刘瑞洋的实验报告（医药行业）

一、年报爬取、处理与下载

#爬取公司为【600080金花股份、600085同仁堂、600161天坛生物、600195中牧股份、600200江苏吴中、600201生物股份、600216浙江医药、600267海正药业、600276恒瑞医药、600351亚宝药业】


'################################一键下载年报##############################'
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.support import expected_conditions
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
import time
import pandas as pd
import re
from filter_url import filter_words,filter_date,start_end_10y,filter_nb_10y,prepare_hrefs_years
from download import download_pdf,download_pdfs,download_pdfs_codes

years = ['2022','2021','2020','2019','2018','2017','2016','2015','2014','2013']

def get_table_sse(code):
    browser = webdriver.Edge()
    browser.set_window_size(1550, 830)
    url = "http://www.sse.com.cn/disclosure/listedinfo/regular/"
    browser.get(url)
    time.sleep(3)
    browser.find_element(By.ID, "inputCode").click()
    browser.find_element(By.ID, "inputCode").send_keys(code)#'601919'
    selector = ".sse_outerItem:nth-child(4) .filter-option-inner-inner"
    browser.find_element(By.CSS_SELECTOR, selector).click()
    browser.find_element(By.LINK_TEXT,"年报").click()
    time.sleep(3)
    #
    css_selector = "body > div.container.sse_content > div > div.col-lg-9.col-xxl-10 > div > div.sse_colContent.js_regular > div.table-responsive > table"
    #
    element = browser.find_element(By.CSS_SELECTOR, css_selector)
    table_html = element.get_attribute('innerHTML')
    #
    fname = f'{code}.html'
    f = open(fname,'w',encoding='utf-8')
    f.write(table_html)
    f.close()
    #
    browser.quit()
#获取元素

        
def get_data(tr):
    p_td = re.compile('(.*?)',re.DOTALL)
    tds = p_td.findall(tr)
    #
    s = tds[0].find('>')+1
    e = tds[0].rfind('<')
    code = tds[0][s:e]
    #
    s = tds[1].find('>')+1
    e = tds[1].rfind('<')
    name = tds[1][s:e]
    #
    s = tds[2].find('href="')+6
    e = tds[2].find('.pdf"')+4
    href = 'http://www.sse.com.cn'+tds[2][s:e]
    s = tds[2].find('$(this))">')+10
    e = tds[2].find('')
    title = tds[2][s:e]
    #
    date = tds[3].strip()
    
    data = [code,name,href,title,date]
    return(data)

def parse_table(fname,save=True):
    f = open(fname,encoding='utf-8')
    html = f.read()
    f.close()
    #
    p = re.compile('(.+?)',re.DOTALL)
    trs = p.findall(html)
    #
    trs_new = []
    for tr in trs:
        if tr.strip()!='':
            trs_new.append(tr)
    #
    data_all = [get_data(tr) for tr in trs_new[1:]]
    
    df = pd.DataFrame({
            'code':[d[0] for d in data_all],
            'name':[d[1] for d in data_all],
            'href':[d[2] for d in data_all],
            'title':[d[3] for d in data_all],
            'date':[d[4] for d in data_all]
            })
    df = filter_nb_10y(df,keep_words=['年报','年度报告'],exclude_words=['摘要'],start='')  #将df处理掉摘要等
    tp = prepare_hrefs_years(df) #只留下链接和年份
    
    download_pdfs(tp[0],code,tp[1]) #下载pdf
    #
    if save:
        df.to_csv(f'{fname[0:-5]}.csv')
    return(df)
#解析html，获取df并处理掉摘要、只留下代码和链接，并一键下载年报
    

codes = ['600080','600085','600161','600195','600200','600201','600216','600267','600276','600351']



for code in codes:
    get_table_sse(code)
    fname = f'{code}.html'
    parse_table(fname,save=True)
#调用函数，一键下载所有年报
    
