Merge pull request #1075 from kvch/finish-jibe-b-engines

Finish PRs of @jibe-b: pubmed, oa_doi_rewrite, openaire, arxiv

searx/engines/arxiv.py

@@ -0,0 +1,76 @@
+#!/usr/bin/env python
+
+"""
+ ArXiV (Scientific preprints)
+ @website     https://arxiv.org
+ @provide-api yes (export.arxiv.org/api/query)
+ @using-api   yes
+ @results     XML-RSS
+ @stable      yes
+ @parse       url, title, publishedDate, content
+ More info on api: https://arxiv.org/help/api/user-manual
+"""
+
+from lxml import html
+from datetime import datetime
+from searx.url_utils import urlencode
+
+
+categories = ['science']
+
+base_url = 'http://export.arxiv.org/api/query?search_query=all:'\
+           + '{query}&start={offset}&max_results={number_of_results}'
+
+# engine dependent config
+number_of_results = 10
+
+
+def request(query, params):
+    # basic search
+    offset = (params['pageno'] - 1) * number_of_results
+
+    string_args = dict(query=query,
+                       offset=offset,
+                       number_of_results=number_of_results)
+
+    params['url'] = base_url.format(**string_args)
+
+    return params
+
+
+def response(resp):
+    results = []
+
+    dom = html.fromstring(resp.content)
+    search_results = dom.xpath('//entry')
+
+    for entry in search_results:
+        title = entry.xpath('.//title')[0].text
+
+        url = entry.xpath('.//id')[0].text
+
+        content_string = '{doi_content}{abstract_content}'
+
+        abstract = entry.xpath('.//summary')[0].text
+
+        #  If a doi is available, add it to the snipppet
+        try:
+            doi_content = entry.xpath('.//link[@title="doi"]')[0].text
+            content = content_string.format(doi_content=doi_content, abstract_content=abstract)
+        except:
+            content = content_string.format(doi_content="", abstract_content=abstract)
+
+        if len(content) > 300:
+                    content = content[0:300] + "..."
+        # TODO: center snippet on query term
+
+        publishedDate = datetime.strptime(entry.xpath('.//published')[0].text, '%Y-%m-%dT%H:%M:%SZ')
+
+        res_dict = {'url': url,
+                    'title': title,
+                    'publishedDate': publishedDate,
+                    'content': content}
+
+        results.append(res_dict)
+
+    return results

searx/engines/base.py

@@ -73,7 +73,7 @@ def request(query, params):
 def response(resp):
     results = []
 
-    search_results = etree.XML(resp.text)
+    search_results = etree.XML(resp.content)
 
     for entry in search_results.xpath('./result/doc'):
         content = "No description available"

searx/engines/pubmed.py

@@ -0,0 +1,98 @@
+#!/usr/bin/env python
+
+"""
+ PubMed (Scholar publications)
+ @website     https://www.ncbi.nlm.nih.gov/pubmed/
+ @provide-api yes (https://www.ncbi.nlm.nih.gov/home/develop/api/)
+ @using-api   yes
+ @results     XML
+ @stable      yes
+ @parse       url, title, publishedDate, content
+ More info on api: https://www.ncbi.nlm.nih.gov/books/NBK25501/
+"""
+
+from flask_babel import gettext
+from lxml import etree
+from datetime import datetime
+from searx.url_utils import urlencode
+from searx.poolrequests import get
+
+
+categories = ['science']
+
+base_url = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi'\
+           + '?db=pubmed&{query}&retstart={offset}&retmax={hits}'
+
+# engine dependent config
+number_of_results = 10
+pubmed_url = 'https://www.ncbi.nlm.nih.gov/pubmed/'
+
+
+def request(query, params):
+    # basic search
+    offset = (params['pageno'] - 1) * number_of_results
+
+    string_args = dict(query=urlencode({'term': query}),
+                       offset=offset,
+                       hits=number_of_results)
+
+    params['url'] = base_url.format(**string_args)
+
+    return params
+
+
+def response(resp):
+    results = []
+
+    # First retrieve notice of each result
+    pubmed_retrieve_api_url = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?'\
+                              + 'db=pubmed&retmode=xml&id={pmids_string}'
+
+    pmids_results = etree.XML(resp.content)
+    pmids = pmids_results.xpath('//eSearchResult/IdList/Id')
+    pmids_string = ''
+
+    for item in pmids:
+        pmids_string += item.text + ','
+
+    retrieve_notice_args = dict(pmids_string=pmids_string)
+
+    retrieve_url_encoded = pubmed_retrieve_api_url.format(**retrieve_notice_args)
+
+    search_results_xml = get(retrieve_url_encoded).content
+    search_results = etree.XML(search_results_xml).xpath('//PubmedArticleSet/PubmedArticle/MedlineCitation')
+
+    for entry in search_results:
+        title = entry.xpath('.//Article/ArticleTitle')[0].text
+
+        pmid = entry.xpath('.//PMID')[0].text
+        url = pubmed_url + pmid
+
+        try:
+            content = entry.xpath('.//Abstract/AbstractText')[0].text
+        except:
+            content = gettext('No abstract is available for this publication.')
+
+        #  If a doi is available, add it to the snipppet
+        try:
+            doi = entry.xpath('.//ELocationID[@EIdType="doi"]')[0].text
+            content = 'DOI: {doi} Abstract: {content}'.format(doi=doi, content=content)
+        except:
+            pass
+
+        if len(content) > 300:
+                    content = content[0:300] + "..."
+        # TODO: center snippet on query term
+
+        publishedDate = datetime.strptime(entry.xpath('.//DateCreated/Year')[0].text
+                                          + '-' + entry.xpath('.//DateCreated/Month')[0].text
+                                          + '-' + entry.xpath('.//DateCreated/Day')[0].text, '%Y-%m-%d')
+
+        res_dict = {'url': url,
+                    'title': title,
+                    'publishedDate': publishedDate,
+                    'content': content}
+
+        results.append(res_dict)
+
+        return results

