mirror of
https://github.com/EvolutionAPI/adk-python.git
synced 2025-12-21 21:02:19 -06:00
Agent Development Kit(ADK)
An easy-to-use and powerful framework to build AI agents.
This commit is contained in:
41
src/google/adk/tools/load_web_page.py
Normal file
41
src/google/adk/tools/load_web_page.py
Normal file
@@ -0,0 +1,41 @@
|
||||
# Copyright 2025 Google LLC
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
"""Tool for web browse."""
|
||||
|
||||
import requests
|
||||
|
||||
|
||||
def load_web_page(url: str) -> str:
|
||||
"""Fetches the content in the url and returns the text in it.
|
||||
|
||||
Args:
|
||||
url (str): The url to browse.
|
||||
|
||||
Returns:
|
||||
str: The text content of the url.
|
||||
"""
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
response = requests.get(url)
|
||||
|
||||
if response.status_code == 200:
|
||||
soup = BeautifulSoup(response.content, 'lxml')
|
||||
text = soup.get_text(separator='\n', strip=True)
|
||||
else:
|
||||
text = f'Failed to fetch url: {url}'
|
||||
|
||||
# Split the text into lines, filtering out very short lines
|
||||
# (e.g., single words or short subtitles)
|
||||
return '\n'.join(line for line in text.splitlines() if len(line.split()) > 3)
|
||||
Reference in New Issue
Block a user