爬取www.piaofang.biz电影信息并存储到数据库

环境：python3.7

import re
import requests
import pymysql

headers = {'User-Agent':'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4209.2 Mobile Safari/537.36'}

req = requests.get('http://www.piaofang.biz/',headers=headers)

# 如果网站的编码不是采用utf-8，一般采用以下的形式获取数据
# con =req.content.decode()
# 1、设置网站的解码的编码格式
req.encoding = 'gb2312'

# 2、通过text属性获取内容
con = req.text

names = re.findall(r'<td class="title">《<a href=\'.+?\' target=_blank>(.+?)<b>票房</b></a>》<span>|<td class="title">《(.*?)》',con)
print(names)
print(len(names))

names = [  i[0] if i[0]!='' else i[1]    for i in names]
print(names)
print(len(names))

years = re.findall(r'<td class="year">(\d+)</td>',con)
print(years)
print(len(years))

types = re.findall(r'<td class="type">(.+?)<span>',con)
print(types)
print(len(types))

daoyans = re.findall(r'<td class="daoyan">(.*?)</td>',con)
print(daoyans)
print(len(daoyans))

piaofangs = re.findall(r'<td class="piaofang"><span>(.*?)</span',con)
print(piaofangs)
print(len(piaofangs))

# 连接数据库
con = pymysql.connect(host='127.0.0.1',user='root',database='test',password='Python141804.')

# 创建游标
cursor = con.cursor()
print(cursor)

sql = 'insert into movies values '
for name,year,type,daoyan,piaofang in zip(names,years,types,daoyans,piaofangs):
    sql += f'(null,"{name}",{year},"{type}","{daoyan}",{piaofang.replace(",","")}),'

sql = sql[:-1]

print(sql)

cursor.execute(sql)

con.commit()

cursor.close()
con.close()