summaryrefslogtreecommitdiff
path: root/searx
diff options
context:
space:
mode:
authormarc <a01200356@itesm.mx>2017-05-13 02:22:27 -0500
committerAdam Tauber <asciimoo@gmail.com>2017-05-17 15:45:55 +0200
commit9ee8e552da4654cd41228ce1a3addfa1fa1f377d (patch)
tree205ac3dfb49faa6e7d91359764cc1774e5552778 /searx
parentc0bb89fd4660b0577f29a184bf330c0a276930df (diff)
downloadsearxng-9ee8e552da4654cd41228ce1a3addfa1fa1f377d.tar.gz
searxng-9ee8e552da4654cd41228ce1a3addfa1fa1f377d.zip
[fix] bing images
Diffstat (limited to 'searx')
-rw-r--r--searx/engines/bing_images.py21
1 files changed, 11 insertions, 10 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