爬取小说，制作小说下载器

小说网站链接:https://www.heenee.com/

整本小说下载代码：

import requests
import parsel
from prettytable import PrettyTable
from tqdm import tqdm
import os
import time

# 小说网站链接:https://www.heenee.com/
# 采集单章小说 采集正本小说 实现搜索下载

# 采集单章小说
def GetResponse(url):
    headers = {
        "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
    }
    response = requests.get(url=url,headers=headers)
    return response

def GetContent(href):
    '''获取单章小说内容'''
    link = 'https://www.heenee.com'+href
    html = GetResponse(link).text
    selector = parsel.Selector(html)
    content = '\n\n'.join(selector.css('div #htmlContent p::text').getall())
    return content

def SaveContent(filename,title,content):
    with open(filename+title+'.txt',mode='a',encoding='utf-8') as f:
        f.write(content)

def GetInfo():
    '''获取小说章节链接，章节名字，小说名字'''
    # 目录页链接，获取数据
    url = 'https://www.heenee.com/quanben/27/27001/'
    html = GetResponse(url).text
    #解析数据
    selector = parsel.Selector(html)
    name = selector.css('dd h1::text').get().split(' ')[0]
    title_list = selector.css('.L a::text').getall()
    href_list = selector.css('.L a::attr(href)').getall()
    return name,title_list,href_list

if __name__ == '__main__':
    name,title_list,href_list = GetInfo()
    filename = f'{name}\\'
    if not os.path.exists(filename):
        os.mkdir(filename)
    for title,href in tqdm(zip(title_list,href_list)):
        time.sleep(1)
        content = GetContent(href)
        SaveContent(filename,title,content)
        print(f'正在下载:{title}')

实现搜索整本小说下载：

import requests
import parsel
from prettytable import PrettyTable
from tqdm import tqdm
import os
import time

# 小说网站链接:https://www.heenee.com/
# 采集单章小说 采集整本本小说 实现搜索下载

# 采集单章小说
def GetResponse(url):
    headers = {
        "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
    }
    response = requests.get(url=url,headers=headers)
    return response

def GetContent(href):
    '''获取单章小说内容'''
    link = 'https://www.heenee.com'+href
    html = GetResponse(link).text
    selector = parsel.Selector(html)
    content = '\n\n'.join(selector.css('div #htmlContent p::text').getall())
    return content

def SaveContent(filename,title,content):
    with open(filename+title+'.txt',mode='a',encoding='utf-8') as f:
        f.write(content)

def GetInfo(link):
    '''获取小说章节链接，章节名字，小说名字'''
    # 目录页链接，获取数据
    html = GetResponse(link).text
    #解析数据
    selector = parsel.Selector(html)
    name = selector.css('dd h1::text').get().split(' ')[0]
    title_list = selector.css('.L a::text').getall()
    href_list = selector.css('.L a::attr(href)').getall()
    return name,title_list,href_list

def GetSearch():
    info = []
    input_content = input('可输入作者和书名，请您别少字也别错别字:')
    try:
        search_url = f'https://www.heenee.com/api/search?q={input_content}'
        json_data = GetResponse(search_url).json()
        tb = PrettyTable()
        num = 0
        tb.field_names = ['序号','分类','书名','作者','更新时间','状态','更新章节','书籍详情链接']
        for index in json_data['data']['search']:
            dit = {
                '分类': index['cate_name'],
                '书名': index['book_name'],
                '作者': index['author'],
                '更新时间': index['uptime'],
                '状态': index['status_str'],
                '最新章节': index['latest_chapter_name'],
                '书籍详情链接': index['book_list_url'],
            }
            info.append(dit)
            tb.add_row([num,index['cate_name'],index['book_name'],index['author'],index['uptime'],index['status_str'],index['latest_chapter_name'],index['book_list_url']])
            num += 1
        print(tb)
    except:
        print('请再次详细一点输入:')
    key_num = int(input('请输入你要下载的歌曲序号: '))
    link = f'https://www.heenee.com{info[key_num]["书籍详情链接"]}' #注意这里里面的引号必须是双引号
    return link

if __name__ == '__main__':
    link = GetSearch()
    print(link)
    name,title_list,href_list = GetInfo(link)
    filename = f'{name}\\'
    if not os.path.exists(filename):
        os.mkdir(filename)
    for title,href in tqdm(zip(title_list,href_list)):
        time.sleep(1)
        content = GetContent(href)
        SaveContent(filename,title,content)
        print(f'正在下载:{title}')

结果展现：

 

分析，首先分析单章小说怎么下载，然后在目录页，找到整本小说所有章节的链接，然后在搜索页面，找到如何输入一个关键词，就能出所有结果的接口。打开开发者工具，在搜索框输入遮天。

 

所有结果在该数据包

 

详细分析过程见下面的链接：

【Python采集小说网站-制作小说下载器-哔哩哔哩】 https://b23.tv/6kbS4jU