logoChat01.ai

import asyncio import aiohttp from bs4 import Beau...

Tạo vào: 13 tháng 9, 2025

Trả lời bằng GPT-5 Thinking bởi Chat01

Câu hỏi

import asyncio
import aiohttp
from bs4 import BeautifulSoup
import aiofiles
import logging
import json
import random
from googletrans import Translator # Import Google Translate library

Set up logging

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

=== Telegram Bot Settings ===

TELEGRAM_BOT_TOKEN = '7772853489:AAHQ2mNe23HnqpBPfmQy5v7oCqAPpxrYWC4' # Insert your bot token
CHAT_ID = '5920264584' # Insert your chat_id

List of URLs to monitor

urls = [
'https://as.com/noticias/albacete-balompie/',
'https://as.com/noticias/ud-almeria/',
'https://as.com/noticias/burgos-cf/',
'https://as.com/noticias/cadiz-cf/',
'https://as.com/noticias/cartagena-fc/',
'https://as.com/noticias/cd-castellon/',
'https://as.com/noticias/cordoba-cf/',
'https://as.com/noticias/deportivo/',
'https://as.com/noticias/sd-eibar/',
'https://as.com/noticias/elche-cf/',
'https://as.com/noticias/club-deportivo-eldense/',
'https://as.com/noticias/granada-cf/',
'https://as.com/noticias/sd-huesca/',
'https://as.com/noticias/levante-ud/',
'https://as.com/noticias/malaga-cf/',
'https://as.com/noticias/cd-mirandes/',
'https://as.com/noticias/racing-ferrol/',
'https://as.com/noticias/racing-de-santander/',
'https://as.com/noticias/real-oviedo/',
'https://as.com/noticias/real-zaragoza/',
'https://as.com/noticias/sporting/',
'https://as.com/noticias/cd-tenerife/',
]

found_links_file = 'found_links2.json'

List of User-Agents

user_agents = [
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)'
' Chrome/70.0.3538.77 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)'
' Chrome/79.0.3945.117 Safari/537.36',
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko)'
' Chrome/44.0.2403.157 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_5)'
' AppleWebKit/605.1.15 (KHTML, like Gecko) Version/12.1.1 Safari/605.1.15',
# Add more User-Agents if necessary
]

Initialize Translator object

translator = Translator()

async def load_found_links(file_name):
try:
async with aiofiles.open(file_name, 'r') as f:
data = await f.read()
return json.loads(data)
except FileNotFoundError:
logging.warning(f"File not found: {file_name}")
return []

async def save_found_links(file_name, found_links):
async with aiofiles.open(file_name, 'w') as f:
await f.write(json.dumps(found_links))
logging.info(f"Links saved to file: {file_name}")

async def send_message(text, url):
# Translate the message to Russian
translated_text = translator.translate(text, src='es', dest='ru').text # Translate from Spanish to Russian
message_text = f"<a href='{url}'>{translated_text}</a>"
send_url = f'https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}/sendMessage'
payload = {
'chat_id': CHAT_ID,
'text': message_text,
'parse_mode': 'HTML'
}
async with aiohttp.ClientSession() as session:
async with session.post(send_url, data=payload) as response:
if response.status == 200:
logging.info(f"Message sent: {translated_text}")
else:
resp_text = await response.text()
logging.error(f"Failed to send message: {resp_text}")

async def process_url(session, url, found_links):
headers = {'User-Agent': random.choice(user_agents)}
new_links = []
try:
await asyncio.sleep(random.uniform(0.5, 1.5)) # Random delay before request
async with session.get(url, headers=headers) as response:
if response.status == 200:
logging.info(f"Successfully fetched page: {url}")
html = await response.text()
soup = BeautifulSoup(html, 'html.parser')
h2_elements = soup.find_all('h2', class_='s__tl')
for h2 in h2_elements:
link = h2.find('a', href=True)
if link:
href = link['href']
if not href.startswith('http'):
href = f'https://as.com{href}'
title = link.get_text().strip()
if href not in found_links:
await send_message(title, href)
new_links.append(href)
else:
logging.warning(f"Failed to fetch URL: {url} with status code: {response.status}")
except Exception as e:
logging.error(f"Error processing URL: {url}. Error: {str(e)}")
return new_links

async def main():
found_links = set(await load_found_links(found_links_file))
while True:
async with aiohttp.ClientSession() as session:
tasks = [process_url(session, url, found_links) for url in urls]
results = await asyncio.gather(*tasks)
new_found_links = set()
for new_links in results:
new_found_links.update(new_links)
if new_found_links:
found_links.update(new_found_links)
await save_found_links(found_links_file, list(found_links))
logging.info("Waiting for the next cycle...")
await asyncio.sleep(10) # Wait 10 seconds before the next cycle

