БЛОГ НА HUSL


Как исправить вечную ошибку в боте, который использует парсинг?

Автор вопроса: Brawler 
import requests
from bs4 import BeautifulSoup
import time
import threading
from collections import defaultdict
import logging
import vk_api
from vk_api.bot_longpoll import VkBotEventType, VkBotLongPoll

# Настройка логирования
logging.basicConfig(level=logging.INFO)


def write_msg(peer_id, message):
    vk.method('messages.send', {'peer_id': peer_id, 'message': message, 'random_id': 0})


key = 'vk1.a.0vmA-PHEPh8IMRca6h7gI_CK28sNMcWlbNE3bVJp4lyc-LOQdpcVEvb6c5w2aU8AxXyGc9Vp7WQ_3ruiFaD9xurIK2hSGkiB32Tm44uaO5b8GxfHSxnoMnmvc2lVvwpCywaDb6iW0dfwL7Sf8aWNqtk4_ZqYyjFfAm9s1mn9kypf-MinNcgDpGErPIoYfX-qRmowz1X2t2LiC2Lyhqx9tg'
url = 'https://forum.mordor-rp.com/index.php?reports/'
url_1 = 'https://forum.mordor-rp.com/index.php?reports/closed'
url_2 = 'https://forum.mordor-rp.com/index.php?forums/Общая-курилка.560/'
url_3 = 'https://forum.mordor-rp.com/index.php?forums/Транспорт.178/'
url_4 = 'https://forum.mordor-rp.com/index.php?forums/Недвижимость.179/'
url_5 = 'https://forum.mordor-rp.com/index.php?forums/Предприятия.180/'
url_6 = 'https://forum.mordor-rp.com/index.php?forums/Аксессуары-Одежда-Материалы.320/'
url_7 = 'https://forum.mordor-rp.com/index.php?whats-new/latest-activity'
last = ['лох', 'шлюха', 'мать', 'пидорас']
user_agents = ("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 "
               "Safari/537.36 OPR/105.0.0.0")

vk = vk_api.VkApi(token=key)

longpoll = VkBotLongPoll(vk, 226970140)


def load_cookies(file_path):
    cookies = {}
    with open(file_path, 'r') as file:
        for line in file:
            if '#' in line:
                line = line.split('#')[0].strip()
            if line:
                parts = line.split('\t')
                if len(parts) >= 7:
                    cookies[parts[5]] = parts[6].strip()  # Удаляем символы новой строки
    return cookies


cookie = load_cookies('cookies.txt')
# #curl.exe -c cookies.txt -b cookies.txt -L -d "username=&password=" https://forum.mordor-rp.com/index.php?login/


cookies = {
    'xf_csrf': '',
    'xf_session': ''
}
def get_message():
    response = requests.get(url=url_7, cookies=cookies)
    soup = BeautifulSoup(response.text, 'html.parser')
    link = soup.find('div', class_='contentRow-title')
    full_link = link.find_all('a')[0].find_next('a').get('href')
    data = soup.find('div', class_='contentRow-snippet').text
    for item in last:
        if item in data:
            return item, full_link
    return None, None


def get_aks():
    response = requests.get(url=url_6, cookies=cookies)
    soup = BeautifulSoup(response.text, 'html.parser')
    data = soup.find('div', class_='structItemContainer-group js-threadList')
    if data is None:
        data = ""
        print(data)
        return 1, 1
    else:
        first = data.find('div', class_='structItem-title')
        l = first.find_all('a')[0].find_next('a').get('href')
        answers = data.find('dd').text
        return l, answers


def get_pred():
    response = requests.get(url=url_5, cookies=cookies)
    soup = BeautifulSoup(response.text, 'html.parser')
    data = soup.find('div', class_='structItemContainer-group js-threadList')
    if data is None:
        data = ""
        print(data)
        return 1, 1
    else:
        first = data.find('div', class_='structItem-title')
        l = first.find_all('a')[0].find_next('a').get('href')
        answers = data.find('dd').text
        return l, answers


def get_ned():
    response = requests.get(url=url_4, cookies=cookies)
    soup = BeautifulSoup(response.text, 'html.parser')
    data = soup.find('div', class_='structItemContainer-group js-threadList')
    if data is None:
        data = ""
        print(data)
        return 1, 1
    else:
        first = data.find('div', class_='structItem-title')
        l = first.find_all('a')[0].find_next('a').get('href')
        answers = data.find('dd').text
        return l, answers


