Merge pull request #830 from davidar/se

Semantic Scholar

searx/engines/xpath.py

 def extract_text(xpath_results):
     if type(xpath_results) == list:
         # it's list of result : concat everything using recursive call
-        if not xpath_results:
-            raise Exception('Empty url resultset')
         result = ''
         for e in xpath_results:
             result = result + extract_text(e)
 
 
 def extract_url(xpath_results, search_url):
+    if xpath_results == []:
+        raise Exception('Empty url resultset')
     url = extract_text(xpath_results)
 
     if url.startswith('//'):
     if results_xpath:
         for result in dom.xpath(results_xpath):
             url = extract_url(result.xpath(url_xpath), search_url)
-            title = extract_text(result.xpath(title_xpath)[0])
-            content = extract_text(result.xpath(content_xpath)[0])
+            title = extract_text(result.xpath(title_xpath))
+            content = extract_text(result.xpath(content_xpath))
             results.append({'url': url, 'title': title, 'content': content})
     else:
         for url, title, content in zip(

searx/settings.yml

 #        - ...
 #    disabled : True
 
+  - name : semantic scholar
+    engine : xpath
+    paging : True
+    search_url : https://www.semanticscholar.org/search?q={query}&sort=relevance&page={pageno}&ae=false
+    results_xpath : //article
+    url_xpath : .//div[@class="search-result-title"]/a/@href
+    title_xpath : .//div[@class="search-result-title"]/a
+    content_xpath : .//div[@class="search-result-abstract"]
+    shortcut : se
+    categories : science
+
   - name : spotify
     engine : spotify
     shortcut : stf