import requests from lxml import etree urls = ['https://www.xxddxs.com/book/{}.html'.format(i) for i in range(1, 20)] path = r'D:\py\venv\Scripts\xiaoshuo' def get_text(url: object) -> object: r = requests.get(url) r.encoding = 'utf-8' selector = etree.HTML(r.text) # Get the book title from the page title = selector.xpath('//div[@class="bookname"]/h1/text()') # If no title found, print an error message and return early if len(title) == 0: print(f"No title found for {url}") return # Get the text of the chapter text = selector.xpath('//div[@id="content"]/text()') # Print the text to standard output print(text) # Write the text to a file in the specified directory with open(path + "\\" + title[0], 'w', encoding='utf-8') as f: for i in text: f.write(i) if __name__ == '__main__': for url in urls: get_text(url) 帮我修改并可以爬取到标题

Sure! 以下是修改后的代码：

import requests
from lxml import etree

urls = ['https://www.xxddxs.com/book/{}.html'.format(i) for i in range(1, 20)]
path = r'D:\py\venv\Scripts\xiaoshuo'

def get_text(url):
    r = requests.get(url)
    r.encoding = 'utf-8'
    selector = etree.HTML(r.text)

    # Get the book title from the page
    title = selector.xpath('//div[@class="bookname"]/h1/text()')

    # If no title found, print an error message and return early
    if len(title) == 0:
        print(f"No title found for {url}")
        return

    # Get the text of the chapter
    text = selector.xpath('//div[@id="content"]/text()')

    # Print the text to standard output
    print(text)

    # Write the text to a file in the specified directory
    with open(path + "\\" + title[0].strip() + ".txt", 'w', encoding='utf-8') as f:
        for i in text:
            f.write(i)

if __name__ == '__main__':
    for url in urls:
        get_text(url)

在原有代码的基础上，我在 `open()` 方法中添加了 `.strip()`，以去除标题中的空白字符。此外，我还为文件添加了 `.txt` 扩展名，以方便后续的操作。