searx

commit: 57149661e4f90e5ad3a9a4c36bb5f31a1c7ec6aa
parent: b1d49bacb0d6135a7c0a5a32a82681b12b1762cd
Author: Adam Tauber <asciimoo@gmail.com>
Date:   Wed, 18 Jan 2017 23:50:11 +0100

Merge pull request #830 from davidar/se

Semantic Scholar
Diffstat:
M
searx/engines/xpath.py
8
++++----
M
searx/settings.yml
11
+++++++++++

2 files changed, 15 insertions(+), 4 deletions(-)
diff --git a/searx/engines/xpath.py b/searx/engines/xpath.py
@@ -31,8 +31,6 @@ if xpath_results is a string element, then it's already done
 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)
@@ -48,6 +46,8 @@ def extract_text(xpath_results):
 
 
 def extract_url(xpath_results, search_url):
+    if xpath_results == []:
+        raise Exception('Empty url resultset')
     url = extract_text(xpath_results)
 
     if url.startswith('//'):
@@ -103,8 +103,8 @@ def response(resp):
     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(
diff --git a/searx/settings.yml b/searx/settings.yml
@@ -462,6 +462,17 @@ engines:
 #        - ...
 #    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