logo

searx

My custom branche(s) on searx, a meta-search engine
commit: 80df181575d3dac663434c8ed290dc3e4eb3dcae
parent: ddd5c2632ff92947d80e530e93ba65c62537a298
Author: Adam Tauber <asciimoo@gmail.com>
Date:   Thu, 23 Mar 2017 21:25:52 +0100

Merge pull request #881 from mmuman/framalibre

Add framalibre engine

Diffstat:

Asearx/engines/framalibre.py72++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Msearx/settings.yml5+++++
Atests/unit/engines/test_framalibre.py103+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 180 insertions(+), 0 deletions(-)

diff --git a/searx/engines/framalibre.py b/searx/engines/framalibre.py @@ -0,0 +1,72 @@ +""" + FramaLibre (It) + + @website https://framalibre.org/ + @provide-api no + + @using-api no + @results HTML + @stable no (HTML can change) + @parse url, title, content, thumbnail, img_src +""" + +from urlparse import urljoin +from cgi import escape +from urllib import urlencode +from lxml import html +from searx.engines.xpath import extract_text +from dateutil import parser + +# engine dependent config +categories = ['it'] +paging = True + +# search-url +base_url = 'https://framalibre.org/' +search_url = base_url + 'recherche-par-crit-res?{query}&page={offset}' + +# specific xpath variables +results_xpath = '//div[@class="nodes-list-row"]/div[contains(@typeof,"sioc:Item")]' +link_xpath = './/h3[@class="node-title"]/a[@href]' +thumbnail_xpath = './/img[@class="media-object img-responsive"]/@src' +content_xpath = './/div[@class="content"]//p' + + +# do search-request +def request(query, params): + offset = (params['pageno'] - 1) + params['url'] = search_url.format(query=urlencode({'keys': query}), + offset=offset) + + return params + + +# get response from search-request +def response(resp): + results = [] + + dom = html.fromstring(resp.text) + + # parse results + for result in dom.xpath(results_xpath): + link = result.xpath(link_xpath)[0] + href = urljoin(base_url, link.attrib.get('href')) + # there's also a span (class="rdf-meta element-hidden" property="dc:title")'s content property for this... + title = escape(extract_text(link)) + thumbnail_tags = result.xpath(thumbnail_xpath) + thumbnail = None + if len(thumbnail_tags) > 0: + thumbnail = extract_text(thumbnail_tags[0]) + if thumbnail[0] == '/': + thumbnail = base_url + thumbnail + content = escape(extract_text(result.xpath(content_xpath))) + + # append result + results.append({'url': href, + 'title': title, + 'thumbnail': thumbnail, + 'img_src': thumbnail, + 'content': content}) + + # return results + return results diff --git a/searx/settings.yml b/searx/settings.yml @@ -465,6 +465,11 @@ engines: shortcut : scc disabled : True + - name : framalibre + engine : framalibre + shortcut : frl + disabled : True + # - name : searx # engine : searx_engine # shortcut : se diff --git a/tests/unit/engines/test_framalibre.py b/tests/unit/engines/test_framalibre.py @@ -0,0 +1,103 @@ +# -*- coding: utf-8 -*- +from collections import defaultdict +import mock +from searx.engines import framalibre +from searx.testing import SearxTestCase + + +class TestFramalibreEngine(SearxTestCase): + + def test_request(self): + query = 'test_query' + dicto = defaultdict(dict) + dicto['pageno'] = 0 + params = framalibre.request(query, dicto) + self.assertTrue('url' in params) + self.assertTrue(query in params['url']) + self.assertTrue('framalibre.org' in params['url']) + + def test_response(self): + self.assertRaises(AttributeError, framalibre.response, None) + self.assertRaises(AttributeError, framalibre.response, []) + self.assertRaises(AttributeError, framalibre.response, '') + self.assertRaises(AttributeError, framalibre.response, '[]') + + response = mock.Mock(text='{}') + self.assertEqual(framalibre.response(response), []) + + response = mock.Mock(text='{"data": []}') + self.assertEqual(framalibre.response(response), []) + + html = u""" + <div class="nodes-list-row"> + <div id="node-431" + class="node node-logiciel-annuaires node-promoted node-teaser node-teaser node-sheet clearfix nodes-list" + about="/content/gogs" typeof="sioc:Item foaf:Document"> + <header class="media"> + <div class="media-left"> + <div class="field field-name-field-logo field-type-image field-label-hidden"> + <div class="field-items"> + <div class="field-item even"> + <a href="/content/gogs"> + <img class="media-object img-responsive" typeof="foaf:Image" + src="https://framalibre.org/sites/default/files/styles/teaser_logo/public/leslogos/gogs-lg.png?itok=rrCxKKBy" + width="70" height="70" alt="" /> + </a> + </div> + </div> + </div> + </div> + <div class="media-body"> + <h3 class="node-title"><a href="/content/gogs">Gogs</a></h3> + <span property="dc:title" content="Gogs" class="rdf-meta element-hidden"></span> + <div class="field field-name-field-annuaires field-type-taxonomy-term-reference field-label-hidden"> + <div class="field-items"> + <div class="field-item even"> + <a href="/annuaires/cloudwebapps" + typeof="skos:Concept" property="rdfs:label skos:prefLabel" + datatype="" class="label label-primary">Cloud/webApps</a> + </div> + </div> + </div> + </div> + </header> + <div class="content"> + <div class="field field-name-field-votre-appr-ciation field-type-fivestar field-label-hidden"> + <div class="field-items"> + <div class="field-item even"> + </div> + </div> + </div> + <div class="field field-name-body field-type-text-with-summary field-label-hidden"> + <div class="field-items"> + <div class="field-item even" property="content:encoded"> + <p>Gogs est une interface web basée sur git et une bonne alternative à GitHub.</p> + </div> + </div> + </div> + </div> + <footer> + <a href="/content/gogs" class="read-more btn btn-default btn-sm">Voir la notice</a> + <div class="field field-name-field-lien-officiel field-type-link-field field-label-hidden"> + <div class="field-items"> + <div class="field-item even"> + <a href="https://gogs.io/" target="_blank" title="Voir le site officiel"> + <span class="glyphicon glyphicon-globe"></span> + <span class="sr-only">Lien officiel</span> + </a> + </div> + </div> + </div> + </footer> + </div> + </div> + """ + response = mock.Mock(text=html) + results = framalibre.response(response) + self.assertEqual(type(results), list) + self.assertEqual(len(results), 1) + self.assertEqual(results[0]['title'], 'Gogs') + self.assertEqual(results[0]['url'], + 'https://framalibre.org/content/gogs') + self.assertEqual(results[0]['content'], + u"Gogs est une interface web basée sur git et une bonne alternative à GitHub.")