python 3.8
pycharm

requests  >>> pip install requests 數(shù)據(jù)請(qǐng)求
parsel  >>> pip install parsel 數(shù)據(jù)解析
(完善功能) 添加搜索功能 搜索小說(shuō)名字或者作者名字
tqdm  >>> pip install tqdm  下載進(jìn)度條顯示模塊
pandas >>> pip install pandas 輸入的格式好看一些

# 導(dǎo)入數(shù)據(jù)請(qǐng)求模塊
import requests
# 導(dǎo)入數(shù)據(jù)解析模塊
import parsel
# 導(dǎo)入正則表達(dá)式模塊
import re
# 導(dǎo)入pandas
import pandas as pd
# 導(dǎo)入進(jìn)度條顯示模塊
from tqdm import tqdm

while True:
    key_word = input('請(qǐng)輸入你想要下載的小說(shuō)名字(輸入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() # 小說(shuō)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 = {
                '書名': novel_name,
                '作者': author,
                '書ID': href,
            }
            lis.append(dit)
        print(f'一共搜索到{len(lis)}條數(shù)據(jù)內(nèi)容, 結(jié)果如下')
        search_data = pd.DataFrame(lis)
        print(search_data)
        key_num = input('請(qǐng)選擇你想要下載小說(shuō)序號(hào): ')  # 輸入的數(shù)據(jù)類型字符串?dāng)?shù)據(jù)
        novel_id = lis[int(key_num)]['書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)  # 正則表達(dá)式提取出來(lái)數(shù)據(jù)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. 發(fā)送請(qǐng)求, 對(duì)于剛剛分析得到的url地址發(fā)送請(qǐng)求
            # url = 'https://www./book/60126/14362.html'
            response = requests.get(novel_url, headers)  # <Response [200]> 返回response響應(yīng)對(duì)象, 200表示請(qǐng)求成功
            # 2. 獲取數(shù)據(jù), 獲取服務(wù)器返回的response響應(yīng)數(shù)據(jù)
            # response.text 獲取響應(yīng)體返回文本數(shù)據(jù)(網(wǎng)頁(yè)源代碼)
            # print(response.text)
            # 3. 解析數(shù)據(jù), 提取我們想要的數(shù)據(jù)內(nèi)容 小說(shuō)章節(jié)名字 以及小說(shuō)內(nèi)容
            # 提取數(shù)據(jù)方式: xpath css re 這三種方式都是可以提取數(shù)據(jù)
            selector = parsel.Selector(response.text)  # 把獲取到的response.text 轉(zhuǎn)換成 selector 對(duì)象
            # novel_title = selector.css('.bookname h1::text').get()  # get獲取第一個(gè)標(biāo)簽數(shù)據(jù) 返回字符串?dāng)?shù)據(jù)
            # novel_title_1 = selector.xpath('//*[@class="bookname"]/h1/text()').get()  # get獲取第一個(gè)標(biāo)簽數(shù)據(jù) 返回字符串?dāng)?shù)據(jù)
            novel_content_list = selector.css('#content::text').getall()  # getall 獲取所有標(biāo)簽內(nèi)容, 返回列表數(shù)據(jù)
            # 需要把列表轉(zhuǎn)成字符串?dāng)?shù)據(jù) join  \n換行符
            novel_content = '\n'.join(novel_content_list)
            # print(novel_title)
            # print(novel_title_1)
            # print(novel_content_list)
            # print(novel_content)
            # 4. 保存數(shù)據(jù)
            # w寫入數(shù)據(jù)但是覆蓋 a寫入追加寫入, 寫入文件末尾 b 二進(jìn)制模式
            """
            第一章 xxx
            小說(shuō)內(nèi)容
            第二章 xxx
            小說(shuō)內(nèi)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('請(qǐng)正確輸入小說(shuō)名字或者作者名字 / 沒有這本書的數(shù)據(jù)..')

https://www.bilibili.com/video/BV1FT4y1X7B2/