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.

1 files changed, 65 insertions, 0 deletions

diff --git a/searx/engines/searchcode_code.py b/searx/engines/searchcode_code.py
new file mode 100644
index 000000000..2ba0e52f1
--- /dev/null
+++ b/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