def get_transport():
    response = requests.get(url=url_3, cookies=cookies)
    soup = BeautifulSoup(response.text, 'html.parser')
    data = soup.find('div', class_='structItemContainer-group js-threadList')
    if data is None:
        data = ""
        print(data)
        return 1, 1
    else:
        first = data.find('div', class_='structItem-title')
        l = first.find_all('a')[0].find_next('a').get('href')
        answers = data.find('dd').text
        return l, answers


def get_smoking():
    response = requests.get(url=url_2, cookies=cookies)
    soup = BeautifulSoup(response.text, 'html.parser')
    data = soup.find('div', class_='structItemContainer-group js-threadList')
    nick1 = data.find('ul', class_='structItem-parts')
    nick = nick1.find('a', class_='username').text
    title = data.find('div', class_='structItem-title').text
    link = data.find('div', class_='structItem-title')
    link = link.find('a').get('href')
    answers = data.find('dd').text
    return nick, title, link, answers


def get_week():
    response = requests.get(url_1, cookies=cookies)
    soup = BeautifulSoup(response.text, 'html.parser')

    name_counts = defaultdict(int)

    data = soup.find_all('div', class_='structItem structItem--report')
    for item in data:
        step = item.find('div', class_='structItem-cell structItem-cell--latest')
        step1 = step.find('div', class_='structItem-minor').text.strip()

        name_counts[step1] += 1

    sorted_names = sorted(name_counts.items(), key=lambda x: x[1], reverse=True)
    return sorted_names


def get_status():
    response = requests.get(url, cookies=cookies)
    soup = BeautifulSoup(response.text, 'html.parser')
    data = soup.find('div', class_='p-pageWrapper')

    ll = data.find('div', class_='xb-page-wrapper')
    two = ll.find('div', class_='structItem-cell structItem-cell--main')
    status = two.find('li').text
    return status.strip()


def get_report_data():
    response = requests.get(url, cookies=cookies)
    soup = BeautifulSoup(response.text, 'html.parser')
    data = soup.find('div', class_='p-pageWrapper')
    line = soup.find_all('div', class_='structItem-cell structItem-cell--latest')

    # Getting the number of reports
    one = data.find('a').get('data-badge')
    if one is None:
        one = 0  # Handle the case where there are no reports
    ll = data.find('div', class_='xb-page-wrapper')
    two = ll.find('div', class_='structItem-cell structItem-cell--main')
    link = two.find('a').get('href')
    full_link = 'https://forum.mordor-rp.com' + link

    # Extracting href from each element in line
    hrefs = []
    for item in line:
        a_tag = item.find('a')
        if a_tag:
            href = a_tag.get('href')
            if href:
                full_href = 'https://forum.mordor-rp.com' + href
                hrefs.append(full_href)

    return one, full_link, hrefs


def check_for_new_words(last_link):
    message, link = get_message()
    if link != last_link:
        write_msg(2000000004, f'?Возможно найдено нарушение!\n'
                              f'Возможное нарушение: "{message}"\n'
                              f'Ссылка на нарушение: https://forum.mordor-rp.com{link}')
        return link
    return last_link


def check_for_new_reports(last_link):
    one, link, hrefs = get_report_data()
    status = get_status()
    if link != last_link and status == 'Открыто':
        if int(one) >= 5:
            for i, href in enumerate(hrefs, start=1):
                if i <= int(one):
                    write_msg(2000000006, f' @all Уже {one} жалоб!\n'
                                          f'{i}.{href}')
                continue
        elif int(one) < 5:
            write_msg(2000000006, f'@online Пришла новая жалоба: {link}')
        return link
    return last_link


def check_aks(last_link):
    link, answers = get_aks()
    if link != last_link and int(answers) == 0:
        write_msg(2000000005, f'@online Создана новая тема в Аксессуарах/Одежде/Материалах:\n'
                              f'Ссылка на тему: https://forum.mordor-rp.com{link[0:-5]}')
        return link
    return last_link


def check_ned(last_link):
    link, answers = get_ned()
    if link != last_link and int(answers) == 0:
        write_msg(2000000005, f'@online Создана новая тема в Недвижимости:\n'
                              f'Ссылка на тему: https://forum.mordor-rp.com{link[0:-5]}')
        return link
    return last_link


