OwlBurst/Ponysearch
1
0
Fork 0
forked from Ponysearch/Ponysearch
Code Pull requests Activity

minor fixes of arxiv

Browse source 
Closes #1050
This commit is contained in:
Noémi Ványi 2017-11-01 12:28:18 +01:00
parent e391b2d970
commit 9c2b7a82f0
2 changed files with 9 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
searx/engines/arxiv.py
View file

@ -2,7 +2,7 @@
""" """
ArXiV (Scientific preprints) ArXiV (Scientific preprints)
@website https://axiv.org @website https://arxiv.org
@provide-api yes (export.arxiv.org/api/query) @provide-api yes (export.arxiv.org/api/query)
@using-api yes @using-api yes
@results XML-RSS @results XML-RSS
@ -41,7 +41,8 @@ def request(query, params):
def response(resp): def response(resp):
results = [] results = []
search_results = html.fromstring(resp.text).xpath('//entry') dom = html.fromstring(resp.content)
search_results = dom.xpath('//entry')
for entry in search_results: for entry in search_results:
title = entry.xpath('.//title')[0].text title = entry.xpath('.//title')[0].text
@ -49,15 +50,15 @@ def response(resp):
url = entry.xpath('.//id')[0].text url = entry.xpath('.//id')[0].text
content_string = '{doi_content}{abstract_content}' content_string = '{doi_content}{abstract_content}'
abstract = entry.xpath('.//summary')[0].text abstract = entry.xpath('.//summary')[0].text
# If a doi is available, add it to the snipppet # If a doi is available, add it to the snipppet
try: try:
doi_content = entry.xpath('.//link[@title="doi"]')[0].text doi_content = entry.xpath('.//link[@title="doi"]')[0].text
content = content_string.format(doi_content=doi_content, abstract_content=abstract_content) content = content_string.format(doi_content=doi_content, abstract_content=abstract)
except: except:
content = content_string.format(abstract_content=abstract_content) content = content_string.format(doi_content="", abstract_content=abstract)
if len(content) > 300: if len(content) > 300:
content = content[0:300] + "..." content = content[0:300] + "..."

6
tests/unit/engines/test_arxiv.py
View file

@ -21,11 +21,11 @@ class TestBaseEngine(SearxTestCase):
self.assertRaises(AttributeError, arxiv.response, '') self.assertRaises(AttributeError, arxiv.response, '')
self.assertRaises(AttributeError, arxiv.response, '[]') self.assertRaises(AttributeError, arxiv.response, '[]')
response = mock.Mock(text='''<?xml version="1.0" encoding="UTF-8"?> response = mock.Mock(content=b'''<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom"></feed>''') <feed xmlns="http://www.w3.org/2005/Atom"></feed>''')
self.assertEqual(arxiv.response(response), []) self.assertEqual(arxiv.response(response), [])
xml_mock = '''<?xml version="1.0" encoding="UTF-8"?> xml_mock = b'''<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom"> <feed xmlns="http://www.w3.org/2005/Atom">
<title type="html">ArXiv Query: search_query=all:test_query&amp;id_list=&amp;start=0&amp;max_results=1</title> <title type="html">ArXiv Query: search_query=all:test_query&amp;id_list=&amp;start=0&amp;max_results=1</title>
<id>http://arxiv.org/api/1</id> <id>http://arxiv.org/api/1</id>
@ -50,7 +50,7 @@ class TestBaseEngine(SearxTestCase):
</feed> </feed>
''' '''
response = mock.Mock(text=xml_mock.encode('utf-8')) response = mock.Mock(content=xml_mock)
results = arxiv.response(response) results = arxiv.response(response)
self.assertEqual(type(results), list) self.assertEqual(type(results), list)
self.assertEqual(len(results), 1) self.assertEqual(len(results), 1)