Game research for system requirements selected for a computer with the word

par30games.py

import webbrowser
import time, random
import requests
from bs4 import BeautifulSoup


def get_all_links(url):
    """
    Fetches a webpage and extracts all URLs from anchor tags.
    """
    try:
        response = requests.get(url, cookies='',headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36 Edg/130.0.0.0'})
        response.raise_for_status()  # Raise an exception for bad status codes
        # Accessing all cookies
        for cookie in response.cookies:
            print(f"Name: {cookie.name}, Value: {cookie.value}")

        # Accessing a specific cookie by name
        if 'session_id' in response.cookies:
            session_cookie_value = response.cookies['session_id']
            print(f"Session ID: {session_cookie_value}")
    except requests.exceptions.RequestException as e:
        print(f"Error fetching the URL: {e}")
        return []

    soup = BeautifulSoup(response.text, 'html.parser')
    links = []
    for anchor_tag in soup.find_all('a'):
        href = anchor_tag.get('href')
        if href:  # Ensure the href attribute exists
            links.append(href)
    return links


def research(number_start_page_from):
    S = 'https://par30games.net/pc/page/'
    exist = True
    special_games = []
    print('number start page from', number_start_page_from, 'to you click Ctrl+C')
    # to end of number at pages
    while exist:
        try:
            number_start_page_from += 1
            list_games = get_all_links(S+str(number_start_page_from))
            special_games += list_games[170:186]
            print('page:', number_start_page_from)
        except KeyboardInterrupt as KeyError:
            exist = False

    with open('links.txt', 'w+') as f:
        #print('s'*20,special_games )
        for l in special_games:
            #print(l)
            f.write(l+'\n')
        f.close()


def remove_duplicate_lines(input_file, output_file):
    seen_lines = set()
    with open(input_file, 'r', encoding='utf-8') as infile, open(output_file, 'w', encoding='utf-8') as outfile:
        for line in infile:
            if line not in seen_lines:
                outfile.write(line)
                seen_lines.add(line)


def ready_for_collect(select, path_links, black_list):
    f = open(select, 'w+')
    # Send an HTTP GET request
    url = ""
    for url in open(path_links).readlines():
        name = url[-1:].rfind('/')
        print(url[name:])
        GAME = url[name:]
        response = requests.get(url, headers={'user-agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 Edg/128.0.0.0"})

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

        # Find the element by its ID
        element = soup.find(dir="ltr")
        #e = element.format_string

        # Print the element or its content
        if element:
           
            #e = e.replace('<br/>', ',')
            ##e = e.replace('</p>', ',')
            e = element.text
            #f.write(element.)
            #print(element)  # Full HTML of the element
              # Text inside the element
            if not any(item in e for item in black_list):
            #if  'GTX' not in e and '12 GB RAM' not in e and '4GB VRAM ' not in e and 'Gtx' not in e and '6GB VRAM' not in e:
                print(e)
                print(url)
                webbrowser.open(url, new=0,autoraise=True)
                f.write(url)
            # Generate a random integer between 10 and 20 (inclusive)
            random_number = random.randint(3, 7)
            print('wait: ', random_number)
            time.sleep(random_number)
            print()
        else:
            print("Element with the specified ID not found.")
    f.close()


if __name__ == "__main__":
    research(350)
    # Example usage
    db = 'database.txt'
    input_file = 'links.txt'  # Replace with your input file name
    output_file = 'games.txt'  # Replace with your desired output file name
    remove_duplicate_lines(input_file, output_file)
    ready_for_collect(db, output_file, ['GTX', 'RTX', '12 GB RAM', '4GB VRAM ',  'Gtx', '6GB VRAM'])
    '''with open(db, 'r') as f:
        for url in f.readlines():
            print(url)
            #url = "https://www.example.com"
            webbrowser.open(url, new=0,autoraise=True) # Opens in the default browser
            time.sleep(4)# need to read and collect
    '''