获取豆瓣电影排名

import urllib.request
import os
import re

def open_url(url):
    req = urllib.request.Request(url)
    #加上一个referer就成功了
    req.add_header("Referer","https://movie.douban.com/top250?start=25&filter=")
    req.add_header("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36")
    response = urllib.request.urlopen(req)
    html = response.read()
    return html
    
def find_imgs(url):
    html =   open_url(url).decode("utf-8")
    p = r'<span class=\"title\">([^&].+?)</span>'#[^&]用法：匹配不包含&的所有字符
    img_addrs1 = re.findall(p,html)
    return img_addrs1

def save(img_addrs):     
    with open("豆瓣top250.txt","w") as f:
        #将字典形式写入txt文件的一种方法。
        for each in img_addrs.items():
            #print(each)
            for i in each:
                print(i)
                j = str(i)
                f.write(j)
                f.write("\000")#加一个空格
            f.write("\n")
    f.close
    
def download(pages):#page可以自定义
    os.chdir(r"E:\python汇总\pythonsource\爬取存放")#切换到该目录
    #如果文件已存在就覆盖它
    try:
       os.mkdir("豆瓣top250")#创建新的目录
    except FileExistsError:
        pass
    
    os.chdir("豆瓣top250")#切换到该目录
  
    page_num = 0#int(get_page(url))
    global img_addrs
    img_addrs = []

    for i in range(pages):    
        page_url = "https://movie.douban.com/top250?start="+ str(page_num)+ "&filter="  
        img_addrs1 = find_imgs(page_url)
        for factor in img_addrs1:
            img_addrs.append(factor)
        #print(img_addrs)
        page_num += 25
    #print(img_addrs)
    #加上标号，变为字典形式
    num1 = [x for x in range(1,len(img_addrs)+1)]
    img_addrs = {x:y for (x,y) in zip(num1,img_addrs)}
    #img_addrs = list(img_addrs)
    #print(img_addrs)
    save(img_addrs)
        
if __name__=='__main__':
    #单独运行或者说作为程序运行时才为真，当作为模块运行时则为假
    url="https://movie.douban.com/top250?start=0&filter="
    download(10)