Python数据持久化存储实现方法分析

conn = pymongo.MongoClient('IP地址'，27017)

db = conn['库名']

myset = db['集合名']

myset.inset.one({})

#!/usr/bin/python
# -*- coding: utf-8 -*-
# @Time : 2019/6/26 8:56
# @Author : #####
# @Site :
# @File : 猫眼电影_mongo存储.py
# @Software: PyCharm
from urllib import request
import re
import time
import pymongo
class MaoyanSpider(object):
  def __init__(self):
    self.headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.5221.400 QQBrowser/10.0.1125.400'}
    #用来计数
    self.page=1
    #连接对象
    self.coon =pymongo.MongoClient('locslhost',27017)
    #创建库对象
    self.db=self.coon['maoyaodb']
    #集合对象
    self.myset=self.db['top100']
  def get_page(self,url):
    req = request.Request(url,headers=self.headers)
    res = request.urlopen(req)
    html = res.read().decode('utf-8')
    self.parse_page(html)
  def parse_page(self,html):
    p = re.compile( '
.*?title="(.*?)".*?class="star">(.*?)
.*?class="releasetime">(.*?)
',re.S)
    r_list = p.findall(html)
    self.write_mongo(r_list)
  def write_mongo(self,r_list):
    for r_t in r_list:
      d={
        '电影名称：':r_t[0].strip(),
        '电影主演：':r_t[1].strip(),
        '上映时间：':r_t[2].strip()
      }
    #插入数据库
      self.myset.inset.one(d)
  def work_on(self):
    for pn in range(0,41,10):
      url = 'https://maoyan.com/board/4?offset=%s' % str(pn)
      self.get_page(url)
      print('第%d页爬取成功' % self.page)
      self.page += 1
      time.sleep(4)
if __name__ == '__main__':
  begin = time.time()
  spider = MaoyanSpider()
  spider.work_on()
  end = time.time()
  print("执行时间%.2f" % (end - begin)) #注不完美，仍然需修改