AutoGPT1 / autogpt /commands /web_requests.py
Vito99's picture
Duplicate from aliabid94/AutoGPT
40a5d34
"""Browse a webpage and summarize it using the LLM model"""
from __future__ import annotations
from urllib.parse import urljoin, urlparse
import requests
from bs4 import BeautifulSoup
from requests import Response
from requests.compat import urljoin
from autogpt.config import Config
from autogpt.memory import get_memory
from autogpt.processing.html import extract_hyperlinks, format_hyperlinks
CFG = Config()
memory = get_memory(CFG)
session = requests.Session()
session.headers.update({"User-Agent": CFG.user_agent})
def is_valid_url(url: str) -> bool:
"""Check if the URL is valid
Args:
url (str): The URL to check
Returns:
bool: True if the URL is valid, False otherwise
"""
try:
result = urlparse(url)
return all([result.scheme, result.netloc])
except ValueError:
return False
def sanitize_url(url: str) -> str:
"""Sanitize the URL
Args:
url (str): The URL to sanitize
Returns:
str: The sanitized URL
"""
return urljoin(url, urlparse(url).path)
def check_local_file_access(url: str) -> bool:
"""Check if the URL is a local file
Args:
url (str): The URL to check
Returns:
bool: True if the URL is a local file, False otherwise
"""
local_prefixes = [
"file:///",
"file://localhost/",
"file://localhost",
"http://localhost",
"http://localhost/",
"https://localhost",
"https://localhost/",
"http://2130706433",
"http://2130706433/",
"https://2130706433",
"https://2130706433/",
"http://127.0.0.1/",
"http://127.0.0.1",
"https://127.0.0.1/",
"https://127.0.0.1",
"https://0.0.0.0/",
"https://0.0.0.0",
"http://0.0.0.0/",
"http://0.0.0.0",
"http://0000",
"http://0000/",
"https://0000",
"https://0000/",
]
return any(url.startswith(prefix) for prefix in local_prefixes)
def get_response(
url: str, timeout: int = 10
) -> tuple[None, str] | tuple[Response, None]:
"""Get the response from a URL
Args:
url (str): The URL to get the response from
timeout (int): The timeout for the HTTP request
Returns:
tuple[None, str] | tuple[Response, None]: The response and error message
Raises:
ValueError: If the URL is invalid
requests.exceptions.RequestException: If the HTTP request fails
"""
try:
# Restrict access to local files
if check_local_file_access(url):
raise ValueError("Access to local files is restricted")
# Most basic check if the URL is valid:
if not url.startswith("http://") and not url.startswith("https://"):
raise ValueError("Invalid URL format")
sanitized_url = sanitize_url(url)
response = session.get(sanitized_url, timeout=timeout)
# Check if the response contains an HTTP error
if response.status_code >= 400:
return None, f"Error: HTTP {str(response.status_code)} error"
return response, None
except ValueError as ve:
# Handle invalid URL format
return None, f"Error: {str(ve)}"
except requests.exceptions.RequestException as re:
# Handle exceptions related to the HTTP request
# (e.g., connection errors, timeouts, etc.)
return None, f"Error: {str(re)}"
def scrape_text(url: str) -> str:
"""Scrape text from a webpage
Args:
url (str): The URL to scrape text from
Returns:
str: The scraped text
"""
response, error_message = get_response(url)
if error_message:
return error_message
if not response:
return "Error: Could not get response"
soup = BeautifulSoup(response.text, "html.parser")
for script in soup(["script", "style"]):
script.extract()
text = soup.get_text()
lines = (line.strip() for line in text.splitlines())
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
text = "\n".join(chunk for chunk in chunks if chunk)
return text
def scrape_links(url: str) -> str | list[str]:
"""Scrape links from a webpage
Args:
url (str): The URL to scrape links from
Returns:
str | list[str]: The scraped links
"""
response, error_message = get_response(url)
if error_message:
return error_message
if not response:
return "Error: Could not get response"
soup = BeautifulSoup(response.text, "html.parser")
for script in soup(["script", "style"]):
script.extract()
hyperlinks = extract_hyperlinks(soup, url)
return format_hyperlinks(hyperlinks)
def create_message(chunk, question):
"""Create a message for the user to summarize a chunk of text"""
return {
"role": "user",
"content": f'"""{chunk}""" Using the above text, answer the following'
f' question: "{question}" -- if the question cannot be answered using the'
" text, summarize the text.",
}