一个贼简单的python爬虫实例

import requests
import json
import os

header = {
        "User-Agent": "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.162 Mobile Safari/537.36"}
class douban:
    def __init__(self, url, dir):
        self.url = url
        self.dir = dir
        self.TV_name = []
        self.TV_picture = []
    def get_sourcename(self):
        print("开始获取剧名和剧照................")
        response = requests.get(self.url,headers=header)
        rejson = json.loads(response.content.decode())
        x = 0
        count=len(rejson["subjects"])
        print(count)
        if count==0:
            return x
        for x in range(count):
            self.TV_name.append(rejson["subjects"][x]["title"])
            self.TV_picture.append(rejson["subjects"][x]["cover"])
        print("获取了",x+1,"张剧照！")
        return x+1
    def get_source(self):
        print("开始保存到本地................")
        for y in range(len(self.TV_name)):
            directory = "{}\{}.jpg"
            name=self.TV_name[y].replace("<","").replace(">","")
            name1=name.replace("/","").replace("\\","")
            name2=name1.replace(" ","").replace(":","")
            name3=name2.replace("*","").replace("?","")
            response2 = requests.get(self.TV_picture[y])
            with open(directory.format(dir, name3), "wb") as file:
                file.write(response2.content)
        print("保存成功！")

if __name__ == "__main__":
    url ="https://movie.douban.com/j/search_subjects?type=tv&tag={}&page_limit=20&page_start={}"#input("输入豆瓣网址：")
    dir ="douban_{}_dramas"#input("输入存储文件夹：")
    Type_of_opera=input("请输入电视的种类（热门 美剧 英剧 韩剧 日剧 国产剧 港剧 日本动画 综艺 纪录片）：")
    director=input("请输入图片存储的目录：")
    dir=dir.format(director)
    if os.path.exists(dir) == 0:
        os.mkdir(dir)
    page=1
    print("开始获取：")
    while page:
        print("第", page, "次获取:")
        urllist=url.format(Type_of_opera,(page-1)*20)
        print(urllist)
        db = douban(urllist,dir)
        stop = db.get_sourcename()
        db.get_source()
        page+=1
        if stop <20:
            print("获取结束!")
            print("总共获取了",(page-2)*20+stop,"张剧照")
            break