diff options
| author | Alexandre Flament <alex@al-f.net> | 2022-09-23 19:58:14 +0200 |
|---|---|---|
| committer | Alexandre Flament <alex@al-f.net> | 2022-09-23 20:52:55 +0200 |
| commit | d6446be38f3f858c09887a89c8fc490a3c300b95 (patch) | |
| tree | 1b911cba1b96970455b115d1cc706db52d5613da /searx/engines | |
| parent | 08b88597052dfdf17e947289d79510fdadad51e3 (diff) | |
| download | searxng-d6446be38f3f858c09887a89c8fc490a3c300b95.tar.gz searxng-d6446be38f3f858c09887a89c8fc490a3c300b95.zip | |
[mod] science category: various update of about PR 1705
Diffstat (limited to 'searx/engines')
| -rw-r--r-- | searx/engines/crossref.py | 4 | ||||
| -rw-r--r-- | searx/engines/semantic_scholar.py | 3 | ||||
| -rw-r--r-- | searx/engines/springer.py | 3 |
3 files changed, 4 insertions, 6 deletions
diff --git a/searx/engines/crossref.py b/searx/engines/crossref.py index d61318146..fbe2f0c2a 100644 --- a/searx/engines/crossref.py +++ b/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', [])] diff --git a/searx/engines/semantic_scholar.py b/searx/engines/semantic_scholar.py index b2701c333..7a1b5b231 100644 --- a/searx/engines/semantic_scholar.py +++ b/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 diff --git a/searx/engines/springer.py b/searx/engines/springer.py index 2711fa807..e5255b794 100644 --- a/searx/engines/springer.py +++ b/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')], |