刚开始学习的时候写的代码 现在看看真是感慨

Posted 2021-01-02 cwkcwk

from urllib import request
import json
import time
import re

url = ["https://movie.douban.com/celebrity/1032800/movies?start=0&format=pic&sortby=time&","https://movie.douban.com/celebrity/1032800/movies?start=10&format=pic&sortby=time&","https://movie.douban.com/celebrity/1032800/movies?start=20&format=pic&sortby=time&","https://movie.douban.com/celebrity/1032800/movies?start=30&format=pic&sortby=time&"]
for i in url:
    

    url = i

    rsp = request.urlopen(url)
    print(type(rsp))

    data = rsp.read().decode()
    print(type(data))
    #data = json.loads(data)
    #timesleep(1)
    ##########print(data)

#需要提取<dt>()</div>
    s = r‘<dt>(.*?)</div>‘

    pattern = re.compile(s,re.S) #re.S将整个提取内容视作一整个字符串 否则第一行跳转后，就会使抓取结束

    dianying = pattern.findall(data)
    ##########print(len(dianying))
    #print(dianying)
    #print("==="*50)

    for dyname in dianying:
        ss = r‘<img.*?alt="(.*?)"‘
        pattern = re.compile(ss)
        biaoti = pattern.findall(dyname)
        print(biaoti)

        sss = r‘<span>(.*?)</span>‘
        pattern = re.compile(sss)
        fenshu = pattern.findall(dyname)
        print(fenshu)

        sss = r‘<dd>(.*?)</dd>‘
        pattern = re.compile(sss)
        daoyan = pattern.findall(dyname)[0]
        print("导演:",daoyan)
        try:
            yanyuan = pattern.findall(dyname)[1]
            print("演员:",yanyuan)
        except:
            print("无导演")
        print("-----------------------------"*8)