我在B站上跟着视频教程学习网页爬虫,做到了想要爬取网页上的演员信息的时候就出错了,以下是目前的代码
import bs4
import re
import urllib.request,urllib.error
import sqlite3
from bs4 import BeautifulSoup
import sys
import requests
import importlib
importlib.reload(sys)
def main():
#爬取页面
baseurl="https://baike.baidu.com/item/平凡的荣耀"
datalist=getData(baseurl)
askURL("https://baike.baidu.com/item/平凡的荣耀")
#savepath=".\\平凡的荣耀数据.json"
#saveData(savepath)
#解析页面
#保存页面
def askURL(url):#获取指定页面内容
head={
"User-Agent":"Mozilla/5.0(Windows NT 10.0;WOW64)AppleWebKit/537.36(KHTML, likeGecko)Chrome/70.0.3538.25Safari/537.36Core/1.70.3741.400QQBrowser/10.5.3863.400"
}#假装自己是一个浏览器
request=urllib.request.Request(url,headers=head)
html=""
try:
response = requests.get(url,headers=head)
html=BeautifulSoup(response.text,'html')
#print(html)
except urllib.error.URLError as e:
if hasattr(e,"code"):
print(e.code)
if hasattr(e,"reason"):
print(e.reason)
return html
def getData(url):#爬取内容
datalist=[]
return datalist
def getTVData(url):
datalist=[]
html=askURL(url)
soup=BeautifulSoup(html,"html.parser")
for item in soup.find_all('div',class_="viewport"):#收视率
print(item)
return
#return datalist
def saveData(savepath):
print('save...')
# Press the green button in the gutter to run the script.
if __name__ == '__main__':
baseurl="https://baike.baidu.com/item/平凡的荣耀"
getTVData(baseurl)
结果报错了TypeError: 'NoneType' object is not callable
求大佬指教……