任选一小说网站，爬取任意一部小说，以记事本的形式保存。

本文链接：https://blog.youkuaiyun.com/cygqtt/article/details/106492389

本文介绍了一种使用Python的requests库和lxml库抓取网络小说的方法，通过解析网页结构，获取小说章节链接和内容，并保存为本地文件。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

1、任选一小说网站，爬取任意一部小说，以记事本的形式保存。

第一种情况(网址可能已失效)：

import requests
from lxml import etree
def get_url():
    url = 'http://www.yuetutu.com/cbook_24378/'
    r = requests.get(url)
    tree = etree.HTML(r.text)
    return tree

def get_book_url(tree):
    book_list= []
    dd_list = tree.xpath('//*[@id="list"]/dl/dd')
    i = 1
    for dd in dd_list:
        if i >= 9:
            url_book = dd.xpath('a')[0].attrib['href']
            title_book = dd.xpath('a')[0].text
            book_list.append((title_book, url_book))
        i += 1
    return book_list

def get_content(book):
    domain = 'http://www.yuetutu.com'
    for i in book:
        url = domain + i[1]
        r = requests.get(url)
        r.encoding = 'utf8'
        tree = etree.HTML(r.text)
        title = tree.xpath('//*[@id="wrapper"]/div[3]/div/div[2]/h1')[0].text
        text = tree.xpath('//*[@id="content"]/text()')

        path = r'C:\Users\dell\Desktop\小说\ '
        with open(path + title + '.txt', 'w', encoding='utf8') as f:
            for j in text:
                f.write(j)
        print('******{} 下载完成! ******'.format(title))


if __name__ == '__main__':
    a = get_url()
    b = get_book_url(a)
    get_content(b)

在这里插入图片描述

第二种情况：

import requests
from lxml import etree
def get_url():
    url = 'https://www.51biquge.com/book_12066/'
    r = requests.get(url)
    tree = etree.HTML(r.text)
    return tree

def get_book_url(tree):
    book_list = []
    dd_list = tree.xpath('//*[@id="list"]/dl/dd')
    i = 1
    for dd in dd_list:
        if i >= 13:
            url_book = dd.xpath('a')[0].attrib['href']
            title_book = dd.xpath('a')[0].text.strip()
            book_list.append((title_book, url_book))
        i += 1
    return book_list

def get_content(book):
    domain = 'https://www.51biquge.com'
    for i in book:
        url = domain + i[1]
        r = requests.get(url)
        r.encoding = 'utf8'
        tree = etree.HTML(r.text)
        title = tree.xpath('//*[@id="main"]/div/div/div[2]/h1')[0].text
        text = tree.xpath('//*[@id="content"]//p/text()')
        path = r'C:\Users\dell\Desktop\小说\ '
        with open(path + title + '.txt', 'w', encoding='utf8') as f:
            for j in text:
                f.write(j)
        print('******{} 下载完成! ******'.format(title))


if __name__ == '__main__':
    a = get_url()
    b = get_book_url(a)
    get_content(b)