fixed a crawler bug
This commit is contained in:
@@ -217,6 +217,7 @@ def js_extractor(response):
|
|||||||
|
|
||||||
|
|
||||||
def handle_anchor(parent_url, url):
|
def handle_anchor(parent_url, url):
|
||||||
|
scheme = urlparse(parent_url).scheme
|
||||||
if url[:4] == 'http':
|
if url[:4] == 'http':
|
||||||
return url
|
return url
|
||||||
elif url[:2] == '//':
|
elif url[:2] == '//':
|
||||||
|
|||||||
Reference in New Issue
Block a user