diff --git a/searx/engines/subtitleseeker.py b/searx/engines/subtitleseeker.py index 9aaf1947..acefe30e 100644 --- a/searx/engines/subtitleseeker.py +++ b/searx/engines/subtitleseeker.py @@ -12,6 +12,7 @@ from cgi import escape from urllib import quote_plus from lxml import html from searx.languages import language_codes +from searx.engines.xpath import extract_text # engine dependent config categories = ['videos'] @@ -20,7 +21,7 @@ language = "" # search-url url = 'http://www.subtitleseeker.com/' -search_url = url+'search/TITLES/{query}&p={pageno}' +search_url = url + 'search/TITLES/{query}&p={pageno}' # specific xpath variables results_xpath = '//div[@class="boxRows"]' @@ -44,7 +45,7 @@ def response(resp): if resp.search_params['language'] != 'all': search_lang = [lc[1] for lc in language_codes - if lc[0][:2] == resp.search_params['language']][0] + if lc[0][:2] == resp.search_params['language'].split('_')[0]][0] # parse results for result in dom.xpath(results_xpath): @@ -56,17 +57,17 @@ def response(resp): elif search_lang: href = href + search_lang + '/' - title = escape(link.xpath(".//text()")[0]) + title = escape(extract_text(link)) - content = result.xpath('.//div[contains(@class,"red")]//text()')[0] + content = extract_text(result.xpath('.//div[contains(@class,"red")]')) content = content + " - " - text = result.xpath('.//div[contains(@class,"grey-web")]')[0] - content = content + html.tostring(text, method='text') + text = extract_text(result.xpath('.//div[contains(@class,"grey-web")]')[0]) + content = content + text if result.xpath(".//span") != []: content = content +\ " - (" +\ - result.xpath(".//span//text()")[0].strip() +\ + extract_text(result.xpath(".//span")) +\ ")" # append result diff --git a/searx/tests/engines/test_subtitleseeker.py b/searx/tests/engines/test_subtitleseeker.py new file mode 100644 index 00000000..a641601b --- /dev/null +++ b/searx/tests/engines/test_subtitleseeker.py @@ -0,0 +1,169 @@ +from collections import defaultdict +import mock +from searx.engines import subtitleseeker +from searx.testing import SearxTestCase + + +class TestSubtitleseekerEngine(SearxTestCase): + + def test_request(self): + query = 'test_query' + dicto = defaultdict(dict) + dicto['pageno'] = 1 + params = subtitleseeker.request(query, dicto) + self.assertTrue('url' in params) + self.assertTrue(query in params['url']) + self.assertTrue('subtitleseeker.com' in params['url']) + + def test_response(self): + dicto = defaultdict(dict) + dicto['language'] = 'fr_FR' + response = mock.Mock(search_params=dicto) + + self.assertRaises(AttributeError, subtitleseeker.response, None) + self.assertRaises(AttributeError, subtitleseeker.response, []) + self.assertRaises(AttributeError, subtitleseeker.response, '') + self.assertRaises(AttributeError, subtitleseeker.response, '[]') + + response = mock.Mock(text='', search_params=dicto) + self.assertEqual(subtitleseeker.response(response), []) + + html = """ +