%20Query.jpg&quot;}"
-                mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
-                t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
-                <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&amp;o=4&amp;pid=1.7"
-                style="height:144px;" width="178" height="144"/>
-            </a>
-        </div>
-        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
-            <a href="#" ihk="HN.608003696942779811"
-                m="{ns:&quot;images&quot;,k:&quot;5045&quot;,
-mid:&quot;659EB92C317974F34517A1CCAEBEF76A578E08DEE&quot;,
-surl:&quot;http://www.page.url/&quot;,imgurl:&quot;http://test.url/Test%20Query.jpg&quot;,
-oh:&quot;238&quot;,tft:&quot;0&quot;,oi:&quot;http://www.image.url/Images/Test%20Query.jpg&quot;}"
-                mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
-                t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
-                <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&amp;o=4&amp;pid=1.7"
-                style="height:144px;" width="178" height="144"/>
-            </a>
-        </div>
-        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
-            <a href="#" ihk="HN.608003696942779811"
-                m="{ns:&quot;images&quot;,k:&quot;5045&quot;,
-mid:&quot;659EB92C317974F34517A1CCAEBEF76A578E08DEE&quot;,
-surl:&quot;http://www.page.url/&quot;,imgurl:&quot;http://test.url/Test%20Query.jpg&quot;,
-oh:&quot;238&quot;,tft:&quot;0&quot;,oi:&quot;http://www.image.url/Images/Test%20Query.jpg&quot;}"
-                mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
-                t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
-                <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&amp;o=4&amp;pid=1.7"
-                style="height:144px;" width="178" height="144"/>
-            </a>
-        </div>
-        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
-            <a href="#" ihk="HN.608003696942779811"
-                m="{ns:&quot;images&quot;,k:&quot;5045&quot;,
-mid:&quot;659EB92C317974F34517A1CCAEBEF76A578E08DEE&quot;,
-surl:&quot;http://www.page.url/&quot;,imgurl:&quot;http://test.url/Test%20Query.jpg&quot;,
-oh:&quot;238&quot;,tft:&quot;0&quot;,oi:&quot;http://www.image.url/Images/Test%20Query.jpg&quot;}"
-                mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
-                t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
-                <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&amp;o=4&amp;pid=1.7"
-                style="height:144px;" width="178" height="144"/>
-            </a>
-        </div>
-        <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
-            <a href="#" ihk="HN.608003696942779811"
-                m="{ns:&quot;images&quot;,k:&quot;5045&quot;,
-mid:&quot;659EB92C317974F34517A1CCAEBEF76A578E08DEE&quot;,
-surl:&quot;http://www.page.url/&quot;,imgurl:&quot;http://test.url/Test%20Query.jpg&quot;,
-oh:&quot;238&quot;,tft:&quot;0&quot;,oi:&quot;http://www.image.url/Images/Test%20Query.jpg&quot;}"
-                mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
-                t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
-                <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&amp;o=4&amp;pid=1.7"
-                style="height:144px;" width="178" height="144"/>
-            </a>
-        </div>
+        </div></div>
         """
         html = html.replace('\r\n', '').replace('\n', '').replace('\r', '')
         response = mock.Mock(text=html)
         results = bing_images.response(response)
         self.assertEqual(type(results), list)
-        self.assertEqual(len(results), 10)
+        self.assertEqual(len(results), 3)