python爬取猫眼电影top100名单

用requests、正则表达式爬取猫眼电影top100的名单
完整代码如下：

import requests
import re
def getHtmltext(url):	#获得网页
    try:
        html = requests.get(url)
        html.raise_for_status()
        html.encoding = html.apparent_encoding
        return html.text
    except:
        return None

def parsehtml(html):	#提取信息
    numtitle = re.findall(r'<i class=".*?">(\d+)</i>\s*<a hre'          #匹配出来为列表，里面为元组
                          r'f=".*?" title="(.*?)" class=',html,re.M)    #源代码换行用\s*来匹配
    return numtitle
def printlist(List):    #打印出列表
    for i in List:
        print("{:<6}{:<12}".format(i[0],i[1]))
def main():
    print("{:<6}{:<12}".format('名次', '电影名'))
    for i in range(10):		#10页
        url = "https://maoyan.com/board/4?offset=" + str(i * 10)
        html = getHtmltext(url)
        numtitle = parsehtml(html)
        printlist(numtitle)

if __name__ == "__main__":
    main()