哪里有问题，帮我看看？

Question

import requests

第一页

https://www.dy2018.com/2/index_1.html

第二页

https://www.dy2018.com/2/index_2.html

第三页

https://www.dy2018.com/2/index_3.html

class DYspider:
"""
电影天堂爬虫
功能：动作片前五页的内容保存
"""
def init(self) :
# 1.请求构造地址
self.url = "https://www.dy2018.com/2/index_{}.html"
def get_response(self,url):
response = requests.get(url).content.decode()
return response

def save_page(self, content, page_num):
    """保存页面"""
    file_name = f"第{page_num}页.html"
    with open(f'./电影天堂/{file_name}', 'w', encoding='utf-8') as f:
        # 写入文件
        f.write(content)

def run(self, page=5):
    """爬虫启动函数"""
    # 1. 构造地址
    for pn in range(page):
        # pn的取值0 1 2 3 4
        url = self.url.format(pn+1)
        # 发送请求并获取响应
        content = self.get_response(url)
        # 保存全站内容
        self.save_page(content, pn + 1)

if name == "main":
# 实例化
DYspider().run()
import requests

第一页

https://www.dy2018.com/2/index_1.html

第二页

https://www.dy2018.com/2/index_2.html

第三页

https://www.dy2018.com/2/index_3.html

class DYspider:
"""
电影天堂爬虫
功能：动作片前五页的内容保存
"""
def init(self) :
# 1.请求构造地址
self.url = "https://www.dy2018.com/2/index_{}.html"
def get_response(self,url):
response = requests.get(url).content.decode()
return response

def save_page(self, content, page_num):
    """保存页面"""
    file_name = f"第{page_num}页.html"
    with open(f'./电影天堂/{file_name}', 'w', encoding='utf-8') as f:
        # 写入文件
        f.write(content)

def run(self, page=5):
    """爬虫启动函数"""
    # 1. 构造地址
    for pn in range(page):
        # pn的取值0 1 2 3 4
        url = self.url.format(pn+1)
        # 发送请求并获取响应
        content = self.get_response(url)
        # 保存全站内容
        self.save_page(content, pn + 1)

if name == "main":
# 实例化
DYspider().run()

Answer 1

requests.get(url).content.decode()这句要加上headers，来源和user-agent要加上，要不被反扒获取不到数据。用gbk解码内容，第一页网址也有问题，需要判断下是否第一页，改下面就可以了

import requests
class DYspider:
    def __init__(self):
# 1.请求构造地址
        self.url = "https://www.dy2018.com/2/index_{}.html"
    def get_response(self,url):
        response = requests.get(url,headers={
        'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36 Edg/96.0.1054.62',
        'referer':url
        }).content.decode('gbk')#用gbk解码

        return response

    def save_page(self, content, page_num):
        file_name = f"第{page_num}页.html"
        with open(f'./电影天堂/{file_name}', 'w', encoding='utf-8') as f:
        # 写入文件
            f.write(content)
 
    def run(self, page=5):
    # 1. 构造地址
        for pn in range(page):
        # pn的取值0 1 2 3 4
            if pn==0:
                url = self.url.replace('_{}','')#没有index_1.html这种链接，会404
            else:
                url = self.url.format(pn+1)

        # 发送请求并获取响应
            content = self.get_response(url)
        # 保存全站内容
            self.save_page(content, pn + 1)

if __name__ == "__main__":
# 实例化
    DYspider().run()