Gecko [ myeducation.co.th ]

Name	Size	Permission
__pycache__	[ DIR ]	drwxr-xr-x
venv	[ DIR ]	drwxr-xr-x
BankSineBot.py	14.07 KB	-rw-r--r--
botreadweb.log	2.24 MB	-rw-r--r--
botreadweb.py	2.44 KB	-rw-r--r--
favicon.ico	0 B	-rw-r--r--
hello.py	54 B	-rw-r--r--
image.jpg	9.9 KB	-rw-r--r--
main.py	437 B	-rw-r--r--
test_connections.py	2.75 KB	-rw-r--r--
udo crontab -e	1.51 KB	-rw-r--r--
udo systemctl enable py123.ser...	2 KB	-rw-r--r--

Code Editor : botreadweb.py

#/var/www/py/py123.testproject.work/botreadweb.py
# python3 botreadweb.py
import requests
from bs4 import BeautifulSoup
import time
import re
from concurrent.futures import ThreadPoolExecutor

def read_website(url):
    try:
        headers = {
            'User-Agent': 'AFRABot'
        }
        
        # Send a GET request to the URL with headers
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            # Use BeautifulSoup to parse the HTML content
            soup = BeautifulSoup(response.text, 'html.parser')
            
            # Extract the text from the parsed HTML
            text = soup.get_text(separator=' ', strip=True)
            
            # Collect details about the reading operation
            current_time = time.strftime("%Y-%m-%d %H:%M:%S")
            total_characters = len(text)
            words = re.findall(r'\w+', text.lower())  # Convert to lower case and find all whole words
            total_words = len(words)
            
            # Log details to a file
            with open("botreadweb.log", "a") as log_file:
                log_file.write(f"Website content read at: {current_time}\n")
                log_file.write(f"Website URL: {url}\n")
                log_file.write(f"Total number of characters (including spaces and punctuation): {total_characters}\n")
                log_file.write(f"Total number of words: {total_words}\n\n")
            
            # Print details to console
            print(f"Website content read at: {current_time}")
            print(f"Website URL: {url}")
            print(f"Total number of characters (including spaces and punctuation): {total_characters}")
            print(f"Total number of words: {total_words}")
            
            # Print the text content
            #print("\nText extracted:", text)
            
            
        else:
            print("Issue reading the website:", response.status_code)
    except Exception as e:
        print("An error occurred:", e)

# List of URLs to read
urls = [
    "https://dev.rampagesoft.com/",
    "https://seo.rampagesoft.com/",
    "https://rampagesoft.com/webdesign/",
    "https://rampagesoft.com/",
    "https://siamwebsite.me/",
    "https://ttt-website.com/website.php",
    "https://ttt-website.com/",
    "https://blog.ttt-website.com/"
]

# Create a thread pool executor with maximum of 6 threads
with ThreadPoolExecutor(max_workers=6) as executor:
    executor.map(read_website, urls)

${this.title}

Code Editor : botreadweb.py