forked from Ponysearch/Ponysearch
[fix] bing_videos (#1579)
use JSON where possible, compose 'content' using all available data, use correct 'url' (direct to source instead of redirect through bing)
This commit is contained in:
Frank de Lange
Alexandre Flament
parent
4b56a4bfaa
commit
204a2cbbf0
2 changed files with 40 additions and 62 deletions
|
|
@ -13,7 +13,6 @@
|
||||||
from json import loads
|
from json import loads
|
||||||
from lxml import html
|
from lxml import html
|
||||||
from searx.engines.bing_images import _fetch_supported_languages, supported_languages_url
|
from searx.engines.bing_images import _fetch_supported_languages, supported_languages_url
|
||||||
from searx.engines.xpath import extract_text
|
|
||||||
from searx.url_utils import urlencode
|
from searx.url_utils import urlencode
|
||||||
from searx.utils import match_language
|
from searx.utils import match_language
|
||||||
|
|
||||||
|
|
@ -22,11 +21,16 @@ categories = ['videos']
|
||||||
paging = True
|
paging = True
|
||||||
safesearch = True
|
safesearch = True
|
||||||
time_range_support = True
|
time_range_support = True
|
||||||
number_of_results = 10
|
number_of_results = 28
|
||||||
language_support = True
|
language_support = True
|
||||||
|
|
||||||
search_url = 'https://www.bing.com/videos/asyncv2?{query}&async=content&'\
|
base_url = 'https://www.bing.com/'
|
||||||
'first={offset}&count={number_of_results}&CW=1366&CH=25&FORM=R5VR5'
|
search_string = 'videos/search'\
|
||||||
|
'?{query}'\
|
||||||
|
'&count={count}'\
|
||||||
|
'&first={first}'\
|
||||||
|
'&scope=video'\
|
||||||
|
'&FORM=QBLH'
|
||||||
time_range_string = '&qft=+filterui:videoage-lt{interval}'
|
time_range_string = '&qft=+filterui:videoage-lt{interval}'
|
||||||
time_range_dict = {'day': '1440',
|
time_range_dict = {'day': '1440',
|
||||||
'week': '10080',
|
'week': '10080',
|
||||||
|
|
@ -41,7 +45,12 @@ safesearch_types = {2: 'STRICT',
|
||||||
|
|
||||||
# do search-request
|
# do search-request
|
||||||
def request(query, params):
|
def request(query, params):
|
||||||
offset = (params['pageno'] - 1) * 10 + 1
|
offset = ((params['pageno'] - 1) * number_of_results) + 1
|
||||||
|
|
||||||
|
search_path = search_string.format(
|
||||||
|
query=urlencode({'q': query}),
|
||||||
|
count=number_of_results,
|
||||||
|
first=offset)
|
||||||
|
|
||||||
# safesearch cookie
|
# safesearch cookie
|
||||||
params['cookies']['SRCHHPGUSR'] = \
|
params['cookies']['SRCHHPGUSR'] = \
|
||||||
|
|
@ -52,9 +61,7 @@ def request(query, params):
|
||||||
params['cookies']['_EDGE_S'] = 'mkt=' + language + '&F=1'
|
params['cookies']['_EDGE_S'] = 'mkt=' + language + '&F=1'
|
||||||
|
|
||||||
# query and paging
|
# query and paging
|
||||||
params['url'] = search_url.format(query=urlencode({'q': query}),
|
params['url'] = base_url + search_path
|
||||||
offset=offset,
|
|
||||||
number_of_results=number_of_results)
|
|
||||||
|
|
||||||
# time range
|
# time range
|
||||||
if params['time_range'] in time_range_dict:
|
if params['time_range'] in time_range_dict:
|
||||||
|
|
@ -70,19 +77,18 @@ def response(resp):
|
||||||
dom = html.fromstring(resp.text)
|
dom = html.fromstring(resp.text)
|
||||||
|
|
||||||
for result in dom.xpath('//div[@class="dg_u"]'):
|
for result in dom.xpath('//div[@class="dg_u"]'):
|
||||||
url = result.xpath('./div[@class="mc_vtvc"]/a/@href')[0]
|
try:
|
||||||
url = 'https://bing.com' + url
|
metadata = loads(result.xpath('.//div[@class="vrhdata"]/@vrhm')[0])
|
||||||
title = extract_text(result.xpath('./div/a/div/div[@class="mc_vtvc_title"]/@title'))
|
info = ' - '.join(result.xpath('.//div[@class="mc_vtvc_meta_block"]//span/text()')).strip()
|
||||||
content = extract_text(result.xpath('./div/a/div/div/div/div/text()'))
|
content = '{0} - {1}'.format(metadata['du'], info)
|
||||||
thumbnail = result.xpath('./div/a/div/div/img/@src')[0]
|
thumbnail = '{0}th?id={1}'.format(base_url, metadata['thid'])
|
||||||
|
results.append({'url': metadata['murl'],
|
||||||
|
'thumbnail': thumbnail,
|
||||||
|
