爬取1688网站

最近在学习爬虫,写了一个爬取淘宝1688数据的爬虫,使用selenium与BeautifulSoup,现在简单记录一下

# -*- coding: utf-8 -*-
from selenium import webdriver
from selenium.webdriver.support import wait
from selenium.webdriver.support import expected_conditions as ec
from selenium.webdriver.common.by import By
from selenium.webdriver import ActionChains
from bs4 import BeautifulSoup
from hashlib import md5
import requests
import time
import pymysql
import re
import os
import random
import traceback
class Item():
    img_url=""
    title=""
    money=""
    year=""
    consigment_in_30=""
    head_turn=""
    the_type=""
    factory_name=""
    price=""
    houmiao=""
    xiangying=""
    fahuo=""
class get1688():
    def __init__(self,name):
        self.name=name
        self.begin()
    def begin(self):
        self.getHTML()
    def getHTML(self):
        driver=webdriver.Chrome()
        driver.get("https://www.1688.com")
        driver.maximize_window()
        try:
            input_tag=driver.find_element_by_id("home-header-searchbox")
            input_tag.send_keys(self.name)
            search=driver.find_element_by_xpath('//*[@id="app"]/div/div[3]/section/div[2]/div/div/div/form/fieldset/div/div[2]/button')
            time.sleep(1)
            search.click()
            num=int(driver.find_element_by_xpath('//*[@id="fui_widget_5"]/span/a[9]').text)
            for index in range(num):
                try:
                    driver.find_element_by_xpath('//*[@id="s-module-overlay"]/div[2]/div/div[2]').click()
                except:
                    pass
                driver.execute_script('window.scrollTo(0, document.body.scrollHeight)')
                w=wait.WebDriverWait(driver,15)
                w.until(ec.presence_of_element_located((By.CSS_SELECTOR,'#offer60')))
                print("共%s页,当前正在爬取第%s页"%(str(num),str(index+1)))
                result=[]
                
                lis=driver.find_elements_by_css_selector(".sm-offer-item.sw-dpl-offer-item")
                i=1
                for li in lis:
                    #将鼠标悬停在商品上才可以显示所有属性值
                    ActionChains(driver).move_to_element(driver.find_element_by_id('offer'+str(i))).perform()
                    time.sleep(random.randint(1,3))
                    HTML=driver.find_element_by_id('offer'+str(i)).get_attribute('innerHTML')
                    time.sleep(random.randint(1,3))
                    item=self.parseOneItem(HTML)
                    if item != None:
                        result.append(item)
                    i+=1
                    if i % 30 == 0:
                        self.pipeMysql(result)
                print("第%s页爬取成功"%(str(index+1)))
                driver.find_element_by_xpath('//*[@id="fui_widget_5"]/span/a[10]').click()
                time.sleep(3)
        except:
            fo=open("D:"+os.path.sep+"log.txt",'a')
            fo.write(traceback.format_exc())
            fo.write("\n\n")
            fo.close()
        finally:
            driver.close()
            driver.quit()
    #解析一个商品      
    def parseOneItem(self,html):
        soup=BeautifulSoup(html,'lxml')
        try:
            img_tag=soup.find('div',class_="sm-offer-photo sw-dpl-offer-photo hover").find('a').find('img')
            img_url=img_tag.get("src")
            title=img_tag.get('alt')
        except:
            return None
        try:
            money_in_30day=str(soup.find('span',class_="sm-offer-trade sw-dpl-offer-trade sm-offer-tradeBt").find('em').string)
        except:
            money_in_30day=str(soup.find('span',class_="sm-offer-priceNum sw-dpl-offer-priceNum").get("title"))
        try:
            year=soup.find('a',attrs={"title":"阿里巴巴建议您优先选择诚信通会员"}).string
        except:
            year="暂无记录"
        try:
            consigment_in_30=str(soup.find("span",class_="sm-offer-localservice-num").string)
        except:
            consigment_in_30="暂无记录"
        try:
            head_turn=soup.find("div",class_='sm-widget-offershopwindowshoprepurchaserate').find_all('span')[2].string
            if len(head_turn) > 10:
                head_turn="暂无"
        except:
            head_turn='暂无'

