爬取淘宝商品信息demo

最新推荐文章于 2024-08-09 10:04:21 发布

John.liu_Test

最新推荐文章于 2024-08-09 10:04:21 发布

阅读量384

点赞数 1

分类专栏： selenium

本文链接：https://blog.csdn.net/lystest/article/details/103868429

版权

selenium 专栏收录该内容

12 篇文章 0 订阅

订阅专栏

from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
import time


dr = webdriver.Chrome()
# dr = webdriver.PhantomJS()


def check_login(times):
    """
    校验登录是否成功
    :param times: 超时时间，每秒检查一次
    :return:
    """
    n = 0
    while n <= times:
        try:
            check_login = dr.find_element_by_class_name("site-nav-user").text
            if check_login != "":
                print("恭喜用户：%s 登录成功" %str(check_login).strip())
                break
        except NoSuchElementException as msg:
            print("第%d次找不到元素" %n,msg)
            time.sleep(1)
        n += 1


def write_txt(key,pageNums):
    """
    写入csv文件
    :param key:关键字
    :param pageNums:最大页数
    :return:
    """
    with open("E://商品信息_%s.csv" % key, "w") as a:
        num = 1
        while num <= pageNums:
            time.sleep(1)
            # 商品价格
            sp_price = dr.find_elements_by_xpath("//div[@id='mainsrp-itemlist']//div[@class='items']/div/div[2]/div[1]/div[1]/strong")
            # 付款人数
            fk_num = dr.find_elements_by_xpath("//div[@id='mainsrp-itemlist']//div[@class='items']/div/div[2]/div[1]/div[2]")
            # 店铺名称
            shop_name = dr.find_elements_by_xpath("//div[@id='mainsrp-itemlist']//div[@class='items']/div/div[2]/div[3]/div[1]/a/span[2]")
            # 发货地
            sp_fhd = dr.find_elements_by_xpath("//div[@id='mainsrp-itemlist']//div[@class='items']/div/div[2]/div[3]/div[2]")
            # 商品标题
            sp_bt = dr.find_elements_by_xpath("//div[@id='mainsrp-itemlist']//div[@class='items']/div/div[2]/div[2]/a")
            for price in range(len(sp_price)):
                sp_info = "类别名称：,"+key\
                          + ",商品标题：,"+str(sp_bt[price].text).strip()\
                          + ",店铺名称：,"+shop_name[price].text\
                          + ",商品价格：,"+sp_price[price].text\
                          + ",付款人数：,"+fk_num[price].text\
                          + ",商品发货地：,"+sp_fhd[price].text\
                          + "\n"
                print(sp_info)
                a.write(sp_info)
            if num >= pageNums:
                print("当前为第%d页数据"%pageNums)
            else:
                # 点击翻页
                print("正在第%d次点击下一页" %num)
                dr.find_element_by_xpath("//ul[@class='items']/li[3]").click()
            num += 1


def go():
    dr.get("https://www.taobao.com/")
    dr.maximize_window()
    time.sleep(1)
    dr.find_element_by_xpath("//a[text()='亲，请登录']").click()
    time.sleep(3)
    # val = input("输入查询的关键字：")
    # 校验登录
    check_login(1000)
    with open("E://Keywords.txt") as readKey:
        read_list = readKey.readlines()
        for key in read_list:
            print("当前关键字:",key)
            val = key.strip("\n")
            dr.find_element_by_id("q").send_keys(val)
            time.sleep(1)
            dr.find_element_by_xpath("//button[@type='submit' and text()='搜索']").click()
            time.sleep(1)
            # 搜索结果页数
            get_page_num = dr.find_element_by_xpath("//ul[@class='items']/li[2]").text
            page_num = str(get_page_num).split("/")[1]
            print("当前页数：",page_num)
            if int(page_num) > 10:
                print("当前页数大于10")
                write_txt(val,10)
            else:
                print("当前页数小于10")
                write_txt(val,int(page_num))


go()
time.sleep(3)
dr.quit()