if name == 'main':
asyncio.run(main()) errors File "c:\Python\Парсеры\AScomSegunda.py", line 8, in <module>
from googletrans import Translator # Import Google Translate library
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\User\AppData\Local\Programs\Python\Python313\Lib\site-packages\googletrans_init_.py", line 6, in <module>
from googletrans.client import Translator
File "C:\Users\User\AppData\Local\Programs\Python\Python313\Lib\site-packages\googletrans\client.py", line 13, in <module>
import httpx
File "C:\Users\User\AppData\Local\Programs\Python\Python313\Lib\site-packages\httpx_init_.py", line 2, in <module>
from ._api import delete, get, head, options, patch, post, put, request, stream
File "C:\Users\User\AppData\Local\Programs\Python\Python313\Lib\site-packages\httpx_api.py", line 3, in <module>
from ._client import Client, StreamContextManager
File "C:\Users\User\AppData\Local\Programs\Python\Python313\Lib\site-packages\httpx_client.py", line 8, in <module>
from ._auth import Auth, BasicAuth, FunctionAuth
File "C:\Users\User\AppData\Local\Programs\Python\Python313\Lib\site-packages\httpx_auth.py", line 10, in <module>
from ._models import Request, Response
File "C:\Users\User\AppData\Local\Programs\Python\Python313\Lib\site-packages\httpx_models.py", line 1, in <module>
import cgi
ModuleNotFoundError: No module named 'cgi' fix it

Suy nghĩ

Proposing fixes with minimal changes

The issue seems related to Python 3.13 removing 'cgi', and googletrans pulls in httpx, which still tries to import it. I’ll suggest a fix: upgrade httpx, install legacy-cgi, and use googletrans==4.0.0rc1. Alternatively, switch to a free translation API like Yandex or MyMemory, but it’d require API keys.

Recommended fixes and improvements

The safest fix here is installing legacy-cgi. Although we can't confirm the removal of cgi in httpx, this approach addresses the issue. Alternatively, running the code with Python 3.12 could help. Also, recommend rotating the bot token for security and using environment variables for token management via os.getenv. No code changes needed if we install the legacy fix.

Providing an improved fix

Since you're running Python 3.13, the removal of 'cgi' causes the error. This happens due to httpx, pulled in by googletrans, still importing cgi. Option 1: Install legacy-cgi with pip install legacy-cgi to resolve this. I’ll also suggest reading the token from environment variables (using os.getenv) and using asyncio.to_thread for translation. Code block and executed commands will follow, keeping security in mind.

Providing concise update & instructions

To resolve the error, use:
pip install --upgrade pip && pip install --upgrade googletrans==4.0.0rc1 legacy-cgi

For security, be sure to revoke the bot token using BotFather’s /revoke command.

In case of timeouts, I’d suggest adding timeouts for aiohttp and Telegram requests. But since you just want the error fixed, I’ll provide minimal code patches and the necessary installation steps for the environment.

Thought for 58s

Trả lời

You’re hitting this because you’re running Python 3.13, which removed the built-in cgi module. googletrans pulls in httpx, and some versions of httpx still import cgi, so on 3.13 that import explodes with ModuleNotFoundError: No module named 'cgi'. (Python documentation)

Quick fix (no code changes)

Install a drop-in replacement for the removed stdlib module:

bash
# (Windows)
py -m pip install --upgrade pip
py -m pip install legacy-cgi googletrans==4.0.0rc1

legacy-cgi restores the cgi module so httpx (and thus googletrans) can import it on Python 3.13. (PyPI)

Alternate route: run this project under Python 3.12 (where cgi still exists) if you prefer not to add the backport. (pradyunsg-cpython-lutra-testing.readthedocs.io)

🔐 Important: your Telegram bot token is exposed

The token you pasted can be used by anyone to control your bot. Revoke and regenerate it now in @BotFather:

  1. /mybots → select your bot → API Token → Revoke current token
  2. Or use /revoke / /token directly.
  3. Update your script with the new token (ideally via an environment variable). (BotoStore)

Example (optional) change to keep secrets out of code:

python
import os
TELEGRAM_BOT_TOKEN = os.getenv("TELEGRAM_BOT_TOKEN")
CHAT_ID = os.getenv("CHAT_ID")
# then set them in your environment before running:
# set TELEGRAM_BOT_TOKEN=123:ABC...
# set CHAT_ID=5920264584

Why this works

  • Python 3.13 removed cgi per PEP 594 → anything importing it breaks. (Python documentation)
  • legacy-cgi is a maintained fork that provides the same API name (cgi) on PyPI, so existing imports keep working without code changes. (PyPI)
  • The googletrans project itself acknowledges the 3.13/cgi issue. (GitHub)

If you want, I can also show a minimal patch to add timeouts and avoid blocking the event loop during translation—but the error you posted will be resolved by installing legacy-cgi (or by using Python 3.12).

Chia sẻ Q&A này