searx/plugins/__init__.py

@@ -22,7 +22,7 @@ if version_info[0] == 3:
 
 logger = logger.getChild('plugins')
 
-from searx.plugins import (doai_rewrite,
+from searx.plugins import (oa_doi_rewrite,
                            https_rewrite,
                            infinite_scroll,
                            open_results_on_new_tab,
@@ -78,7 +78,7 @@ class PluginStore():
 
 
 plugins = PluginStore()
-plugins.register(doai_rewrite)
+plugins.register(oa_doi_rewrite)
 plugins.register(https_rewrite)
 plugins.register(infinite_scroll)
 plugins.register(open_results_on_new_tab)

searx/plugins/doai_rewrite.py → searx/plugins/oa_doi_rewrite.py

@@ -1,14 +1,18 @@
 from flask_babel import gettext
 import re
 from searx.url_utils import urlparse, parse_qsl
+from searx import settings
+
 
 regex = re.compile(r'10\.\d{4,9}/[^\s]+')
 
-name = gettext('DOAI rewrite')
+name = gettext('Open Access DOI rewrite')
 description = gettext('Avoid paywalls by redirecting to open-access versions of publications when available')
 default_on = False
 preference_section = 'privacy'
 
+doi_resolvers = settings['doi_resolvers']
+
 
 def extract_doi(url):
     match = regex.search(url.path)
@@ -21,12 +25,20 @@ def extract_doi(url):
     return None
 
 
+def get_doi_resolver(args, preference_doi_resolver):
+    doi_resolvers = settings['doi_resolvers']
+    doi_resolver = args.get('doi_resolver', preference_doi_resolver)[0]
+    if doi_resolver not in doi_resolvers:
+        doi_resolvers = settings['default_doi_resolver']
+    return doi_resolver
+
+
 def on_result(request, search, result):
     doi = extract_doi(result['parsed_url'])
     if doi and len(doi) < 50:
         for suffix in ('/', '.pdf', '/full', '/meta', '/abstract'):
             if doi.endswith(suffix):
                 doi = doi[:-len(suffix)]
-        result['url'] = 'http://doai.io/' + doi
+        result['url'] = get_doi_resolver(request.args, request.preferences.get_value('doi_resolver')) + doi
         result['parsed_url'] = urlparse(result['url'])
     return True

searx/preferences.py

@@ -15,6 +15,7 @@ LANGUAGE_CODES = [l[0] for l in languages]
 LANGUAGE_CODES.append('all')
 DISABLED = 0
 ENABLED = 1
+DOI_RESOLVERS = list(settings['doi_resolvers'])
 
 
 class MissingArgumentException(Exception):
@@ -266,7 +267,9 @@ class Preferences(object):
                                    'results_on_new_tab': MapSetting(False, map={'0': False,
                                                                                 '1': True,
                                                                                 'False': False,
-                                                                                'True': True})}
+                                                                                'True': True}),
+                                   'doi_resolver': MultipleChoiceSetting(['oadoi.org'], choices=DOI_RESOLVERS),
+                                   }
 
         self.engines = EnginesSetting('engines', choices=engines)
         self.plugins = PluginsSetting('plugins', choices=plugins)

searx/settings.yml

@@ -60,6 +60,12 @@ engines:
     disabled : True
     shortcut : ai
 
+  - name : arxiv
+    engine : arxiv
+    shortcut : arx
+    categories : science
+    timeout : 4.0
+
   - name : base
     engine : base
     shortcut : bs
@@ -409,6 +415,18 @@ engines:
     shortcut : nt
     disabled : True
 
