logo

searx

My custom branche(s) on searx, a meta-search engine
commit: 856dfc3018083d62308f18f36b50e5b0d767edf6
parent: 081f51db4ef057e34fc1b9934d0c0cc19427f512
Author: marc <a01200356@itesm.mx>
Date:   Fri, 21 Jul 2017 22:17:28 -0500

add google videos

Diffstat:

Asearx/engines/google_videos.py83+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Msearx/settings.yml4++++
Atests/unit/engines/test_google_videos.py60++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 147 insertions(+), 0 deletions(-)

diff --git a/searx/engines/google_videos.py b/searx/engines/google_videos.py @@ -0,0 +1,83 @@ +""" + Google (Videos) + + @website https://www.google.com + @provide-api yes (https://developers.google.com/custom-search/) + + @using-api no + @results HTML + @stable no + @parse url, title, content +""" + +from datetime import date, timedelta +from json import loads +from lxml import html +from searx.engines.xpath import extract_text +from searx.url_utils import urlencode + + +# engine dependent config +categories = ['videos'] +paging = True +safesearch = True +time_range_support = True +number_of_results = 10 + +search_url = 'https://www.google.com/search'\ + '?{query}'\ + '&tbm=vid'\ + '&{search_options}' +time_range_attr = "qdr:{range}" +time_range_custom_attr = "cdr:1,cd_min:{start},cd_max{end}" +time_range_dict = {'day': 'd', + 'week': 'w', + 'month': 'm'} + + +# do search-request +def request(query, params): + search_options = { + 'ijn': params['pageno'] - 1, + 'start': (params['pageno'] - 1) * number_of_results + } + + if params['time_range'] in time_range_dict: + search_options['tbs'] = time_range_attr.format(range=time_range_dict[params['time_range']]) + elif params['time_range'] == 'year': + now = date.today() + then = now - timedelta(days=365) + start = then.strftime('%m/%d/%Y') + end = now.strftime('%m/%d/%Y') + search_options['tbs'] = time_range_custom_attr.format(start=start, end=end) + + if safesearch and params['safesearch']: + search_options['safe'] = 'on' + + params['url'] = search_url.format(query=urlencode({'q': query}), + search_options=urlencode(search_options)) + + return params + + +# get response from search-request +def response(resp): + results = [] + + dom = html.fromstring(resp.text) + + # parse results + for result in dom.xpath('//div[@class="g"]'): + + title = extract_text(result.xpath('.//h3/a')) + url = result.xpath('.//h3/a/@href')[0] + content = extract_text(result.xpath('.//span[@class="st"]')) + + # append result + results.append({'url': url, + 'title': title, + 'content': content, + 'thumbnail': '', + 'template': 'videos.html'}) + + return results diff --git a/searx/settings.yml b/searx/settings.yml @@ -266,6 +266,10 @@ engines: engine : google_news shortcut : gon + - name : google videos + engine : google_videos + shortcut : gov + - name : google scholar engine : xpath paging : True diff --git a/tests/unit/engines/test_google_videos.py b/tests/unit/engines/test_google_videos.py @@ -0,0 +1,60 @@ +from collections import defaultdict +import mock +from searx.engines import google_videos +from searx.testing import SearxTestCase + + +class TestGoogleVideosEngine(SearxTestCase): + + def test_request(self): + query = 'test_query' + dicto = defaultdict(dict) + dicto['pageno'] = 1 + dicto['safesearch'] = 1 + dicto['time_range'] = '' + params = google_videos.request(query, dicto) + self.assertIn('url', params) + self.assertIn(query, params['url']) + + dicto['safesearch'] = 0 + params = google_videos.request(query, dicto) + self.assertNotIn('safe', params['url']) + + def test_response(self): + self.assertRaises(AttributeError, google_videos.response, None) + self.assertRaises(AttributeError, google_videos.response, []) + self.assertRaises(AttributeError, google_videos.response, '') + self.assertRaises(AttributeError, google_videos.response, '[]') + + html = r""" + <div> + <div> + <div class="g"> + <div> + <h3><a href="url_1">Title 1</h3> + </div> + <div> + <span class="st">Content 1</span> + </div> + </div> + <div class="g"> + <div> + <h3><a href="url_2">Title 2</h3> + </div> + <div> + <span class="st">Content 2</span> + </div> + </div> + </div> + </div> + """ + response = mock.Mock(text=html) + results = google_videos.response(response) + self.assertEqual(type(results), list) + self.assertEqual(len(results), 2) + self.assertEqual(results[0]['url'], u'url_1') + self.assertEqual(results[0]['title'], u'Title 1') + self.assertEqual(results[0]['content'], u'Content 1') + self.assertEqual(results[1]['url'], u'url_2') + self.assertEqual(results[1]['title'], u'Title 2') + self.assertEqual(results[1]['content'], u'Content 2')