from bs4 import BeautifulSoup as bs
import requests
import HBD

link = 'https://x8.h-chan.me/manga/newest?offset=' #https://x8.h-chan.me/manga/
result = HBD.find_doc_with_max_id(HBD.connect_to_mongo())

max_id = '51196'
max_num = 29915


def form_date(date_str):
    months = {
        "января": "01",
        "февраля": "02",
        "марта": "03",
        "апреля": "04",
        "мая": "05",
        "июня": "06",
        "июля": "07",
        "августа": "08",
        "сентября": "09",
        "октября": "10",
        "ноября": "11",
        "декабря": "12",
    }

    day, month_str, year = date_str.split()

    # Получаем числовое значение месяца
    month = months[month_str]

    # Формируем дату в нужном формате
    formatted_date = f"{day}.{month}.{year}"

    return formatted_date

def try_request(link, max_retries=50):
    retries = 0
    while retries < max_retries:
        try:
            response = requests.get(link)

            if response.status_code == 200:
                return response
            else:
                retries += 1
        except:
            retries += 1

def pars(link, flag, count):
    data_hantai = {}

    response = try_request(link)

    soup = bs(response.text, 'html.parser')
    main_container = soup.find_all(class_='content_row')

    for item in main_container:
        img = item.find(class_='manga_images')
        img = img.find('img')
        img = img['src'] if img else None

        id = img.split('/')[-2][:10]

        row_container = item.find(class_='title_link')
        link_manga = 'https://hentaichan.live' + row_container.get('href')

        title = row_container.text

        tags = item.find(class_='genre')
        tags = [tag.strip() for tag in tags.text.split(',')]



        date = item.find(class_='row4_right').find('b').text
        date = form_date(date)

        manga_link = link_manga + '?cacheId=' + id
        manga_link = manga_link.replace('/manga/', '/online/')

        ID = link_manga.split('/')[-1].split('-')[0]

        if int(ID) == int(max_id):
            flag = True
            return data_hantai, flag

        data_hantai[title] = {
            'img': img,
            'link': link_manga,
            'tags': tags,
            'date': date,
            'manga_link': manga_link,
            'original_id' : ID,
        }

    print(f'стр - {count}', data_hantai)

    for i, j in data_hantai.items():
        print('-'*10, i, j['manga_link'])

    return data_hantai, flag

def get_data():
    data = {}
    count = 1

    for i in range(0, 5000, 20):

        flag = False
        data_hantai, flag = pars(link + str(i), flag, count)
        count +=1

        data.update(data_hantai)

        if flag is True:
            return data