mirror of
https://github.com/crawlab-team/crawlab.git
synced 2026-01-22 17:31:03 +01:00
updated spiders
This commit is contained in:
@@ -509,7 +509,7 @@ class SpiderApi(BaseApi):
|
||||
}, r.status_code
|
||||
|
||||
# get html parse tree
|
||||
sel = etree.HTML(r.content)
|
||||
sel = etree.HTML(r.content.decode('utf-8'))
|
||||
|
||||
# remove unnecessary tags
|
||||
unnecessary_tags = [
|
||||
|
||||
Reference in New Issue
Block a user