Spaces:
Runtime error
Runtime error
File size: 4,874 Bytes
9b674e9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 |
from bs4 import BeautifulSoup
import requests
import re
from urllib.parse import urljoin
import datetime
from .tooler import tool
from .top_bar_wrapper import wrapper
_standard_tools_ = {}
def register_tool(func):
if func.__name__ not in _standard_tools_:
_standard_tools_[func.__name__] = tool(func)
return func
@register_tool
@wrapper
def read_website(url: str, max_content_length: int = 5000) -> dict:
"""
Read the content of a website and return the title, meta data, content, and sub-links.
"""
try:
response = requests.get(url)
response.raise_for_status()
html = response.text
except requests.RequestException as e:
return {"error": f"Failed to retrieve the website content: {e}"}
soup = BeautifulSoup(html, "html.parser")
meta_properties = [
"og:description",
"og:site_name",
"og:title",
"og:type",
"og:url",
"description",
"keywords",
"author"
]
meta = {}
for property_name in meta_properties:
tag = soup.find("meta", property=property_name) or soup.find("meta", attrs={"name": property_name})
if tag:
meta[property_name] = tag.get("content", "")
for ignore_tag in soup(["script", "style"]):
ignore_tag.decompose()
title = soup.title.string.strip() if soup.title else ""
content = soup.body.get_text(separator="\n") if soup.body else ""
links = []
for a in soup.find_all("a", href=True):
link_url = urljoin(url, a["href"])
links.append({"title": a.text.strip(), "link": link_url})
content = re.sub(r"[\n\r\t]+", "\n", content)
content = re.sub(r" +", " ", content)
content = re.sub(r"[\n ]{3,}", "\n\n", content)
content = content.strip()
if len(content) > max_content_length:
content = content[:max_content_length].rsplit(' ', 1)[0] + '...'
return {"meta": meta, "title": title, "content": content, "sub_links": links}
@register_tool
@wrapper
def google(query: str, max_number: int = 20) -> list:
"""
Search the query on Google and return the results.
"""
try:
from googlesearch import search as gsearch
return list(gsearch(query, stop=max_number))
except:
return "An exception occurred"
@register_tool
@wrapper
def duckduckgo(query: str, max_number: int = 20) -> list:
"""
Search the query on DuckDuckGo and return the results.
"""
try:
from duckduckgo_search import DDGS
return [result["href"] for result in DDGS().text(query, max_results=max_number)]
except:
return "An exception occurred"
@register_tool
@wrapper
def copy(text: str):
"""
Copy the text to the clipboard.
"""
import pyperclip
pyperclip.copy(text)
pyperclip.copy(text)
@register_tool
@wrapper
def open_url(url) -> bool:
"""
Open the URL in the default web browser.
:param url: str:
"""
import webbrowser
try:
webbrowser.open(url)
return True
except:
return False
return False
@register_tool
@wrapper
def sleep(seconds: int):
"""
Sleep for the given number of seconds.
"""
import time
time.sleep(seconds)
@register_tool
@wrapper
def keyboard_write(text: str):
"""
Write the text using the keyboard.
"""
import pyautogui
pyautogui.write(text)
@register_tool
@wrapper
def keyboard_press(key: str):
"""
Press the key using the keyboard.
"""
import pyautogui
pyautogui.press(key)
pyautogui.press(key)
from langchain_experimental.utilities import PythonREPL
the_py_client = PythonREPL()
@register_tool
@wrapper
def python_repl(code: str) -> str:
"""
Run and return the given python code in python repl
"""
return the_py_client.run(code)
@register_tool
@wrapper
def app_open(app_name: str) -> bool:
"""
Opens the native apps.
"""
try:
from AppOpener import open
open(app_name, throw_error=True)
return True
except:
try:
from MacAppOpener import open
open(app_name)
except:
return False
@register_tool
@wrapper
def app_close(app_name: str) -> bool:
"""
Closes the native apps.
"""
try:
from AppOpener import close
close(app_name, throw_error=True)
return True
except:
try:
from MacAppOpener import open
close(app_name)
except:
return False
@register_tool
@wrapper
def get_current_time() -> str:
"""
Get the current time in ISO format.
"""
return datetime.datetime.now().isoformat()
def get_standard_tools():
print("Tool len", len(_standard_tools_))
last_list = [_standard_tools_[each] for each in _standard_tools_]
return last_list
|