【Python爬虫】爬取淘宝商品数据——新手教程

keywords = '高跟鞋'
while 1:
 try:
        driver = webdriver.Chrome()
        break
 except:
        time.sleep(1)
driver.get('https://www.taobao.com/')
page = search_product(keywords)

with open('data.csv','a',newline='') as filecsv:
    csvwriter = csv.writer(filecsv,delimiter = ',')
    csvwriter.writerow(['商品名称','商品价格','付款人数','店铺','发货地址'])
    get_product()
    page_num = 1

while page_num != page:
        print('正在爬取第'+str(page_num)+'页数据')
        driver.get('https://s.taobao.com/search?q='+keywords+'&imgfile=&commend=all&ssid=s5-e&search_type=item&sourceId=tb.index&spm=a21bo.2017.201856-taobao-item.2&ie=utf8&initiative_id=tbindexz_20170306&bcoffset=3&ntoffset=3&p4ppushleft=1%2C48&s='+str(page_num*44))
        driver.implicitly_wait(2)                      #浏览器等待 因为爬取速度过快
        driver.maximize_window()                       #浏览器最大化
        get_product()
        page_num = page_num+1
 
def get_product():
    divs = driver.find_elements_by_xpath('//div[@class="items"]/div[@class="item J_MouserOnverReq  "]')
    product = {}
    product_all = {}
 with open('data.csv','a',newline='') as filecsv:
        csvwriter = csv.writer(filecsv,delimiter = ',')
 for id_product,div in enumerate(divs):
            product['info'] = div.find_elements_by_xpath('.//div[@class="row row-2 title"]')[0].text
            product['price'] = div.find_elements_by_xpath('.//div[@class="price g_price g_price-highlight"]/strong')[0].text+'元'
            product['Number_of_people'] = div.find_elements_by_xpath('.//div[@class="deal-cnt"]')[0].text
            product['address'] = div.find_elements_by_xpath('.//div[@class="location"]')[0].text
            product['Shop'] = div.find_elements_by_xpath('//div[@class="shop"]/a/span[2]')[0].text
 #   with open('data.csv','a',newline='') as filecsv:
 #       csvwriter = csv.writer(filecsv,delimiter = ',')
            csvwriter.writerow([product['info'],product['price'],product['Number_of_people'],product['Shop'],product['address']])