Add 500px and Searchcode engines

Allow to search for images on 500px. It doesn't use the official API, but the page result. Less stable, but less API key to possess...

Two engines were necessary for Searchcode because there are to search mode : search for documentation or search for code example. Both use open APIs.

searx/engines/500px.py

@@ -0,0 +1,57 @@
+## 500px (Images)
+#
+# @website     https://500px.com
+# @provide-api yes (https://developers.500px.com/)
+#
+# @using-api   no
+# @results     HTML
+# @stable      no (HTML can change)
+# @parse       url, title, thumbnail, img_src, content
+#
+# @todo        rewrite to api
+
+
+from urllib import urlencode
+from urlparse import urljoin
+from lxml import html
+
+# engine dependent config
+categories = ['images']
+paging = True
+
+# search-url
+base_url = 'https://500px.com'
+search_url = base_url+'/search?search?page={pageno}&type=photos&{query}'
+
+
+# do search-request
+def request(query, params):
+    params['url'] = search_url.format(pageno=params['pageno'],
+                                      query=urlencode({'q': query}))
+
+    return params
+
+
+# get response from search-request
+def response(resp):
+    results = []
+    
+    dom = html.fromstring(resp.text)
+    
+    # parse results
+    for result in dom.xpath('//div[@class="photo"]'):
+        link = result.xpath('.//a')[0]
+        url = urljoin(base_url, link.attrib.get('href'))
+        title = result.xpath('.//div[@class="title"]//text()')[0]
+        img_src = link.xpath('.//img')[0].attrib['src']
+        content = result.xpath('.//div[@class="info"]//text()')[0]
+
+        # append result
+        results.append({'url': url,
+                        'title': title,
+                        'img_src': img_src,
+                        'content': content,
+                        'template': 'images.html'})
+
+    # return results
+    return results

searx/engines/searchcode_code.py

@@ -0,0 +1,65 @@
+## Searchcode (It)
+#
+# @website     https://searchcode.com/
+# @provide-api yes (https://searchcode.com/api/)
+#
+# @using-api   yes
+# @results     JSON
+# @stable      yes
+# @parse       url, title, content
+
+from urllib import urlencode
+from json import loads
+import cgi
+import re
+
+# engine dependent config
+categories = ['it']
+paging = True
+
+# search-url
+url = 'https://searchcode.com/'
+search_url = url+'api/codesearch_I/?{query}&p={pageno}'
+
+
+# do search-request
+def request(query, params):
+    params['url'] = search_url.format(query=urlencode({'q': query}),
+                                      pageno=params['pageno']-1)
+
+    return params
+
+
+# get response from search-request
+def response(resp):
+    results = []
+    
+    search_results = loads(resp.text)
+
+    # parse results
+    for result in search_results['results']:
+        href = result['url']
+        title = "" + result['name'] + " - " + result['filename']
+        content = result['repo'] + "<br />"
+        
+        lines = dict()
+        for line, code in result['lines'].items():
+            lines[int(line)] = code
+
+        content = content + '<pre class="code-formatter"><table class="code">'
+        for line, code in sorted(lines.items()):
+            content = content + '<tr><td class="line-number" style="padding-right:5px;">' 
+            content = content + str(line) + '</td><td class="code-snippet">' 
+            # Replace every two spaces with ' &nbps;' to keep formatting while allowing the browser to break the line if necessary
+            content = content + cgi.escape(code).replace('\t', '    ').replace('  ', '&nbsp; ').replace('  ', ' &nbsp;') 
+            content = content + "</td></tr>"
+            
+        content = content + "</table></pre>"
+        
+        # append result
+        results.append({'url': href,
+                        'title': title,
+                        'content': content})
+
+    # return results
+    return results

searx/engines/searchcode_doc.py

@@ -0,0 +1,49 @@
+## Searchcode (It)
+#
+# @website     https://searchcode.com/
+# @provide-api yes (https://searchcode.com/api/)
+#
+# @using-api   yes
+# @results     JSON
+# @stable      yes
+# @parse       url, title, content
+
+from urllib import urlencode
+from json import loads
+
+# engine dependent config
+categories = ['it']
+paging = True
+
+# search-url
+url = 'https://searchcode.com/'
+search_url = url+'api/search_IV/?{query}&p={pageno}'
+
+
+# do search-request
+def request(query, params):
+    params['url'] = search_url.format(query=urlencode({'q': query}),
+                                      pageno=params['pageno']-1)
+
+    return params
+
+
+# get response from search-request
+def response(resp):
+    results = []
+    
+    search_results = loads(resp.text)
+
+    # parse results
+    for result in search_results['results']:
+        href = result['url']
+        title = "[" + result['type'] + "] " + result['namespace'] + " " + result['name']
+        content = '<span class="highlight">[' + result['type'] + "] " + result['name'] + " " + result['synopsis'] + "</span><br />" + result['description']
+        
+        # append result
+        results.append({'url': href,
+                        'title': title,
+                        'content': content})
+
+    # return results
+    return results

searx/settings.yml

@@ -64,6 +64,10 @@ engines:
 #    engine : filecrop
 #    categories : files
 #    shortcut : fc
+    
+  - name : 500px
+    engine : 500px
+    shortcut : px
 
   - name : flickr
     engine : flickr
@@ -114,6 +118,14 @@ engines:
   - name : stackoverflow
     engine : stackoverflow
     shortcut : st
+    
+  - name : searchcode doc
+    engine : searchcode_doc
+    shortcut : scd
+    
+  - name : searchcode code
+    engine : searchcode_code
+    shortcut : scc
 
   - name : startpage
     engine : startpage