        the_type=str(soup.find("div",class_="sm-widget-offershopwindowshoprepurchaserate").find('i').string)
        if len(the_type) <=0:#            
            the_type="暂无"
        if the_type == None:
            the_type='暂无'
        factory_name=soup.find("a",attrs={"t-click-item":"com"}).get("title")
        price=""
        for price_span in soup.find('div',class_="imgofferresult-hoverBlock").select("div.s-widget-offershopwindowdealinfo.sm-offer-dealInfo")[0].find_all("span"):
            temp=str(price_span.find("em").get("title")+":"+price_span.find('i').get("title")+";")
            price+=temp
        try:
            smoffs=soup.find('div',class_="sm-offer-bsr-info").find_all('div',class_="sm-offer-bsr-row")
            houmiao=smoffs[0].find('span',class_="sm-offer-bsr-sub").string+":"+smoffs[0].find('span',class_="sm-offer-bsr-value-red").string
            xiangying=smoffs[1].find('span',class_="sm-offer-bsr-sub").string+":"+smoffs[0].find('span',class_="sm-offer-bsr-value-red").string
            fahou=houmiao=smoffs[2].find('span',class_="sm-offer-bsr-sub").string+":"+smoffs[0].find('span',class_="sm-offer-bsr-value-red").string
        except:
            return None
        item=Item()
        item.img_url=img_url
        item.title=title
        item.money=money_in_30day
        item.year=year
        item.consigment_in_30=consigment_in_30
        item.the_type=the_type
        item.factory_name=factory_name
        item.price=price
        item.houmiao=houmiao
        item.xiangying=xiangying
        item.fahuo=fahou
        item.head_turn=head_turn
        return item
    #存储进入mysql,host等信息填自己的
    def pipeMysql(self,items,host="*",user="*",passwd="*",database="1688"):
        
        conn=pymysql.connect(host,user,passwd,database)
        cursor=conn.cursor()
        self.table_exists(cursor,conn,self.name)
        i=0
        for item in items:
            if self.table_exists(cursor,conn,self.name):
                if not os.path.exists("D:"+os.sep+"img_1688"+os.path.sep+self.name):
                    os.makedirs("D:"+os.sep+"img_1688"+os.path.sep+self.name)
                #去重
                new_md5 = md5()
                new_md5.update((item.img_url+self.name).encode(encoding='utf-8'))
                filepath="D:"+os.sep+"img_1688"+os.path.sep+self.name+os.path.sep+new_md5.hexdigest()+".jpg"
                if os.path.exists(filepath):
                    return
                fo=open(filepath,'bw')
                response=requests.get(item.img_url)
                fo.write(response.content)
                fo.close()
                sql="insert into "+self.name+" values(%(img_url)s,%(title)s,%(money)s,%(head_turn)s,%(year)s,%(consigment_in_30)s,%(the_type)s,%(factory_name)s,%(price)s,%(houmiao)s,%(xiangying)s,%(fahuo)s)"
                cursor.execute(sql,{
                    "img_url":filepath,
                    "title":item.title,
                    "money":item.money,
                    "head_turn":item.head_turn,
                    "year":item.year,
                    "consigment_in_30":item.consigment_in_30,
                    "the_type":item.the_type,
                    "factory_name":item.factory_name,
                    "price":item.price,
                    "houmiao":item.houmiao,
                    "xiangying":item.xiangying,
                    "fahuo":item.fahuo  
                })
                if i%5 ==0:
                    conn.commit()
        cursor.close()
        conn.commit()
        conn.close() 
    #判断表是否存在,不存在则新建
    def table_exists (self,cursor,conn,table):
        sql = "show tables"
        cursor.execute(sql)
        tables = cursor.fetchall()
        tables_list = re.findall('(\'.*?\')',str(tables))
        tables_list = [re.sub("'",'',each)for each in tables_list]
        #不存在新建表
        if table not in tables_list:
            try:
                sql = '''
                        CREATE TABLE `'''+self.name+'''`  (
                        `pic_url` varchar(1000),
                        `商品名称` varchar(2000),
                        `30天成交额` varchar(255),
                        `客户回头率` varchar(255),
                        `店铺成立年份` varchar(255),
                        `30天平均发货速度` varchar(255),
                        `经营类型` varchar(255),
                        `店铺名称` varchar(500),
                        `区段价格` varchar(1000),
                        `货描` varchar(255),
                        `响应` varchar(255),
                        `发货` varchar(255));
                      '''
                cursor.execute(sql)
                conn.commit()
            except:
                fo=open("D:"+os.path.sep+"log.txt",'a')
                fo.write(traceback.format_exc())
                fo.write("\n\n")
                fo.close()
                return False
        return True
key=input("查询内容为:")
get1688(key)
  • 0
    点赞
  • 4
    收藏
    觉得还不错? 一键收藏
  • 2
    评论
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值