Plurk paste

import requests
from bs4 import BeautifulSoup
import os
import time
import random
import re
from concurrent.futures import ThreadPoolExecutor, as_completed
from ebooklib import epub

# 全局配置
headers = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
    'Cache-Control': 'max-age=0',
    'Connection': 'keep-alive',
    'Content-Type': 'application/x-www-form-urlencoded',
    'Referer': 'https://www.po18.tw',
    'Upgrade-Insecure-Requests': '1',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.5005.63 Safari/537.36'
}

# 提示用戶輸入自己的 Cookie
cookies = {
    'session_cookie_name': 'YOUR_COOKIE_VALUE_HERE',
    'another_cookie_name': 'YOUR_ANOTHER_COOKIE_VALUE_HERE',
    # 在這裡添加更多的 Cookie，如果有需要的話
    # 示例: 'authtoken1': 'YOUR_AUTHTOKEN_VALUE_HERE'
}

# 清理文件名中的非法字符
def sanitize_filename(filename):
    return re.sub(r'[\\/*?:"<>|]', '_', filename)

# 抓取網頁內容
def fetch_page_content(url):
    try:
        response = session.get(url, headers=headers, cookies=cookies, timeout=15)
        response.raise_for_status()
        return response.text
    except requests.exceptions.RequestException as e:
        print(f"抓取頁面時出錯 {url}: {e}")
        return None

# 從頁面中提取章節連結
def get_chapters_from_page(page_content):
    soup = BeautifulSoup(page_content, 'lxml')
    return soup.find_all('a', class_='btn_L_blue')

# 下載章節
def download_chapter(chapter_url, chapter_number):
    retries = 5
    while retries > 0:
        try:
            text_url = chapter_url.replace("articles", "articlescontent")
            headers['Referer'] = chapter_url
            response = session.get(text_url, headers=headers, cookies=cookies, timeout=30)
            response.raise_for_status()

            chapter = response.text.replace("&nbsp;&nbsp;", '')
            soup = BeautifulSoup(chapter, 'lxml')
            chapter_title = soup.find('h1').get_text()

            book_folder = f'{book_name}_chapters'
            if not os.path.exists(book_folder):
                os.makedirs(book_folder)

            formatted_title = f"{chapter_number:03d}_{sanitize_filename(chapter_title)}"
            filename = os.path.join(book_folder, f'{formatted_title}.txt')

            if os.path.exists(filename):
                print(f'{formatted_title} 已經存在。跳過下載。')
                return True  # 下載成功

            with open(filename, 'w', encoding='utf-8') as txt:
                print(f'{formatted_title} 處理中...')
                txt.write(f'{formatted_title}\n')
                text = soup.find_all('p')
                if not text:
                    print(f"在第 {chapter_number} 章節未找到文本。")
                for row in text:
                    txt.write(row.get_text() + '\n')
                print(f'{formatted_title} 完成。')
            return True  # 下載成功
        except requests.exceptions.RequestException as e:
            print(f"處理章節時出錯 {chapter_url}: {e}")
            retries -= 1
            if retries == 0:
                return False  # 重試後失敗
            time.sleep(2)  # 短暫等待後重試
    return False  # 重試後仍然失敗

# 遍歷所有章節，並下載
def getContent(page, chapter_number):
    content_url = f'https://www.po18.tw/books/{book_number}/articles?page={page}'

    page_content = fetch_page_content(content_url)
    if not page_content:
        return

    chapters = get_chapters_from_page(page_content)
    if not chapters:
        print(f"在第 {page} 頁面未找到章節。")
        return

    with ThreadPoolExecutor(max_workers=20) as executor:
        futures = []
        for i in range(len(chapters)):
            if chapter_number > chapter_sum:
                print("所有章節已經處理完成。")
                return

            chapter_url = 'https://www.po18.tw' + chapters[i].get('href')
            futures.append(executor.submit(download_chapter, chapter_url, chapter_number))
            chapter_number += 1
            time.sleep(random.uniform(1, 2))  # 在提交之間延遲

        for future in as_completed(futures):
            future.result()

    if chapter_number <= chapter_sum:
        page += 1
        getContent(page, chapter_number)

# 重試失敗的章節
def retry_failed_chapters():
    global failed_chapters
    if failed_chapters:
        print("重試失敗的章節...")
        retries = 5
        while failed_chapters and retries > 0:
            current_failed_chapters = failed_chapters.copy()
            failed_chapters = []
            with ThreadPoolExecutor(max_workers=20) as executor:
                futures = [executor.submit(download_chapter, url, num) for url, num in current_failed_chapters]
                for future in as_completed(futures):
                    if not future.result():
                        failed_chapters.append((url, num))  # 重新添加失敗的章節
            retries -= 1
            if failed_chapters:
                print(f"剩餘重試次數: {retries}. 重試失敗的章節...")
            time.sleep(2)  # 短暫等待後重試

# 生成 EPUB 文件
def create_epub():
    book_folder = f'{book_name}_chapters'
    if not os.path.exists(book_folder):
        print(f"文件夾 {book_folder} 不存在。請先下載章節。")
        return

    book = epub.EpubBook()
    book.set_identifier(book_number)
    book.set_title(book_name)
    book.set_language('zh')

    # 添加目錄頁面
    toc = []
    spine = ['nav']

    for filename in sorted(os.listdir(book_folder)):
        if filename.endswith('.txt'):
            chapter_title = filename.split('_', 1)[1].replace('.txt', '')
            with open(os.path.join(book_folder, filename), 'r', encoding='utf-8') as file:
                content = file.read()

            chapter = epub.EpubHtml(title=chapter_title, file_name=filename.replace('.txt', '.xhtml'))
            chapter.content = f"<h1>{chapter_title}</h1><p>{content.replace('\n', '</p><p>')}</p>"

            book.add_item(chapter)
            toc.append(chapter)
            spine.append(chapter)

    # 定義目錄
    book.toc = toc
    book.spine = spine

    # 添加導航文件
    book.add_item(epub.EpubNcx())
    book.add_item(epub.EpubNav())

    # 設置 CSS
    style = '''
    body { font-family: Times, serif; }
    h1 { text-align: center; margin-bottom: 20px; }
    p { text-indent: 1em; margin-top: 0.5em; margin-bottom: 0.5em; }
    '''
    nav_css = epub.EpubItem(uid="style_nav", file_name="style/nav.css", media_type="text/css", content=style)
    book.add_item(nav_css)

    # 生成 EPUB 文件
    epub_name = sanitize_filename(book_name) + '.epub'
    epub.write_epub(epub_name, book, {})

    print(f'EPUB 文件 "{epub_name}" 已生成。')

# 主程序
book_number = '778402'
book_name = '快穿之女配勢要撲倒男主'
chapter_sum = 785

# 從第一頁開始抓取章節 = 1
start_chapter = 1
session = requests.session()

failed_chapters = []

# 開始下載章節
getContent(1, start_chapter)

# 嘗試處理失敗的章節
retry_failed_chapters()

# 生成 EPUB 文件
create_epub()