+  - name : openaire
+    engine : json_engine
+    paging : True
+    search_url : http://api.openaire.eu/search/datasets?format=json&page={pageno}&size=10&title={query}
+    results_query : response/results/result
+    url_query : metadata/oaf:entity/oaf:result/children/instance/webresource/url/$
+    title_query : metadata/oaf:entity/oaf:result/title/$
+    content_query : metadata/oaf:entity/oaf:result/description/$
+    categories : science
+    shortcut : oa
+    timeout: 5.0
+
   - name : openstreetmap
     engine : openstreetmap
     shortcut : osm
@@ -442,6 +460,12 @@ engines:
     url: https://pirateproxy.red/
     timeout : 3.0
 
+  - name : pubmed
+    engine : pubmed
+    shortcut : pub
+    categories: science
+    timeout : 3.0
+
   - name : qwant
     engine : qwant
     shortcut : qw
@@ -694,3 +718,10 @@ locales:
     tr : Türkçe (Turkish)
     uk : українська мова (Ukrainian)
     zh : 中文 (Chinese)
+
+doi_resolvers :
+  oadoi.org : 'https://oadoi.org/'
+  doi.org : 'https://doi.org/'
+  doai.io  : 'http://doai.io/'
+
+default_doi_resolver : 'oadoi.org'

searx/templates/oscar/preferences.html

@@ -118,6 +118,18 @@
                             <option value="0" {% if not results_on_new_tab %}selected="selected"{% endif %}>{{ _('Off')}}</option>
                         </select>
                     {{ preferences_item_footer(info, label, rtl) }}
+
+                    {% set label = _('Open Access DOI resolver') %}
+                    {% set info = _('Redirect to open-access versions of publications when available (plugin required)') %}
+                    {{ preferences_item_header(info, label, rtl) }}
+                        <select class="form-control" id='doi_resolver' name='doi_resolver'>
+                            {% for doi_resolver_name,doi_resolver_url in doi_resolvers.items() %}
+                            <option value="{{ doi_resolver_name }}" {% if doi_resolver_name == current_doi_resolver %}selected="selected"{% endif %}>
+                                    {{ doi_resolver_name }} - {{ doi_resolver_url }}
+                            </option>
+                             {% endfor %}
+                         </select>
+                    {{ preferences_item_footer(info, label, rtl) }}
                 </div>
                 </fieldset>
             </div>

searx/webapp.py

@@ -66,6 +66,7 @@ from searx.search import SearchWithPlugins, get_search_query_from_webapp
 from searx.query import RawTextQuery
 from searx.autocomplete import searx_bang, backends as autocomplete_backends
 from searx.plugins import plugins
+from searx.plugins.oa_doi_rewrite import get_doi_resolver
 from searx.preferences import Preferences, ValidationException
 from searx.answerers import answerers
 from searx.url_utils import urlencode, urlparse, urljoin
@@ -695,6 +696,8 @@ def preferences():
                   shortcuts={y: x for x, y in engine_shortcuts.items()},
                   themes=themes,
                   plugins=plugins,
+                  doi_resolvers=settings['doi_resolvers'],
+                  current_doi_resolver=get_doi_resolver(request.args, request.preferences.get_value('doi_resolver')),
                   allowed_plugins=allowed_plugins,
                   theme=get_current_theme_name(),
                   preferences_url_params=request.preferences.get_as_url_params(),
@@ -839,7 +842,10 @@ def config():
                     'autocomplete': settings['search']['autocomplete'],
                     'safe_search': settings['search']['safe_search'],
                     'default_theme': settings['ui']['default_theme'],
-                    'version': VERSION_STRING})
+                    'version': VERSION_STRING,
+                    'doi_resolvers': [r for r in search['doi_resolvers']],
+                    'default_doi_resolver': settings['default_doi_resolver'],
+                    })
 
 
 @app.errorhandler(404)

