|
@@ -10,9 +10,10 @@
|
|
@parse url, title, content
|
|
@parse url, title, content
|
|
"""
|
|
"""
|
|
|
|
|
|
-from urllib.parse import urlencode, urljoin
|
|
|
|
|
|
+from urllib.parse import urlencode, urljoin, urlparse
|
|
from lxml import html
|
|
from lxml import html
|
|
from searx.utils import extract_text
|
|
from searx.utils import extract_text
|
|
|
|
+from searx.exceptions import SearxEngineCaptchaException
|
|
|
|
|
|
# engine dependent config
|
|
# engine dependent config
|
|
categories = ['it']
|
|
categories = ['it']
|
|
@@ -37,6 +38,10 @@ def request(query, params):
|
|
|
|
|
|
# get response from search-request
|
|
# get response from search-request
|
|
def response(resp):
|
|
def response(resp):
|
|
|
|
+ resp_url = urlparse(resp.url)
|
|
|
|
+ if resp_url.path.startswith('/nocaptcha'):
|
|
|
|
+ raise SearxEngineCaptchaException()
|
|
|
|
+
|
|
results = []
|
|
results = []
|
|
|
|
|
|
dom = html.fromstring(resp.text)
|
|
dom = html.fromstring(resp.text)
|