from selenium import webdriver
from lxml import etree
import json
import os
import timedef write_to_file(content,p_name):new_time = time.strftime('%Y%m%d')with open('../20190708期货数据/'+new_time+p_name+'.txt', 'a', encoding='utf-8') as f:f.write(json.dumps(content, ensure_ascii=False) + '\n')f.close()def get_html(url,s_name,p_Name):try:driver.get(url=url)input0 = driver.find_element_by_id('futures_exchange')input0.send_keys(s_name)input1 = driver.find_element_by_id('futures_variety')input1.send_keys(p_Name)# 选择日期# driver.execute_script("arguments[0].value=arguments[1]", driver.find_element_by_id("inputDate"),#                       "2019-07-08")input3 = driver.find_element_by_id('btnSearch')time.sleep(1)input3.click()time.sleep(1)html = driver.page_sourcereturn htmlexcept:print('没能打开浏览器')return Nonedef parse_one_page(html):et = etree.HTML(html)ls1,ls2,ls3,ls4,ls5,ls6,ls7,ls8,ls9 = [],[],[],[],[],[],[],[],[]# 成交量龙虎榜title01 = et.xpath("//div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@class='IFcb1'][2]/div[@class='IFtit']/text()")ls1.append(title01)title11 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@class='IFcb1'][2]/div[@class='IFUlDiv']/ul[1]/li[@class='IFbb']/span/text()")ls1.append(title11)content1 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@class='IFcb1'][2]/div[@class='IFUlDiv']/ul[@id='ulCjl']/li//text()")for i1 in range(0, len(content1), 4):ls1.append( content1[i1:i1 + 4])# 多头持仓龙虎榜title02 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@class='IFcb2'][3]/div[@class='IFtit']/text()")ls2.append(title02)title12 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@class='IFcb2'][3]/div[@class='IFUlDiv']/ul[1]/li[@class='IFbb']/span/text()")ls2.append(title12)content2 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@class='IFcb2'][3]/div[@class='IFUlDiv']/ul[@id='ulDtcc']/li//text()")for i2 in range(0, len(content2), 4):ls2.append(content2[i2:i2 + 4])# 空头持仓龙虎榜title03 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@class='IFcb2'][4]/div[@class='IFtit']/text()")ls3.append(title03)title13 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@class='IFcb2'][4]/div[@class='IFUlDiv']/ul[1]/li/span/text()")ls3.append(title13)content3 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@class='IFcb2'][4]/div[@class='IFUlDiv']/ul[@id='ulKtcc']/li//text()")for i3 in range(0, len(content3), 4):ls3.append(content3[i3:i3 + 4])# 净多头龙虎榜title04 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb1'][1]/div[@class='IFtit']/text()")ls4.append(title04)title14 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb1'][1]/div[@class='IFUlDiv']/ul[1]/li/span/text()")ls4.append(title14)content4 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb1'][1]/div[@class='IFUlDiv']/ul[@id='ulJdt']/li//text()")for i4 in range(0, len(content4), 4):ls4.append(content4[i4:i4 + 4])# 多头增仓龙虎榜title05 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb2'][1]/div[@class='IFtit']/text()")ls5.append(title05)title15 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb2'][1]/div[@class='IFUlDiv']/ul[1]/li[@class='IFbb']/span/text()")ls5.append(title15)content5 