[mod] science category: various update of about PR 1705

searx/engines/crossref.py

@@ -33,10 +33,10 @@ def response(resp):
         if record_type == 'book-chapter':
             title = record['container-title'][0]
             if record['title'][0].lower().strip() != title.lower().strip():
-                title = title + ' (' + record['title'][0] + ')'
+                title = html_to_text(title) + ' (' + html_to_text(record['title'][0]) + ')'
             journal = None
         else:
-            title = record['title'][0]
+            title = html_to_text(record['title'][0])
             journal = record.get('container-title', [None])[0]
         url = record.get('resource', {}).get('primary', {}).get('URL') or record['URL']
         authors = [author.get('given', '') + ' ' + author.get('family', '') for author in record.get('author', [])]

searx/engines/semantic_scholar.py

@@ -48,7 +48,6 @@ def request(query, params):
 def response(resp):
     res = loads(resp.text)
     results = []
-
     for result in res['results']:
         url = result.get('primaryPaperLink', {}).get('url')
         if not url and result.get('links'):
@@ -72,7 +71,7 @@ def response(resp):
         # pick for the first alternate link, but not from the crawler
         pdf_url = None
         for doc in result.get('alternatePaperLinks', []):
-            if doc['linkType'] != 'crawler':
+            if doc['linkType'] not in ('crawler', 'doi'):
                 pdf_url = doc['url']
                 break
 

searx/engines/springer.py

@@ -58,8 +58,7 @@ def response(resp):
                 'authors': authors,
                 'doi': record.get('doi'),
                 'journal': record.get('publicationName'),
-                'start_page': record.get('start_page'),
-                'end_page': record.get('end_page'),
+                'pages': record.get('start_page') + '-' + record.get('end_page'),
                 'tags': tags,
                 'issn': [record.get('issn')],
                 'isbn': [record.get('isbn')],