python 3.8
pycharm

requests  >>> pip install requests 数据请求
parsel  >>> pip install parsel 数据解析
(完善功能) 添加搜索功能 搜索小说名字或者作者名字
tqdm  >>> pip install tqdm  下载进度条显示模块
# Python学习交流群：924040232
pandas >>> pip install pandas 输入的格式好看一些

# 导入数据请求模块
import requests
# 导入数据解析模块
import parsel
# 导入正则表达式模块
import re
# 导入pandas
import pandas as pd
# 导入进度条显示模块
from tqdm import tqdm

while True:
    key_word = input('请输入你想要下载的小说名字(输入0即可退出): ')
    if key_word == '0':
        break
    search_url = f'https://www.***.com/search.php?q={key_word}'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.82 Safari/537.36'
    }
    response = requests.get(url=search_url, headers=headers)
    # print(response.text)
    selector_1 = parsel.Selector(response.text)
    divs = selector_1.css('.result-list div.result-item')
    # print(divs)
    if divs:
        lis = []
        for div in divs:
            novel_name = div.css('.result-game-item-title-link::attr(title)').get() # 小说名字
            href = div.css('.result-game-item-title-link::attr(href)').get().split('/')[2] # ID
            author = div.css('.result-game-item-info p:nth-child(1) span:nth-child(2)::text').get() # 作者
            # print(novel_name, href, author)
            dit = {
                '书名': novel_name,
                '作者': author,
                '书ID': href,
            }
            lis.append(dit)
        print(f'一共搜索到{len(lis)}条数据内容, 结果如下')
        search_data = pd.DataFrame(lis)
        print(search_data)
        key_num = input('请选择你想要下载小说序号: ')  # 输入的数据类型字符串数据
        novel_id = lis[int(key_num)]['书ID']
        url = f'https://www.***.com/book/{novel_id}/'
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.82 Safari/537.36'
        }
        response = requests.get(url, headers)
        # print(response.text)  # 正则表达式提取出来数据返回列表 ['天道修改器']
        novel_name = re.findall('<h1>(.*?)</h1>', response.text)[0]
        novel_info = re.findall('<dd><a href="(.*?)"  >(.*?)</a></dd>', response.text)
        # print(novel_name)
        # print(novel_info)
        for novel_url, novel_title in tqdm(novel_info):
            # 'https://www.***e.com/book/60126/14362.html'
            novel_url = 'https://www.***.com' + novel_url
            # print(novel_url, novel_title)
            # 1. 发送请求, 对于刚刚分析得到的url地址发送请求
            # url = 'https://www.biqugee.com/book/60126/14362.html'
            response = requests.get(novel_url, headers)  # <Response [200]> 返回response响应对象, 200表示请求成功
            # 2. 获取数据, 获取服务器返回的response响应数据
            # response.text 获取响应体返回文本数据(网页源代码)
            # print(response.text)
            # 3. 解析数据, 提取我们想要的数据内容 小说章节名字 以及小说内容
            # 提取数据方式: xpath css re 这三种方式都是可以提取数据
            selector = parsel.Selector(response.text)  # 把获取到的response.text 转换成 selector 对象
            # novel_title = selector.css('.bookname h1::text').get()  # get获取第一个标签数据 返回字符串数据
            # novel_title_1 = selector.xpath('//*[@class="bookname"]/h1/text()').get()  # get获取第一个标签数据 返回字符串数据
            novel_content_list = selector.css('#content::text').getall()  # getall 获取所有标签内容, 返回列表数据
            # 需要把列表转成字符串数据 join  \n换行符
            novel_content = '\n'.join(novel_content_list)
            # print(novel_title)
            # print(novel_title_1)
            # print(novel_content_list)
            # print(novel_content)
            # 4. 保存数据
            # w写入数据但是覆盖 a写入追加写入, 写入文件末尾 b 二进制模式
            """
            第一章 xxx
            小说内容
            第二章 xxx
            小说内容
            """
            with open(novel_name + '.txt', mode='a', encoding='utf-8') as f:
                f.write(novel_title)
                f.write('\n')
                f.write(novel_content)
                f.write('\n')
            # print('正在保存', novel_title)

    else:
        print('请正确输入小说名字或者作者名字 / 没有这本书的数据..')