forked from Ponysearch/Ponysearch
[FIX] google videos thumbnails
This commit is contained in:
parent
cee15f0375
commit
cf26aba93b
1 changed files with 17 additions and 3 deletions
|
@ -7,15 +7,16 @@
|
|||
@using-api no
|
||||
@results HTML
|
||||
@stable no
|
||||
@parse url, title, content
|
||||
@parse url, title, content, thumbnail
|
||||
"""
|
||||
|
||||
from datetime import date, timedelta
|
||||
from json import loads
|
||||
from lxml import html
|
||||
from searx.engines import logger
|
||||
from searx.engines.xpath import extract_text
|
||||
from searx.url_utils import urlencode
|
||||
|
||||
import re
|
||||
|
||||
# engine dependent config
|
||||
categories = ['videos']
|
||||
|
@ -73,11 +74,24 @@ def response(resp):
|
|||
url = result.xpath('.//div[@class="r"]/a/@href')[0]
|
||||
content = extract_text(result.xpath('.//span[@class="st"]'))
|
||||
|
||||
# get thumbnails
|
||||
script = str(dom.xpath('//script[contains(., "_setImagesSrc")]')[0].text)
|
||||
id = result.xpath('.//div[@class="s"]//img/@id')[0]
|
||||
thumbnails_data = re.findall('s=\'(.*?)(?:\\\\[a-z,1-9,\\\\]+\'|\')\;var ii=\[(?:|[\'vidthumb\d+\',]+)\'' + id,
|
||||
script)
|
||||
logger.debug('google video engine: ' + id + ' matched ' + str(len(thumbnails_data)) + ' times (thumbnail)')
|
||||
tmp = []
|
||||
if len(thumbnails_data) != 0:
|
||||
tmp = re.findall('(data:image/jpeg;base64,[a-z,A-Z,0-9,/,\+]+)', thumbnails_data[0])
|
||||
thumbnail = ''
|
||||
if len(tmp) != 0:
|
||||
thumbnail = tmp[-1]
|
||||
|
||||
# append result
|
||||
results.append({'url': url,
|
||||
'title': title,
|
||||
'content': content,
|
||||
'thumbnail': '',
|
||||
'thumbnail': thumbnail,
|
||||
'template': 'videos.html'})
|
||||
|
||||
return results
|
||||
|
|
Loading…
Reference in a new issue