'############################下载年报代码定义##############################'
import requests
import os
import time


codes = ['600080','600085','600129','600161','600195 ','600196','600200','600201','600216','600222']

years = ['2022','2021','2020','2019','2018','2017','2016','2015','2014','2013']


def download_pdf(href,code,year):
    r = requests.get(href,allow_redirects=True)
    pdf_name = f'{code}_{year}.pdf'
    f = open(pdf_name,'wb')
    f.write(r.content)
    f.close()
    #
    r.close()

def download_pdfs(hrefs,code,years):
    for i in range(len(hrefs)):
        href = hrefs[i]
        year = years[i]
        download_pdf(href,code,year)
        time.sleep(30)
    return()
    
def download_pdfs_codes(list_hrefs,codes,list_years):
    for i in range(len(list_hrefs)):
        hrefs = list_hrefs[i]
        years = list_years[i]
        code = code[i]
        download_pdf(hrefs,code,years)
    return()

'###########################年报处理代码定义###############################'
import datetime

def filter_words(words,df,include=True):
    
    ls = []
    for word in words:
        if include:
            ls.append([word in f for f in df['title']])
        else:
            ls.append([word not in f for f in df['title']])
    index = []
    for r in range(len(df)):
        flag = not include
        for c in range(len(words)):
            if include:
                flag = flag or ls[c][r]
            else:
                flag = flag and ls[c][r]
        index.append(flag)
    df2 = df[index]
    return(df2)


def filter_date(start,end,df):
    date = df['date']
    v = [d>=start and d<=end for d in date]
    df_new = df[v]
    return(df_new)
    
def start_end_10y():
    dt_now = datetime.datetime.now()
    current_year = dt_now.year
    start = f'{current_year-9}-01-01'
    end = f'{current_year}-12-31'
    return((start,end))
    
def filter_nb_10y(df,
                  keep_words=['年报','年度报告','年度报告（修订版）'],
                  exclude_words=[['摘要']],
                  start=''):
    if start == '':
        start,end = start_end_10y()
    else:
        start_y = int(start[0:4])
        end = f'{start_y+9}-12-31'
    #
    df = filter_words(keep_words,df,include=True)
    df = filter_words(exclude_words,df,include=False)
    df = filter_date(start,end,df)
    return(df)
    
def prepare_hrefs_years(df):
    hrefs = df['href'].to_list()
    years = [int(d[:4])-1 for d in df['date']]
    return((hrefs,years))
  

结果

二、数据处理与筛选

2.1提取公司基础信息

# 利用file_name_walk找出pdf_data下所有文件的路径和文件名
import os

def file_name_walk(file_dir):
        '''
        定义一个返回文件所在的绝对路径和
        文件名的列表的函数
        '''
        file_path_lst = []
        for x in os.walk(file_dir):
                file_path_lst.append((x[0],x[2]))
        return file_path_lst

def get_target(doc,bounds =['公司简称','信息披露及备置地点']): 
        # 默认设置为首页页码
        start_pageno = 0
        # 获取上界页码
        for n in range(len(doc)):
            # texts = page.get_text()
            if (bounds[0] or bounds[0]) in doc[n].get_text():
                start_pageno = n
                break
        return start_pageno

def get_subtxtt(doc,bounds=('公司代码','信息披露及备置地点')):
    # 默认设置为首尾页码
    start_pageno = 0
    end_pageno = len(doc) - 1
    #
    lb,ub = bounds # lb:lower bound(下界); ub: upper bound(上界)
    #获取左界页码
    for n in range(len(doc)):
        page = doc[n];txt = page.get_text()
        if lb in txt:
            start_pageno = n; break
    #获取右界页码
    for n in range(start_pageno,len(doc)):
        if ub in doc[n].get_text():
            end_pageno = n; break
    #获取小范围内字符串
    txt = ''
    for n in range(start_pageno,end_pageno+1):
        page = doc[n]
        txt += page.get_text()
    return(txt)


