import requests import re import csv url="https://movie.douban.com/top250" hac={ "User-Agent": "Mozilla/5.0 (Windows NT 10.0 ; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.72 Safari/537.36 Edg/89.0.774.45" } resp=requests.get(url,headers=hac) ww=resp.text obj=re.compile(r'<li>.*?<div class="item">.*?<span class="title">(?P<name>.*?)</span>' r'.*?<br>(?P<year>.*?) .*?<span class="rating_num" property="v:average">' r'(?P<scare>.*?)</span>.*?<span>(?P<rs>.*?)人评价</span>',re.S) result=obj.finditer(ww) f=open("date.csv",mode="w") csvwriter=csv.writer(f) for it in result: dic=it.groupdict() dic['year']=dic['year'].strip() csvwriter.writerow(dic.values()) print("over")
切换一下字符编码
你是什么系统?打开csv用的是什么工具?
如果用excel打开应该不会乱码
在写入数据的时候, 设置编码规则为utf-8 呢