'title': metadata.get('vt', ''),
|
||||||
|
'content': content,
|
||||||
|
'template': 'videos.html'})
|
||||||
|
|
||||||
results.append({'url': url,
|
except:
|
||||||
'title': title,
|
continue
|
||||||
'content': content,
|
|
||||||
'thumbnail': thumbnail,
|
|
||||||
'template': 'videos.html'})
|
|
||||||
|
|
||||||
if len(results) >= number_of_results:
|
|
||||||
break
|
|
||||||
|
|
||||||
return results
|
return results
|
||||||
|
|
|
||||||
|
|
@ -29,7 +29,7 @@ class TestBingVideosEngine(SearxTestCase):
|
||||||
dicto['time_range'] = 'day'
|
dicto['time_range'] = 'day'
|
||||||
dicto['safesearch'] = 2
|
dicto['safesearch'] = 2
|
||||||
params = bing_videos.request(query, dicto)
|
params = bing_videos.request(query, dicto)
|
||||||
self.assertTrue('first=11' in params['url'])
|
self.assertTrue('first=29' in params['url'])
|
||||||
self.assertTrue('1440' in params['url'])
|
self.assertTrue('1440' in params['url'])
|
||||||
self.assertIn('SRCHHPGUSR', params['cookies'])
|
self.assertIn('SRCHHPGUSR', params['cookies'])
|
||||||
self.assertTrue('STRICT' in params['cookies']['SRCHHPGUSR'])
|
self.assertTrue('STRICT' in params['cookies']['SRCHHPGUSR'])
|
||||||
|
|
@ -48,53 +48,25 @@ class TestBingVideosEngine(SearxTestCase):
|
||||||
|
|
||||||
html = """
|
html = """
|
||||||
<div class="dg_u">
|
<div class="dg_u">
|
||||||
<div id="mc_vtvc_1" class="mc_vtvc">
|
<div>
|
||||||
<a class="mc_vtvc_link" href="/video">
|
<a>
|
||||||
<div class="mc_vtvc_th">
|
<div>
|
||||||
<div class="cico">
|
<div>
|
||||||
<img src="thumb_1.jpg" />
|
<div class="mc_vtvc_meta_block">
|
||||||
</div>
|
<div><span>100 views</span><span>1 year ago</span></div><div><span>ExampleTube</span><span>Channel 1<span></div> #noqa
|
||||||
<div class="mc_vtvc_ban_lo">
|
|
||||||
<div class="vtbc">
|
|
||||||
<div class="mc_bc_w b_smText">
|
|
||||||
<div class="mc_bc pivot bpi_2">
|
|
||||||
<span title="">
|
|
||||||
<span class="mv_vtvc_play cipg "></span>
|
|
||||||
</span>
|
|
||||||
</div>
|
|
||||||
<div class="mc_bc items">10:06</div>
|
|
||||||
</div>
|
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
<div class="vrhdata" vrhm='{"du":"01:11","murl":"https://www.example.com/watch?v=DEADBEEF","thid":"OVP.BINGTHUMB1","vt":"Title 1"}'></div> # noqa
|
||||||
<div class="mc_vtvc_meta">
|
|
||||||
<div class="mc_vtvc_title" title="Title 1"></div>
|
|
||||||
<div class="mc_vtvc_meta_block_area">
|
|
||||||
<div class="mc_vtvc_meta_block">
|
|
||||||
<div class="mc_vtvc_meta_row">
|
|
||||||
<span>65,696,000+ views</span>
|
|
||||||
<span>1 year ago</span>
|
|
||||||
</div>
|
|
||||||
<div class="mc_vtvc_meta_row mc_vtvc_meta_row_channel">Content 1</div>
|
|
||||||
<div class="mc_vtvc_meta_row"><span>
|
|
||||||
<div class="cico mc_vtvc_src_ico">
|
|
||||||
<div></div>
|
|
||||||
</div>
|
|
||||||
<span>YouTube</span>
|
|
||||||
</span></div>
|
|
||||||
</div>
|
|
||||||
</div>
|
|
||||||
</div>
|
</div>
|
||||||
<div class="vrhdata"></div>
|
</a>
|
||||||
</a>
|
|
||||||
</div>
|
|
||||||
</div>
|
</div>
|
||||||
|
</div>
|
||||||
"""
|
"""
|
||||||
response = mock.Mock(text=html)
|
response = mock.Mock(text=html)
|
||||||
results = bing_videos.response(response)
|
results = bing_videos.response(response)
|
||||||
self.assertEqual(type(results), list)
|
self.assertEqual(type(results), list)
|
||||||
self.assertEqual(len(results), 1)
|
self.assertEqual(len(results), 1)
|
||||||
self.assertEqual(results[0]['title'], 'Title 1')
|
self.assertEqual(results[0]['title'], 'Title 1')
|
||||||
self.assertEqual(results[0]['url'], 'https://bing.com/video')
|
self.assertEqual(results[0]['url'], 'https://www.example.com/watch?v=DEADBEEF')
|
||||||
self.assertEqual(results[0]['content'], 'Content 1')
|
self.assertEqual(results[0]['content'], '01:11 - 100 views - 1 year ago - ExampleTube - Channel 1')
|
||||||
self.assertEqual(results[0]['thumbnail'], 'thumb_1.jpg')
|
self.assertEqual(results[0]['thumbnail'], 'https://www.bing.com/th?id=OVP.BINGTHUMB1')
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue