Python基于多线程实现抓取数据存入数据库的方法

""" 使用须知：代码中数据表名 aces ，需要更改该数据表名称的注意更改 """ import pymysql class Database(): # 设置本地数据库用户名和密码 host = "localhost" user = "root" password = "" database = "test" port = 3306 charset = "utf8" cursor='' connet ='' def __init__(self): #连接到数据库 self.connet = pymysql.connect(host = self.host , user = self.user,password = self.password , database = self.database, charset = self.charset) self.cursor = self.connet.cursor() # #删表 def dropTables(self): self.cursor.execute('''''drop table if exists aces''') print("删表") #建表 def createTables(self): self.cursor.execute('''''create table if not exists aces ( asin varchar(11) primary key not null, checked varchar(200));''') print("建表") #保存数据 def save(self,aceslist): self.cursor.execute("insert into aces ( asin, checked) values(%s,%s)", (aceslist[0],aceslist[1])) self.connet.commit() #判断元素是否已经在数据库里，在就返回true ,不在就返回false def is_exists_asin(self,asin): self.cursor.execute('select * from aces where asin = %s',asin) if self.cursor.fetchone() is None: return False return True # db =Database()

import urllib.parse import urllib.parse import urllib.request from queue import Queue import time import random import threading import logging import pymysql from bs4 import BeautifulSoup from local_data import Database #一个模块中存储多个类 AmazonSpeder , ThreadCrawl(threading.Thread), AmazonSpiderJob class AmazonSpider(): def __init__(self): self.db = Database() def randHeader(self): head_connection = ['Keep-Alive', 'close'] head_accept = ['text/html, application/xhtml+xml, */*'] head_accept_language = ['zh-CN,fr-FR;q=0.5', 'en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3'] head_user_agent = ['Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko', 'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36', 'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; rv:11.0) like Gecko)', 'Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/2008070208 Firefox/3.0.1', 'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070309 Firefox/2.0.0.3', 'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070803 Firefox/1.5.0.12', 'Opera/9.27 (Windows NT 5.2; U; zh-cn)', 'Mozilla/5.0 (Macintosh; PPC Mac OS X; U; en) Opera 8.0', 'Opera/8.0 (Macintosh; PPC Mac OS X; U; en)', 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/20080219 Firefox/2.0.0.12 Navigator/9.0.0.6', 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Win64; x64; Trident/4.0)', 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0)', 'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E)', 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Maxthon/4.0.6.2000 Chrome/26.0.1410.43 Safari/537.1 ', 'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E; QQBrowser/7.3.9825.400)', 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:21.0) Gecko/20100101 Firefox/21.0 ', 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.92 Safari/537.1 LBBROWSER', 'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; BIDUBrowser 2.x)', 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/3.0 Safari/536.11'] header = { 'Connection': head_connection[0], 'Accept': head_accept[0], 'Accept-Language': head_accept_language[1], 'User-Agent': head_user_agent[random.randrange(0, len(head_user_agent))] } return header def getDataById(self , queryId): #如果数据库中有的数据，直接返回不处理 if self.db.is_exists_asin(queryId): return req = urllib.request.Request(url="https://www.amazon.com/dp/"+str(queryId) , headers=self.randHeader()) webpage = urllib.request.urlopen(req) html = webpage.read() soup = BeautifulSoup(html, 'html.parser') content = soup.find_all("span" , id = "asTitle") # 加入一种判断，有的asin没有该定位， if len(content): # 非空 state = content[0].string else: # 列表为空，没有定位到 state = "other" print(queryId) print(state) self.db.save([queryId,state]) class ThreadCrawl(threading.Thread): #ThreadCrawl类继承了Threading.Thread类 def __init__(self, queue): #子类特有属性， queue FORMAT = time.strftime("[%Y-%m-%d %H:%M:%S]", time.localtime()) + "[AmazonSpider]-----%(message)s------" logging.basicConfig(level=logging.INFO, format=FORMAT) threading.Thread.__init__(self) self.queue = queue self.spider = AmazonSpider() #子类特有属性spider，并初始化，将实例用作属性 def run(self): while True: success = True item = self.queue.get() #调用队列对象的get()方法从队头删除并返回一个项目item try: self.spider.getDataById(item) #调用实例spider的方法getDataById(item) except : # print("失败") success = False if not success : self.queue.put(item) logging.info("now queue size is: %d" % self.queue.qsize()) #队列对象qsize()方法，返回队列的大小 self.queue.task_done() #队列对象在完成一项工作后，向任务已经完成的队列发送一个信号 class AmazonSpiderJob(): def __init__(self , size , qs): self.size = size # 将形参size的值存储到属性变量size中 self.qs = qs def work(self): toSpiderQueue = Queue() #创建一个Queue队列对象 for q in self.qs: toSpiderQueue.put(q) #调用队列对象的put()方法，在对尾插入一个项目item for i in range(self.size): t = ThreadCrawl(toSpiderQueue) #将实例用到一个类的方法中 t.setDaemon(True) t.start() toSpiderQueue.join() #队列对象，等到队列为空，再执行别的操作

from amazon_s import AmazonSpiderJob #从一个模块中导入类 import pymysql import pandas as pd from local_data import Database if __name__ == '__main__': #初次跑程序的时候，需要删除旧表，然后新建表，之后重启再跑的时候需要注释 #---------------------- db = Database() db.dropTables() db.createTables() #--------------------------- df = pd.read_excel("ASIN检查_viogico_1108.xlsx") # print(df.info()) qs = df["asin1"].values print(qs) print(len(qs)) amazonJob = AmazonSpiderJob(8, qs) amazonJob.work()

相关阅读