git-sync/crawlab
1
0
Fork 0
mirror of https://github.com/crawlab-team/crawlab.git synced 2026-01-25 17:42:25 +01:00
Code Issues Packages Projects Releases Wiki Activity

added automatic extraction of fields functionality

Browse Source
This commit is contained in:
Marvin Zhang
2019-05-29 18:02:54 +08:00
parent 925f643cd8
commit 543fe61445
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
crawlab/routes/spiders.py
View File

@@ -523,7 +523,7 @@ class SpiderApi(BaseApi):
tags = []
for tag in sel.iter():
if tag.tag == 'a':
if not tag.get('href').startswith('#') and not tag.get('href').startswith('javascript'):
if tag.get('href') is not None and not tag.get('href').startswith('#') and not tag.get('href').startswith('javascript'):
tags.append(tag)
return tags