学习一个爬虫知识遇到TypeError: object of type 'NoneType' has no len()问题，求明白人指点迷津

Question

本来程序没有什么问题，在添加了如下代码时，程序开始报错

soup = BeautifulSoup(html,"html.parser")
        for item in soup.find_all('div',class_="item"):   #查找符合要求的字符串，形成列表
            data = []
            item = str(item)


            link = re.findall(findLink,item)[0]    #re库通过正则表达式查找指定的字符串
            print(link)
            #print(item)

出现如下问题：

Traceback (most recent call last):
  File "F:\pythonProject\test2\t2.py", line 79, in <module>
    main()
  File "F:\pythonProject\test2\t2.py", line 23, in main
    datalist = getData(baseurl)
  File "F:\pythonProject\test2\t2.py", line 40, in getData
    soup = BeautifulSoup(html,"html.parser")
  File "E:\pythonProject\lib\site-packages\bs4\__init__.py", line 312, in __init__
    elif len(markup) <= 256 and (
TypeError: object of type 'NoneType' has no len()

代码如下，可能有点乱

from test1 import t1
#引入自定义的模块
print(t1.add(3,4))

import urllib.request
import re
import bs4
from bs4 import BeautifulSoup
import sys
import  urllib
import xlwt
import sqlite3


def main():
    baseurl = "https://movie.douban.com/top250?start=0"
    #1.爬取网页
    datalist = getData(baseurl)
    savepath = ".\\doubanTop250.xls"
    #2.解析数据
    #3.保存数据
    #saveData(savepath)

    #askURL("https://movie.douban.com/top250?start=")

findLink = re.compile(r'<a href="(.*?)">')

#1.爬取网页
def getData(baseurl):
    datalist = []
    for i in range(0,1):   #调用获取页面信息的函数*10次
        url = baseurl + str(i*25)
        html = askURL(url)   #保存返回值
        # 2.解析数据
        soup = BeautifulSoup(html,"html.parser")
        for item in soup.find_all('div',class_="item"):   #查找符合要求的字符串，形成列表
            data = []
            item = str(item)


            link = re.findall(findLink,item)[0]    #re库通过正则表达式查找指定的字符串
            print(link)
            #print(item)


    return datalist


#得到指定一个URL的网页内容
def askURL(url):
    head = {   #模拟浏览器头部信息，向豆瓣发送消息
        "User-Agent": "Mozilla / 5.0(Windows NT 10.0;Win64; x64) AppleWebKit / 537.36(KHTML, likeGecko) Chrome / 97.0.4692.71 Safari / 537.36Edg / 97.0.107255"
    }
    #用户代理表示告诉豆瓣服务器我们是什么类型的机器，浏览器（本质上是告诉浏览器，我们可以接受什么内容的文件内容）
    request = urllib.request.Request(url,headers = head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
        print(html)
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)

        return html

#3.保存数据
def saveData(savepath):
    print("save...")

if __name__ == "__main__":
    main()

Answer 1

askURL的return html缩进有问题，放到except外

def askURL(url):
    head = {   #模拟浏览器头部信息，向豆瓣发送消息
        "User-Agent": "Mozilla / 5.0(Windows NT 10.0;Win64; x64) AppleWebKit / 537.36(KHTML, likeGecko) Chrome / 97.0.4692.71 Safari / 537.36Edg / 97.0.107255"
    }
    #用户代理表示告诉豆瓣服务器我们是什么类型的机器，浏览器（本质上是告诉浏览器，我们可以接受什么内容的文件内容）
    request = urllib.request.Request(url,headers = head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
        #print(html)
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)
 
    return html