import asyncio
from crawl4ai import AsyncWebCrawler
from bs4 import BeautifulSoup

async def extract_div_text(html_content):
    """
    從HTML內(nèi)容中提取特定樣式的div文本
    
    參數(shù):
        html_content: 網(wǎng)頁的HTML內(nèi)容
        
    返回:
        提取到的文本內(nèi)容或未找到的提示信息
    """
    soup = BeautifulSoup(html_content, 'html.parser')
    # 查找目標(biāo) div（根據(jù) style 屬性匹配）
    target_div = soup.find('div', style=lambda
        value: value and 'cursor: default;font-size: 16px;line-height: 1.8;padding: 0 19px 25px' in value)

    if target_div:
        # 獲取 div 內(nèi)的所有文本，并清理空白
        text = target_div.get_text(separator='\n', strip=True)
        return text
    return "目標(biāo) div 未找到"

async def main():
    """
    主函數(shù)，執(zhí)行網(wǎng)頁抓取和內(nèi)容提取
    """
    async with AsyncWebCrawler() as crawler:
        # 抓取目標(biāo)網(wǎng)頁
        result = await crawler.arun("https://www.jjwxc.net/onebook.php?novelid=2490683&chapterid=2")
        
        if hasattr(result, 'html'):
            # 提取目標(biāo)div中的文本
            extracted_text = await extract_div_text(result.html)
            print(extracted_text)  # 打印全部字符
        else:
            print("未能獲取 HTML 內(nèi)容")

if __name__ == "__main__":
    # 運行異步主函數(shù)
    asyncio.run(main())

import asyncio
from crawl4ai import AsyncWebCrawler
from bs4 import BeautifulSoup

async def extract_div_text(html_content):
    soup = BeautifulSoup(html_content, 'html.parser')
    target_div = soup.find('div', style=lambda
        value: value and 'cursor: default;font-size: 16px;line-height: 1.8;padding: 0 19px 25px' in value)
    # ...其余代碼...

async def main():
    async with AsyncWebCrawler() as crawler:
        result = await crawler.arun("目標(biāo)URL")
        # ...處理結(jié)果...