商品详情页的促销价

Egの天猫的任一商品详情页为入口，看到的商品促销价或淘宝价：

 

from requestium import Session,Keys

#from selenium.webdriver.common.action_chains import ActionChains

#滑块总显示出错了刷新：改用免安装版Chrome或火狐

options={'arguments':['disable-infobars',],

    'experimental_options':{'prefs':{'profile.managed_default_content_settings.images':2}},

    'binary_location':r'D:\Program Files\Browser\ChromeQuic\\chrome.exe'}

 

def loginByBrowser():

    driver.get('https://login.tmall.com/')

    loginFrame=css('#J_loginIframe')

    loginFrame.send_keys(Keys.TAB,Keys.TAB,Keys.TAB,Keys.ENTER,

        username,Keys.TAB,pwd,Keys.ENTER)

    try:

        css('#J_Logout')

    except:

        input('浏览器端成功处理滑块验证码后，在本句句尾任敲一字母：')

        # source=css('#nc_1_n1z')

        # action=ActionChains(driver)

        # action.click_and_hold(source).perform()

        # for x in range(10):

        #     action.move_by_offset(5,0).perform()

        # action.release()

        loginFrame.send_keys(Keys.SHIFT+Keys.TAB)

        loginFrame.send_keys(pwd,Keys.ENTER)

 

def getGoodsDetail(id='563211819596'):

    driver.get(f'https://detail.tmall.com/item.htm?id={id}')

    促销价=css('#J_PromoPrice .tm-price').text

    月销量=css('.tm-ind-sellCount .tm-count').text

    累计评价=css('#J_ItemRates .tm-count').text

    库存=css('#J_EmStock').text

    print(促销价,月销量,累计评价,库存,sep='；')

 

if __name__ == '__main__':

    username='用户名'

    pwd='密码'

    driver=Session('C:/Program Files/Python36/chromedriver','chrome',5,options).driver

    css=driver.ensure_element_by_css_selector

 

    loginByBrowser()

 

    goodsIDs=True

    while goodsIDs:

        goodsIDs=input('换掉下行待查询的各商品id的列表后回车：')

        goodsIDs=['563211819596',]

        try:

            for id in goodsIDs:

                getGoodsDetail(id)

        except:

            break

    driver.quit()

****************************************分割线****************************************

Egの粤偗偗考各考区的职位报名统计：

 

import os,requests,json,time,pandas as pd

from urllib.parse import parse_qs

 

def spider(region):

    regionID,num=regions[region].split(';')

    data=f'bfa001=201801&bab301={regionID}&page=1&rows={num}&sort=aab119&order=asc'

    data={k: v[0] for k, v in parse_qs(data).items()}

    url='http://ggfw.gdhrss.gov.cn/gwyks/exam/details/spQuery.do'

    headers={'User-Agent':'Mozilla/5.0 Baiduspider+ Chrome/64',

        'Content-Type':'application/x-www-form-urlencoded; charset=UTF-8',

        'Cookie':'JSESSIONID=vE9CvsoJTgJx4mx6w2FPaBKzJbovacHcWPWvQU8TvXldq4kc5ted!-447929663'}

    response=requests.post(url,headers=headers,data=data)

    response.encoding=response.apparent_encoding

    return response.json()['rows']

 

def parse(rows):

    jobs=[]

    for job in rows:

        jobs.append((job['aab004'],job['bfe3a4'],job['bfe301'],job['aab119']))

    tjsj=time.strftime('%Y-%m-%d %H:%M',time.localtime(int(rows[0]['aae036']/1000)))

    df=pd.DataFrame(jobs,columns=['招考单位','招考职位','职位代码','缴费人数'])

    df['统计时间']=tjsj

    df.to_csv(f'D:/公招/报名统计.csv',index=False,mode='a+',encoding='utf-8-sig')

 

def main(region):

    rows=spider(region)

    parse(rows)

 

if __name__ == '__main__':

    regions={'广州':'01;294','深圳':'02;133','珠海':'03;120','汕头':'04;519','佛山':'05;246',

        '韶关':'06;488','河源':'07;493','梅州':'08;500','惠州':'09;355','汕尾':'10;309',

        '东莞':'11;177','中山':'12;178','江门':'13;659','阳江':'14;219','湛江':'15;590',

        '茂名':'16;281','肇庆':'17;585','清远':'18;366','潮州':'19;274','揭阳':'20;354',

        '云浮':'21;302','省直':'99;1033'}

    for region in regions:

        main(region)

        time.sleep(2)

    #regionID,num=regions['佛山'].split(';')

    #main()