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb2'][1]/div[@class='IFUlDiv']/ul[@id='ulDtzc']/li//text()")for i5 in range(0, len(content5), 4):ls5.append(content5[i5:i5 + 4])# 多头减仓龙虎榜title06 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb2'][2]/div[@class='IFtit']/text()")ls6.append(title06)title16 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb2'][2]/div[@class='IFUlDiv']/ul[1]/li/span/text()")ls6.append(title16)content6 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb2'][2]/div[@class='IFUlDiv']/ul[@id='ulDtjc']/li//text()")for i6 in range(0, len(content6), 4):ls6.append(content6[i6:i6 + 4])# 净空头龙虎榜title07 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb2'][2]/div[@class='IFtit']/text()")ls7.append(title07)title17 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb2'][2]/div[@class='IFUlDiv']/ul[1]/li/span/text()")ls7.append(title17)content7 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb2'][2]/div[@class='IFUlDiv']/ul[@id='ulDtjc']/li//text()")for i7 in range(0, len(content7), 4):ls7.append(content7[i7:i7 + 4])# 空头增仓龙虎榜title08 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb2'][3]/div[@class='IFtit']/text()")ls8.append(title08)title18 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb2'][3]/div[@class='IFUlDiv']/ul[1]/li/span/text()")ls8.append(title18)content8 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb2'][3]/div[@class='IFUlDiv']/ul[@id='ulKtzc']/li//text()")for i8 in range(0, len(content8), 4):ls8.append(content8[i8:i8 + 4])#空头减仓龙虎榜title09 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb2'][4]/div[@class='IFtit']/text()")ls9.append(title09)title19 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb2'][4]/div[@class='IFUlDiv']/ul[1]/li/span/text()")ls9.append(title19)content9 = et.xpath("/html/body/div[@id='page']/div[@class='main']/div[@class='framecontent']/div[@class='sitebody']/div[@class='maincont']/div[@class='IFcontentBox']/div[@class='content']/div[2]/div[@id='mainContent']/div[@id='otherList']/div[@class='IFcb2'][4]/div[@class='IFUlDiv']/ul[@id='ulKtjc']/li//text()")for i9 in range(0, len(content9), 4):ls9.append(content9[i9:i9 + 4])return [ls1,ls2,ls3,ls4,ls5,ls6,ls7,ls8,ls9]def Main():Date = {'上海期货交易所':['沪银','沪铝','沪金','沥青','沪铜','燃油','热卷','镍','沪铅','螺纹钢','橡胶','锡','纸浆','沪锌'],'大连商品期货交易所':['豆一','豆二','玉米','玉米淀粉','乙二醇','铁矿石','焦炭','鸡蛋','焦煤','塑料','豆粕','棕榈','聚丙烯','PVC','豆油'],'郑州商品交易所':['郑煤','PTA','白糖','锰硅','硅铁','菜籽','菜粕','普麦','菜油','甲醇','晚籼','粳稻','玻璃','棉纱','红枣','郑棉','苹果']}for key,value in Date.items():for p in value:url = 'http://data.eastmoney.com/futures/dl/data.html'html = get_html(url,key,p)print('--- 正在解析网站 ---')try:ls = parse_one_page(html)for i in ls:for j in i:write_to_file(j,p)print(p,"---写入成功---")except Exception:print('爬虫出错了')if __name__ == '__main__':while True:n = time.strftime('%H:%M:%S')print(n)time.sleep(1)if n == "16:31:00":path = 'D:\chromedriver\chromedriver.exe'driver = webdriver.Chrome(path)if os.path.exists('20190708期货数据') is False:new_time = time.strftime('%Y%m%d')os.mkdir('../'+'20190708期货数据')Main()os.rename('../20190708期货数据',r'D:\Code\Spider\Date\期货数据\\'+new_time+'20190708期货数据' )driver.close()break

