AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-13 20:15:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

For security. (#3642)

Browse Source 
### What problem does this PR solve?


### Type of change

- [x] Performance Improvement
This commit is contained in:
Kevin Hu 2024-11-26 09:34:34 +08:00 committed by GitHub
parent 32cf566a08
commit 3df1663e4f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
agent/component/crawler.py
View File

@ -17,6 +17,7 @@ from abc import ABC
import asyncio import asyncio
from crawl4ai import AsyncWebCrawler from crawl4ai import AsyncWebCrawler
from agent.component.base import ComponentBase, ComponentParamBase from agent.component.base import ComponentBase, ComponentParamBase
from api.utils.web_utils import is_valid_url
class CrawlerParam(ComponentParamBase): class CrawlerParam(ComponentParamBase):
@ -39,7 +40,7 @@ class Crawler(ComponentBase, ABC):
def _run(self, history, **kwargs): def _run(self, history, **kwargs):
ans = self.get_input() ans = self.get_input()
ans = " - ".join(ans["content"]) if "content" in ans else "" ans = " - ".join(ans["content"]) if "content" in ans else ""
if not ans: if not is_valid_url(ans):
return Crawler.be_output("") return Crawler.be_output("")
try: try:
result = asyncio.run(self.get_web(ans)) result = asyncio.run(self.get_web(ans))