From ebbf33343a19089ea7b121ae3001dc528a4d7bf3 Mon Sep 17 00:00:00 2001 From: Adam Tauber Date: Mon, 1 Feb 2016 21:40:28 +0100 Subject: [PATCH] [fix] bing images changes --- searx/engines/bing_images.py | 16 ++++++++-------- tests/unit/engines/test_bing_images.py | 20 +++++++------------- 2 files changed, 15 insertions(+), 21 deletions(-) diff --git a/searx/engines/bing_images.py b/searx/engines/bing_images.py index 06850dfe1..2664b795f 100644 --- a/searx/engines/bing_images.py +++ b/searx/engines/bing_images.py @@ -17,7 +17,7 @@ from urllib import urlencode from lxml import html -from yaml import load +from json import loads import re # engine dependent config @@ -36,6 +36,9 @@ safesearch_types = {2: 'STRICT', 0: 'OFF'} +_quote_keys_regex = re.compile('({|,)([a-z][a-z0-9]*):(")', re.I | re.U) + + # do search-request def request(query, params): offset = (params['pageno'] - 1) * 10 + 1 @@ -65,22 +68,19 @@ def response(resp): dom = html.fromstring(resp.text) - # init regex for yaml-parsing - p = re.compile('({|,)([a-z]+):(")') - # parse results for result in dom.xpath('//div[@class="dg_u"]'): link = result.xpath('./a')[0] - # parse yaml-data (it is required to add a space, to make it parsable) - yaml_data = load(p.sub(r'\1\2: \3', link.attrib.get('m'))) + # 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 = 'http://' + link.attrib.get('t3') - url = yaml_data.get('surl') - img_src = yaml_data.get('imgurl') + url = json_data.get('surl') + img_src = json_data.get('imgurl') # append result results.append({'template': 'images.html', diff --git a/tests/unit/engines/test_bing_images.py b/tests/unit/engines/test_bing_images.py index f42dff7e8..5221d444b 100644 --- a/tests/unit/engines/test_bing_images.py +++ b/tests/unit/engines/test_bing_images.py @@ -39,16 +39,10 @@ class TestBingImagesEngine(SearxTestCase): html = """
- - + + +
""" html = html.replace('\r\n', '').replace('\n', '').replace('\r', '') @@ -56,11 +50,11 @@ oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%2 results = bing_images.response(response) self.assertEqual(type(results), list) self.assertEqual(len(results), 1) - self.assertEqual(results[0]['title'], 'Test Query') - self.assertEqual(results[0]['url'], 'http://www.page.url/') + 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=HN.608003696942779811') - self.assertEqual(results[0]['img_src'], 'http://test.url/Test%20Query.jpg') + 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 = """