python爬虫-豆瓣250,爬取电影名称,年份,评论人数,评分

对代码有疑问的可评论留言

# -*- coding: utf-8 -*-
import json
import re
import requests
import csv
if __name__ == '__main__':
    #UA伪装:将对应的User-Agent封装到一个字典中
    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'
    }
    #批量获取不同企业的id值
    url='https://movie.douban.com/top250?start=0'
    #参数的封装
    resp = requests.get(url,headers=headers)
    page_content = resp.text
    obj = re.compile('<li>.*?<span class="title">(?P<name>.*?)</span>.*?<p class="">.*?<br>(?P<year>.*?)&nbsp.*?<span class="rating_num" property="v:average">(?P<score>.*?)</span>.*?<span>(?P<num>.*?)人评价</span>',re.S)
    result = obj.finditer(page_content)
    f=open("data.csv",mode="w")
    csvwriter =csv.writer(f)
    for it in result:
        print("电影名称:--------")
        print(it.group("name"))
        print("电影出产年份:--------")
        print(it.group("year").strip())
        print("电影评分是:--------")
        print(it.group("score"))
        print("该电影有"+it.group("num")+"人评价")
        #将数据写进csv文件
        dic=it.groupdict()
        dic['year'] =dic['year'].strip()
        csvwriter.writerow(dic.values())
    f.close()
    print("over")