From 9ee8e552da4654cd41228ce1a3addfa1fa1f377d Mon Sep 17 00:00:00 2001 From: marc Date: Sat, 13 May 2017 02:22:27 -0500 Subject: [PATCH] [fix] bing images --- searx/engines/bing_images.py | 21 ++--- tests/unit/engines/test_bing_images.py | 113 ++++++++----------------- 2 files changed, 48 insertions(+), 86 deletions(-) diff --git a/searx/engines/bing_images.py b/searx/engines/bing_images.py index e79740e50..6300c94e4 100644 --- a/searx/engines/bing_images.py +++ b/searx/engines/bing_images.py @@ -31,7 +31,6 @@ time_range_support = True base_url = 'https://www.bing.com/' search_string = 'images/search?{query}&count=10&first={offset}' time_range_string = '&qft=+filterui:age-lt{interval}' -thumb_url = "https://www.bing.com/th?id={ihk}" time_range_dict = {'day': '1440', 'week': '10080', 'month': '43200', @@ -78,30 +77,32 @@ def response(resp): dom = html.fromstring(resp.text) # parse results - for result in dom.xpath('//div[@class="dg_u"]/div'): + for result in dom.xpath('//div[@id="mmComponent_images_1"]/ul/li/div/div[@class="imgpt"]'): link = result.xpath('./a')[0] + # TODO find actual title + title = link.xpath('.//img/@alt')[0] + # parse json-data (it is required to add a space, to make it parsable) json_data = loads(_quote_keys_regex.sub(r'\1"\2": \3', link.attrib.get('m'))) - title = link.attrib.get('t1') - ihk = link.attrib.get('ihk') + url = json_data.get('purl') + img_src = json_data.get('murl') - # url = 'http://' + link.attrib.get('t3') - url = json_data.get('surl') - img_src = json_data.get('imgurl') + thumb_json_data = loads(_quote_keys_regex.sub(r'\1"\2": \3', link.attrib.get('mad'))) + thumbnail = thumb_json_data.get('turl') # append result results.append({'template': 'images.html', 'url': url, 'title': title, 'content': '', - 'thumbnail_src': thumb_url.format(ihk=ihk), + 'thumbnail_src': thumbnail, 'img_src': img_src}) # TODO stop parsing if 10 images are found - if len(results) >= 10: - break + # if len(results) >= 10: + # break # return results return results diff --git a/tests/unit/engines/test_bing_images.py b/tests/unit/engines/test_bing_images.py index cc256f51e..287f13499 100644 --- a/tests/unit/engines/test_bing_images.py +++ b/tests/unit/engines/test_bing_images.py @@ -39,85 +39,46 @@ class TestBingImagesEngine(SearxTestCase): self.assertEqual(bing_images.response(response), []) html = """ -
- - - - -
- """ # noqa - html = html.replace('\r\n', '').replace('\n', '').replace('\r', '') - response = mock.Mock(text=html) - results = bing_images.response(response) - self.assertEqual(type(results), list) - self.assertEqual(len(results), 1) - self.assertEqual(results[0]['title'], 'South Carolina') - self.assertEqual(results[0]['url'], - 'http://www.digital-topo-maps.com/county-map/south-carolina.shtml') - self.assertEqual(results[0]['content'], '') - self.assertEqual(results[0]['thumbnail_src'], - 'https://www.bing.com/th?id=OIP.Mbf3bc87efe6e0e476be8cc34bf6cd80eH0') - self.assertEqual(results[0]['img_src'], - 'http://www.digital-topo-maps.com/county-map/south-carolina-county-map.gif') - - html = """ - - - - """ - response = mock.Mock(text=html) - results = bing_images.response(response) - self.assertEqual(type(results), list) - self.assertEqual(len(results), 0) - - html = """ -
- - - -
-
- - - -
-
- - - -
+
+ + +
""" html = html.replace('\r\n', '').replace('\n', '').replace('\r', '') response = mock.Mock(text=html) results = bing_images.response(response) self.assertEqual(type(results), list) self.assertEqual(len(results), 3) + self.assertEqual(results[0]['title'], 'alt text') + self.assertEqual(results[0]['url'], 'page_url') + self.assertEqual(results[0]['content'], '') + self.assertEqual(results[0]['thumbnail_src'], 'thumb_url') + self.assertEqual(results[0]['img_src'], 'img_url')