爬去东方财富网龙虎榜(wechat:15353378609)相关推荐

  1. 爬取东方财富网的部分股票信息(2)

    爬取东方财富网的部分股票信息(2) 目标:爬取东方财富网的部分股票的名称.代码.涨跌幅.融资余额.融资融券余额.股东户数 编程语言:Python 3.7 开发IDE:Visual Studio 201 ...

  2. 爬取东方财富网的部分股票信息(1)

    爬取东方财富网的部分股票信息(1) 目标:爬取东方财富网的部分股票的名称.代码.涨跌幅.融资余额.融资融券余额.股东户数 编程语言:Python 3.7 开发IDE:Visual Studio 201 ...

  3. 使用python爬取东方财富网机构调研数据

    最近有一个需求,需要爬取东方财富网的机构调研数据.数据所在的网页地址为: 机构调研 网页如下所示: 可见数据共有8464页,此处不能直接使用scrapy爬虫进行爬取,因为点击下一页时,浏览器只是发起了 ...

  4. [Python爬虫]爬取东方财富网公司公告需要注意的几个问题

    在上一篇文章中,以爬取东方财富网公司公告为例,介绍了如何爬取利用ajax加载的网页,以及如何模拟翻页.但是,在实际应用的过程中,发现了一些问题.接下来就来一一分析解决. 问题一.公告数量过多,后面的公 ...

  5. 爬取东方财富网股票行情数据和资讯

    爬取东方财富网股票行情数据和资讯 这个需求源于我的一个练手项目 本篇博客参考:https://zhuanlan.zhihu.com/p/50099084 该博客介绍的东西本博客不做论述 使用技术: 语 ...

  6. python爬取东方财富网资金流向数据(在本地生成csv文件)

    今天我们来试着用python爬取东方财富网资金流向的表格数据. 第一步:程序及应用的准备 首先我们需要安装selenium库,使用命令pip install selenium;然后我们需要下载对应的c ...

  7. 利用python爬取东方财富网股吧评论并进行情感分析(一)

    利用python爬取东方财富网股吧评论(一) python-东方财富网贴吧文本数据爬取 分享一下写论文时爬数据用到的代码,有什么问题或者改善的建议的话小伙伴们一起评论区讨论.涉及内容在前人的研究基础之 ...

  8. 爬虫学习笔记(用python爬取东方财富网实验)

    参考文章以及视频:(11条消息) 爬虫实战 | 爬取东方财富网股票数据_简说Python的博客-CSDN博客.手把手教你从东方财富网上获取股票数据_哔哩哔哩_bilibili.[Python爬虫案例] ...

  9. python爬虫爬取东方财富网股票走势+一些信息

    一.目标 我们的目标是爬取东方财富网(https://www.eastmoney.com/)的股票信息 我的目标是爬取100张股票信息图片 经过实际测试我的爬取范围为000001-000110,000 ...

最新文章

  1. 大数据安全事件警示:海量数据放哪才真正放心
  2. php逗号为什么比点号快,[PHP]
  3. LPC2103开发板I2C测试试验
  4. OGRE 学习小记 开发环境的配置
  5. 发现保存GIF格式后相素发生变化咋办
  6. np完全问题的例子_MIT开发光子算法,试图解决世界7大数学难题的“NP完全问题”...
  7. 如何将参数传递给setTimeout()回调?
  8. frameset ,iframe的使用
  9. 图书馆的uml概念类图怎么画_UML科普文,一篇文章掌握14种UML图
  10. bootstrap引入文件方法
  11. 高端程序员上班摸鱼指南
  12. VC++使用OD反汇编引擎(非BC做DLL或LIB包装)
  13. 简洁桌面(使用Windows自带的桌面整理功能)
  14. 普适计算的六大必备条件
  15. 使用Photoshop画一个圆锥体
  16. 【专题5: 硬件设计】 之 【30.案例三:碎纸机,DC-DC降压方法(电容降压原理)】
  17. 广东高中生多少人_广东2016高考五大变化 考生总人数73.3万
  18. NMOS的栅极充电过程
  19. 新产品、新特性、新生态丨一文回顾openGauss峰会云和恩墨分论坛150分钟的精彩...
  20. ec20 以太网_以太网光纤收发器有什么作用?

热门文章

  1. 【Scratch】青少年蓝桥杯_每日一题_11.25_小猫碰到黑块和白块
  2. Ubuntu 安装Docker 常用命令
  3. http://www.cvvision.cn/2888.html
  4. 天空灰蒙蒙的,心情有点像这天气
  5. SequoiaDB巨杉数据库成为唯一入选 “硅谷2016 大数据地形图”中国厂商, 企业级市场超越MongoDB等海外产品
  6. 借助ChatGPT自动生成PPT
  7. 2013上半年 系统集成项目管理工程师 下午试卷
  8. iOS-AFNetworking源码解析(五)
  9. 仿酒仙网的一款jQuery侧栏弹出导航栏特效
  10. Abp Wcf结合使用问题