python3-10.爬虫-猫眼电影榜单

import urllib
from urllib import request
import re

def main():
    headers = {'User-Agent':'Mozilla/5.0 3578.98 Safari/537.36'}
    url = urllib.request.Request("https://maoyan.com/board/4",headers=headers)
    content = urllib.request.urlopen(url,timeout=15).read().decode('utf-8')

    pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?src="(.*?)".*?name"><a'
                         +'.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'
                         +'.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>', re.S)
 #.*任意数量的不换行的字符 ？重复0次或者n次  \d+匹配1个或更多连续的数字
    items = re.findall(pattern, content)
    list = []
    for item in items:
        dict={}
        dict = {"排名":item[0],"名称":item[2],"主演:":item[3].strip()[3:],"上映时间:":item[4].strip()[5:],"豆瓣评分:":item[5] + item[6]}
        list.append(dict)
    print(list)
        
if __name__ == '__main__':
    print("猫眼电影排名榜单")
    main()

结果：