python爬取新浪股票数据—绘图【原创分享】

目标：不做蜡烛图，只用折线图绘图，绘出四条线之间的关系。

注：未使用接口，仅爬虫学习，不做任何违法操作。

 """
     新浪财经，爬取历史股票数据
 """

 # -*- coding:utf-8 -*-

 import numpy as np
 import urllib.request, lxml.html
 from urllib.request import urlopen
 from bs4 import BeautifulSoup
 import re, time
 import matplotlib.pyplot as plt
 from datetime import datetime
 # 绘图显示中文设置
 plt.rcParams['font.sans-serif'] = ['SimHei']
 plt.rcParams['axes.unicode_minus'] = False

 # 公共模块，请求头信息
 def public(link):
     r = urllib.request.Request(link)

     ug = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0'

     r.add_header('User-Agent', ug)

     cookie = "SUB=_2AkMsqZjif8NxqwJRmfkRxG7nZYpzyg_EieKa9Wk5JRMyHRl-yD83qkJatRB6Bym2DDqPE870e3uMsySIjHjrMbMNxNqk; " \
              "SUBP=0033WrSXqPxfM72-Ws9jqgMF55529P9D9WFXmxLGpAG5k05lCJw6qgYe; " \
              "SINAGLOBAL=172.16.92.24_1542789082.401113; " \
              "Apache=172.16.92.24_1542789082.401115; UOR=www.baidu.com,blog.sina.com.cn,; " \
              "ULV=1542789814434:1:1:1:172.16.92.24_1542789082.401115:; U_TRS1=000000d1.1f4d3546.5bf53673.955fa32e; " \
              "U_TRS2=000000d1.1f593546.5bf53673.736853cc; FINANCE2=661413ac85cadaab72ec7e3d842d6a3a; _s_upa=1"

     r.add_header("Cookie", cookie)

     html = urllib.request.urlopen(r, timeout=500).read()

     bsObj = BeautifulSoup(html, "lxml")  # 将html对象转化为BeautifulSoup对象

     return bsObj

 # 获取股票价格
 def shares_price(code, year, quarter):
     link = "http://money.finance.sina.com.cn/corp/go.php/vMS_MarketHistory/stockid/%s.phtml?year=%d&jidu=%d" % (code, year, quarter)

     bsObj = public(link)
     # print(bsObj)

     a = 0
     # date_list为日期列表，open_list为开盘价列表，high_list为最高价列表，close_list为收盘价列表，low_list为最低价列表
     price_list, date_list, open_list, high_list, close_list, low_list = [], [], [], [], [], []
     # 获取股票信息
     jpg_title = re.findall("(.*?\))", bsObj.title.text)

     prices_bs = bsObj.find_all(name='div', attrs={"align": 'center'})
     # 获取并处理价格信息
     for price_bs in prices_bs:
         # 去除空格
         price_bs_1 = price_bs.text.replace("\n\r\n\t\t\t", "")
         price_bs_2 = price_bs_1.replace("\t\t\t\n", "")

         # 6个字符串为一个列表
         if a != 6:
             price_list.append(price_bs_2)
             a = a + 1
         else:
             date_list.append(price_list[0])
             open_list.append(price_list[1])
             high_list.append(price_list[2])
             close_list.append(price_list[3])
             low_list.append(price_list[4])
             a = 0
             price_list = []
     # 删除列表头
     for b in (date_list, open_list, high_list, close_list, low_list):
         b.pop(0)

     # 全部倒序排列（由日期远到近，从左到右排列）
     for c in (date_list, open_list, high_list, close_list, low_list):
         c.reverse()

     return date_list, open_list, high_list, close_list, low_list, jpg_title

 # 输入股票代码，年份，季度
 code = ""
 year = ""
 quarter = 4
 # 以下为手动输入模式，因调试方便默认上面固定模式。
 # code = input("code：")  # 002925
 # year = input("year：")    # 2018
 # quarter = int(input("quarter："))

 # 列表字符串转为数值date
 x = [datetime.strptime(d, '%Y-%m-%d').date() for d in shares_price(code, int(year), quarter)[0]]
 # 将爬取的数据（字符串）转化为浮点型
 open_list = [float(i) for i in shares_price(code, int(year), quarter)[1]]
 high_list = [float(i) for i in shares_price(code, int(year), quarter)[2]]
 close_list = [float(i) for i in shares_price(code, int(year), quarter)[3]]
 low_list = [float(i) for i in shares_price(code, int(year), quarter)[4]]

 # 线条设置
 plt.plot(x, open_list, label='open', linewidth=1, color='red', marker='o', markerfacecolor='blue', markersize=2)
 plt.plot(x, high_list, label='high', linewidth=1, color='green', marker='o', markerfacecolor='blue', markersize=2)
 plt.plot(x, close_list, label='close', linewidth=1, color='blue', marker='o', markerfacecolor='blue', markersize=2)
 plt.plot(x, low_list, label='low', linewidth=1, color='black', marker='o', markerfacecolor='blue', markersize=2)

 # 取数列最大数值与最小值做图表的边界值。
 plt.ylim(min(low_list)-1, max(high_list)+1)
 plt.gcf().autofmt_xdate()  # 自动旋转日期标记

 # 打印表头
 plt.xlabel('time')
 plt.ylabel('price')
 # shares_price(code, int(year), quarter)[5][0]为title中的股票名称与代码
 plt.title('gp_1_{0}.jpg'.format(shares_price(code, int(year), quarter)[5][0]))
 plt.legend()
 plt.show()

效果如下：

是不是有另一种看法的感觉？如：黑线下跌后向上的第一个大拐点为买入点。