淘宝反爬策略：
使用selenium的webdriver模块伪装成浏览器，然后再用
ActionChains模块模拟整个滑动滑块解锁的过程，成功登陆淘宝账号，抓取数据并写入excel。
from selenium import webdriverfrom selenium.webdriver import ActionChainsimport timeimport reimport xlwtbrowser = webdriver.Chrome()browser.get("/search?q=%E5%A6%AE%E7%BB%B4%E9%9B%85") #q后面是要搜索的产品名称#输入账号browser.find_element_by_xpath('//*[@id="fm-login-id"]').send_keys('手机号xxx')time.sleep(1.5)#输入密码browser.find_element_by_xpath('//*[@id="fm-login-password"]').send_keys('密码xxx')time.sleep(2)#滑块验证button = browser.find_element_by_id('nc_1_n1z')action = ActionChains(browser)action.click_and_hold(button).perform()action.reset_actions()action.move_by_offset(258, 0).perform()time.sleep(1.5)#点击登录browser.find_element_by_xpath('//*[@id="login-form"]/div[4]/button').click()time.sleep(3)#获取源代码data = browser.page_source# print(data)#获取总页数p_pages = '"pager":{"pageSize":.*?"totalPage":(.*?),"currentPage"'pages = int(re.findall(p_pages,data,re.S)[0])#获取全部源代码datas=[]datas.append(data)for i in range(2):#若要抓取全部可以换成pages，这里只抓取前两页browser.find_element_by_xpath('//*[@id="mainsrp-pager"]/div/div/div/ul/li[8]/a').click()time.sleep(5)data = browser.page_sourcedatas.append(data)time.sleep(3)alldata = ''.join(datas)#关闭浏览器窗口browser.quit()#抓取的内容n_name='<span class="H">妮维雅</span>(.*?)</a>'name = re.findall(n_name,alldata,re.S)p_price = '<div class="row row-2 title">.*?trace-price="(.*?)" trace-pid=.*?">'price = re.findall(p_price,alldata,re.S)p_sales = '"view_sales":"(.*?)"'sales = re.findall(p_sales,alldata,re.S)p_detail_url='"detail_url":"(.*?)"'detail_url=re.findall(p_detail_url,alldata,re.S)data_list_content = []content=[]for i in range(len(name)):content = name[i].strip()+','+price[i]+','+sales[i]+','+'http:'+detail_url[i].encode('latin-1').decode('unicode_escape')content =content.split(',')data_list_content.append(content)print(data_list_content)#将抓取内容保存至excelwork_book = xlwt.Workbook(encoding='utf-8') #创建excel表格sheet = work_book.add_sheet('NWY') #创建一个sheetheads = ['name', 'price', 'sales', 'detail_url'] #写入表头for i in range(len(heads)):sheet.write(0, i, heads[i])#写入抓取的具体内容i=1for content in data_list_content:j=0for cont in content:sheet.write(i, j, cont)j += 1i += 1work_book.save('nwy.xls')
