WarOnline_Chat.py

# This is an quote and post library for a specific thread in the WarOnline forum.

import requests
import re
from bs4 import BeautifulSoup
import urllib.request as urllib
import warnings
warnings.filterwarnings("ignore")

# Define the login URL and the thread URL
login_url = 'https://waronline.org/fora/index.php?login/login'
thread_url = 'https://waronline.org/fora/index.php?threads/warbot-playground.17636/'
post_url = "https://waronline.org/fora/index.php?threads/warbot-playground.17636/add-reply"

# Sending the message (change that!)
message = "Test"

# Define the login credentials
username = 'WarBot'
password = 'naP2tion'

# Start a session to persist the login cookie across requests
session = requests.Session()


def compare_pages(url1, url2):
    #Compares 2 pages and returns True if they are the same
    return urllib.urlopen(url1).geturl() == urllib.urlopen(url2).geturl()

def get_last_page_of_thread(thread_url=thread_url, startingPage=1):
    #Returns a link to the last page of the thread
    page = startingPage #Counter
    lastPage = False
    while not lastPage:
        response = requests.get(thread_url + 'page-' + str(page))
        if response.status_code == 200:
            pass  # do something (optional)
            if not compare_pages(thread_url + 'page-' + str(page), thread_url + 'page-' + str(page + 1)):
                page += 1
            else:
                lastPage = True
        else:
            lastPage = True

    return (thread_url + 'page-' + str(page))

def login(username=username, password=password, thread_url=thread_url):
    # Log-In to the forum and redirect to thread

    # Retrieve the login page HTML to get the CSRF token
    login_page_response = session.get(login_url)
    soup = BeautifulSoup(login_page_response.text, 'html.parser')
    csrf_token = soup.find('input', {'name': '_xfToken'})['value']

    # Login to the website
    login_data = {
        'login': username,
        'password': password,
        'remember': '1',
        '_xfRedirect': thread_url,
        '_xfToken': csrf_token
    }
    response = session.post(login_url, data=login_data)

    # Check if the login was successful
    if 'Invalid login' in response.text:
        print('Login failed!')
        exit()

def post(message=message, thread_url=thread_url, post_url=post_url, quoted_by="",quote_text="",quote_source=""):
    #Post a message to the forum (with or without the quote
    #quote_source is in format 'post-3920992'
    quote_source = quote_source.split('-')[-1] # Take the numbers only

    if quoted_by:
        message = f'[QUOTE="{quoted_by}, post: {quote_source}"]{quote_text}[/QUOTE]{message}'
        # optionally add @{quoted_by} to indent the quoter

    # Retrieve the thread page HTML
    response = session.get(thread_url)

    # Parse the HTML with BeautifulSoup
    soup = BeautifulSoup(response.text, 'html.parser')

    # Extract the _xfToken value from the hidden form field
    xf_token = soup.find('input', {'name': '_xfToken'}).get('value')

    # Construct the message data for the POST request
    message_data = {
        '_xfToken': xf_token,
        'message': message,
        'attachment_hash': '',
        'last_date': '',
        '_xfRequestUri': post_url,
        '_xfWithData': '1',
        '_xfResponseType': 'json'
    }

    response = session.post(post_url, data=message_data)

    # Check if the post was successful
    if not response.ok:
        print('Post failed!')
        exit()

    print('Post submitted successfully.')

def readQuote(thread_url=thread_url, username=username):
    # Retrieve the content of the specific thread

    response = session.get(thread_url)
    html_content = response.content

    # Initial values for messangerName and the message ID
    messengerName = ""
    messageID = ""

    # Parse the HTML content using BeautifulSoup
    soup = BeautifulSoup(html_content, 'html.parser')

    # Find all the quotes in the thread
    quotes = soup.find_all('div', {'class': 'bbWrapper'})
    messageData = soup.find_all('div', {'class': 'message-userContent'})

    # Check each quote if it contains your name and keep track of the latest one
    latest_quote = None
    for quote in quotes:
        if username in quote.text:
            latest_quote = quote

    if latest_quote:
        for data in messageData:
            if latest_quote.text in data.text:
                # Patterns to search in the last quote.
                namePattern = re.compile('data-lb-caption-desc="(.*?) ·')
                messageIDPattern = re.compile('data-lb-id="(.*?)"')

                # Get the messager username
                matchName = namePattern.search(str(data))
                if matchName:
                    messengerName = matchName.group(1)

                # Get the message ID
                matchID =  messageIDPattern.search(str(data))
                if matchID:
                    messageID = matchID.group(1)

        reply = latest_quote.text.split("Click to expand...")[-1].replace('\n', ' ').strip()
        return {'reply':reply,'messengerName':messengerName,'messageID':messageID}


if __name__ == '__main__':
    login(username=username, password=password, thread_url=thread_url)
    #post(message=message, thread_url=thread_url, post_url=post_url,quoted_by='Василий Пупкин',quote_text='Testing the XenForo response mechanism')
    quote = readQuote(thread_url=get_last_page_of_thread(thread_url,1), username=username)
    messangerQuote = readQuote(thread_url=get_last_page_of_thread(thread_url,1),username=quote['messengerName'])
    print(quote)
    print(messangerQuote)
    # The task is to fine all the unanswered quotes