爬取猫眼电影TOP100电影信息并将其保存到数据库（电影名，主演，上映时间）

import  re
from urllib import request
from urllib.request import urlopen
from concurrent.futures import ThreadPoolExecutor
#猫眼电影Top100网址
import pymysql

url='http://maoyan.com/board/4'
films=[]
#获取TOP100所有页的网址
def get_all_url(url,page):
    url_li=[url]
    for i in range(page-1):
        new_url=url+'?offset=%d'%((i+1)*10)
        url_li.append(new_url)
    return url_li
#爬取网页信息
def get_info(url):
    header={'User-agent':'Google Chrome/67.0.3396.87'}
    req=request.Request(url,headers=header)
    with urlopen(req) as urlObj:
        return urlObj.read().decode('utf-8')
# get_info(url)
#利用正则表达式提取所需要的信息
def get_content(url):
    content=get_info(url)
    '''
    

                主演：张国荣,张丰毅,巩俐
        
    
上映时间：1993-01-01(中国香港)
 
    '''
    pattern = r'.*<\/a><\/p>\s*
\s*(主演：.*)\s*<\/p>\s*' \
              r'
(上映时间：.*)<\/p> '
    films.extend(re.findall(pattern,content))
    return films
# get_content(url='http://maoyan.com/board/4')
def main():
    res=get_all_url(url,10)
    #使用多线程获取信息
    with ThreadPoolExecutor(max_workers=5)as pool:
        pool.map(get_content,res)


    #数据库连接
    conn=pymysql.connect(host='localhost',user='root',passwd='axis0214',
                         db='films',charset='utf8')
    #创建游标
    cur=conn.cursor()
    try:
        cur.execute('create table movies (movie varchar(40),action varchar(60),timeon varchar(120))')
        insert_sql='insert into movies values(%s,%s,%s)'
        cur.executemany(insert_sql,films)
        cur.execute('select * from movies')
        print(cur.fetchall())
    except Exception as e:
        print(e)
    else:
        print('信息写入成功。。。')
    conn.commit()
    cur.close()
    conn.close()
if __name__ == '__main__':
    main()