def check_ts(last_link):
    link, answers = get_transport()
    if link != last_link and int(answers) == 0:
        write_msg(2000000005, f'@online Создана новая тема в Транспорте:\n'
                              f'Ссылка на тему: https://forum.mordor-rp.com{link[0:-5]}')
        return link
    return last_link


def check_pred(last_link):
    link, answers = get_pred()
    if link != last_link and int(answers) == 0:
        write_msg(2000000005, f'@online Создана новая тема в Предприятиях:\n'
                              f'Ссылка на тему: https://forum.mordor-rp.com{link[0:-5]}')
        return link
    return last_link


def check_for_new_titles(last_link):
    nick, title, link, answers = get_smoking()
    if link != last_link and int(answers) == 0:
        write_msg(2000000005, '@online Создана новая тема в Курилке!\n'
                              f'Название темы: {title}\n'
                              f'Ник-нейм создателя темы:{nick}\n'
                              f'Ссылка на тему: https://forum.mordor-rp.com{link}\n')
        return link
    return last_link


def listen_for_messages():
    for event in longpoll.listen():
        if event.type == VkBotEventType.MESSAGE_NEW:
            request = event.object.message['text']
            peer_id = event.object.message['peer_id']

            logging.info(f"Received message: {request} from peer_id: {peer_id}")

            if request.lower() == 'жалобы':
                one, link, _ = get_report_data()
                status = get_status()
                write_msg(peer_id, f'На данный момент количество жалоб: {one}\nСсылка на последнюю жб: {link}\n'
                                   f'Статус жалобы: {status}')
            elif request.lower() == 'send':
                write_msg(2000000005, 'А вы пожелали сладких снов всем своим близким?\n'
                                      'Напишите ответ: Да/Нет')
            elif request.lower() == 'отчеты':
                week = get_week()
                text = ('Отчеты недели\n'
                        'Владимир Шевцов - топчик\n')
                for name, count in week:
                    text += f'{name}: {count}\n'
                write_msg(peer_id, text)
            elif request.lower() == 'курилка':
                nick, title, link, answers = get_smoking()
                write_msg(peer_id, f'Название темы: {title}\n'
                                   f'Ник-нейм создателя темы:{nick}\n'
                                   f'Ссылка на тему: https://forum.mordor-rp.com{link}\n'
                                   f'Количество ответов в теме: {answers}')
            elif request.lower() == 'пп':
                l, _ = get_transport()
                k, _ = get_ned()
                m, _ = get_pred()
                n, _ = get_aks()
                write_msg(peer_id, f'Первая разделе транспорт:\n https://forum.mordor-rp.com{l}\n'
                                   f'Первая разделе недвижимость: https://forum.mordor-rp.com{k}\n'
                                   f'Первая разделе предприятия: https://forum.mordor-rp.com{m}\n'
                                   f'Первая разделе аксессуары/одежда/материалы: https://forum.mordor-rp.com{n}')
            elif request.lower() == 'чек':
                mes, w = get_message()
                if mes is not None:
                    write_msg(peer_id, f'?Возможно найдено нарушение!\n'
                                       f'Возможное нарушение: "{mes}"\n'
                                       f'Ссылка на нарушение: https://forum.mordor-rp.com{w}')
                else:
                    write_msg(peer_id, 'Ничего не найдено')
        elif event.type == VkBotEventType.GROUP_JOIN:
            peer_id = event.object.message['peer_id']
            write_msg(peer_id, 'Хай')


message_thread = threading.Thread(target=listen_for_messages)
message_thread.start()

last_link_aks = ""
last_link_ned = ""
last_link_ts = ""
last_link_pred = ""
last_link_reports = ""
last_link_titles = ""
last_link_mess = ""

while True:
    last_link_aks = check_aks(last_link_aks)
    last_link_ned = check_ned(last_link_ned)
    last_link_ts = check_ts(last_link_ts)
    last_link_pred = check_pred(last_link_pred)
    last_link_reports = check_for_new_reports(last_link_reports)
    last_link_titles = check_for_new_titles(last_link_titles)
    last_link_mess = check_for_new_words(last_link_mess)
    time.sleep(1)

Сразу говорю, да использовал GPT, но я пока не нашел выхода

line 179, in get_report_data
    two = ll.find('div', class_='structItem-cell structItem-cell--main')
          ^^^^^^^
AttributeError: 'NoneType' object has no attribute 'find'

Источник

Ответы (0 шт):

licensed under cc by-sa 3.0 with attribution.