tests/unit/engines/pubmed.py

@@ -0,0 +1,37 @@
+# -*- coding: utf-8 -*-
+from collections import defaultdict
+import mock
+from searx.engines import pubmed
+from searx.testing import SearxTestCase
+
+
+class TestPubmedEngine(SearxTestCase):
+
+    def test_request(self):
+        query = 'test_query'
+        dicto = defaultdict(dict)
+        dicto['pageno'] = 1
+        params = pubmed.request(query, dicto)
+        self.assertIn('url', params)
+        self.assertIn('eutils.ncbi.nlm.nih.gov/', params['url'])
+        self.assertIn('term', params['url'])
+
+    def test_response(self):
+        self.assertRaises(AttributeError, pubmed.response, None)
+        self.assertRaises(AttributeError, pubmed.response, [])
+        self.assertRaises(AttributeError, pubmed.response, '')
+        self.assertRaises(AttributeError, pubmed.response, '[]')
+
+        response = mock.Mock(text='<PubmedArticleSet></PubmedArticleSet>')
+        self.assertEqual(pubmed.response(response), [])
+
+        xml_mock = """<eSearchResult><Count>1</Count><RetMax>1</RetMax><RetStart>0</RetStart><IdList>
+<Id>1</Id>
+</IdList></eSearchResult>
+"""
+
+        response = mock.Mock(text=xml_mock.encode('utf-8'))
+        results = pubmed.response(response)
+        self.assertEqual(type(results), list)
+        self.assertEqual(len(results), 1)
+        self.assertEqual(results[0]['content'], 'No abstract is available for this publication.')

tests/unit/engines/test_arxiv.py

@@ -0,0 +1,58 @@
+# -*- coding: utf-8 -*-
+from collections import defaultdict
+import mock
+from searx.engines import arxiv
+from searx.testing import SearxTestCase
+
+
+class TestBaseEngine(SearxTestCase):
+
+    def test_request(self):
+        query = 'test_query'
+        dicto = defaultdict(dict)
+        dicto['pageno'] = 1
+        params = arxiv.request(query, dicto)
+        self.assertIn('url', params)
+        self.assertIn('export.arxiv.org/api/', params['url'])
+
+    def test_response(self):
+        self.assertRaises(AttributeError, arxiv.response, None)
+        self.assertRaises(AttributeError, arxiv.response, [])
+        self.assertRaises(AttributeError, arxiv.response, '')
+        self.assertRaises(AttributeError, arxiv.response, '[]')
+
+        response = mock.Mock(content=b'''<?xml version="1.0" encoding="UTF-8"?>
+<feed xmlns="http://www.w3.org/2005/Atom"></feed>''')
+        self.assertEqual(arxiv.response(response), [])
+
+        xml_mock = b'''<?xml version="1.0" encoding="UTF-8"?>
+<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>
+  <id>http://arxiv.org/api/1</id>
+  <updated>2000-01-21T00:00:00-01:00</updated>
+  <opensearch:totalResults xmlns:opensearch="http://a9.com/-/spec/opensearch/1.1/">1</opensearch:totalResults>
+  <opensearch:startIndex xmlns:opensearch="http://a9.com/-/spec/opensearch/1.1/">0</opensearch:startIndex>
+  <opensearch:itemsPerPage xmlns:opensearch="http://a9.com/-/spec/opensearch/1.1/">1</opensearch:itemsPerPage>
+  <entry>
+    <id>http://arxiv.org/1</id>
+    <updated>2000-01-01T00:00:01Z</updated>
+    <published>2000-01-01T00:00:01Z</published>
+    <title>Mathematical proof.</title>
+    <summary>Mathematical formula.</summary>
+    <author>
+      <name>A. B.</name>
+    </author>
+    <link href="http://arxiv.org/1" rel="alternate" type="text/html"/>
+    <link title="pdf" href="http://arxiv.org/1" rel="related" type="application/pdf"/>
+    <category term="math.QA" scheme="http://arxiv.org/schemas/atom"/>
+    <category term="1" scheme="http://arxiv.org/schemas/atom"/>
+  </entry>
+</feed>
+'''
+
+        response = mock.Mock(content=xml_mock)
+        results = arxiv.response(response)
+        self.assertEqual(type(results), list)
+        self.assertEqual(len(results), 1)
+        self.assertEqual(results[0]['title'], 'Mathematical proof.')
+        self.assertEqual(results[0]['content'], 'Mathematical formula.')

tests/unit/engines/test_base.py

@@ -21,10 +21,10 @@ class TestBaseEngine(SearxTestCase):
         self.assertRaises(AttributeError, base.response, '')
         self.assertRaises(AttributeError, base.response, '[]')
 
-        response = mock.Mock(text='<response></response>')
+        response = mock.Mock(content=b'<response></response>')
         self.assertEqual(base.response(response), [])
 
-        xml_mock = """<?xml version="1.0"?>
+        xml_mock = b"""<?xml version="1.0"?>
 <response>
   <lst name="responseHeader">
     <int name="status">0</int>
@@ -83,7 +83,7 @@ class TestBaseEngine(SearxTestCase):
   </result>
 </response>"""
 
-        response = mock.Mock(text=xml_mock.encode('utf-8'))
+        response = mock.Mock(content=xml_mock)
         results = base.response(response)
         self.assertEqual(type(results), list)
         self.assertEqual(len(results), 1)