paths = "C:\\Users\\12738\\Documents\\Python Scripts\\nianbao\\src\\nianbao"
paths_pos = file_name_walk(paths)
del paths_pos[0]
    # 创建一个只包含每只股票2022年年报绝对路径的列表，然后遍历调用
abs_pos_lst = []
for i in file_name_walk(paths):
    for n in i[1]:
        if '2022' in n:
            abs_pos = '{}/{}'.format(i[0],n)
            abs_pos_lst.append(abs_pos)
        else:
            continue
    # 提前创建一个表格，以便于存储数据
keys_Data = pd.DataFrame(columns=['公司简称','公司代码','公司办公地址','公司网址','电子信箱'])
for i in abs_pos_lst:
    docs = fitz.open(i)#i[0]+'\\{}'.format(n)
    brief_ = get_subtxtt(docs,bounds=('公司代码','信息披露及备置地点'))
        # name
    cor_name_compile = re.compile('.*公司简称：(.*?)\s.*',re.DOTALL)
    name = cor_name_compile.findall(brief_)[0].strip()
        # code
    cor_code_compile = re.compile('.*公司代码：(.*?)\s.*',re.DOTALL)
    code = cor_code_compile.findall(brief_)[0].strip()
        # address
    cor_address_compile = re.compile('公司办公地址.*?\n(.*?)\s*\n.*?',re.DOTALL)
    address = cor_address_compile.findall(brief_)[0].strip()
        # web
    cor_web_compile = re.compile('公司网址.*?\n\s*(.*?)\n电子信箱',re.DOTALL)
    web = cor_web_compile.findall(brief_)[0].strip()
        # secretary_mail
    sec_mail_compile = re.compile('.*电子信箱.*?\n\s*(.*?)\n.*',re.DOTALL)
    mail = sec_mail_compile.findall(brief_)[0].strip() 
    keys_Data.loc[len(keys_Data.index)] = {'公司简称':name,'公司代码':code,
              '公司办公地址':address,'公司网址':web,
              '电子信箱':mail}
keys_Data.to_csv('公司基础信息.csv')

结果

2.2提取营业收入、归属于上市公司股东净利润

'###########################年报数据解析获取##############################'
import fitz
import pandas as pd
import re

#filename = '2022_600000.PDF'
#doc = fitz.open(filename)

def get_subtxt(doc,bounds=('主要会计数据和财务指标','总资产')):
    # 默认设置为首尾页码
    start_pageno = 0
    end_pageno = len(doc) - 1
    #
    lb,ub = bounds # lb:lower bound(下界); ub: upper bound(上界)
    #获取左界页码
    for n in range(len(doc)):
        page = doc[n];txt = page.get_text()
        if lb in txt:
            start_pageno = n; break
    #获取右界页码
    for n in range(start_pageno,len(doc)):
        if ub in doc[n].get_text():
            end_pageno = n; break
    #获取小范围内字符串
    txt = ''
    for n in range(start_pageno,end_pageno+1):
        page = doc[n]
        txt += page.get_text()
    return(txt)

def get_th_span(txt):
    nianfen ='(20\d\d|199\d)\s*年末?' #|199\d
    s = f'{nianfen}\s*{nianfen}.*?{nianfen}'
    p = re.compile(s,re.DOTALL)
    matchobj = p.search(txt)
    #
    end = matchobj.end()
    year1 = matchobj.group(1)
    year2 = matchobj.group(2)
    year3 = matchobj.group(3)
    #
    flag = (int(year1) - int(year2) == 1) and (int(year2) - int(year3) == 1)
    #
    while(not flag):
        matchobj = p.search(txt[end:])
        end = matchobj.end()
        year1 = matchobj.group(1)
        year2 = matchobj.group(2)
        year3 = matchobj.group(3)
        flag = (int(year1) - int(year2) == 1)
        flag = flag and (int(year2) - int(year3) == 1)
    #
    return(matchobj.span())

def get_bounds(txt):
    th_span_1st = get_th_span(txt)
    end = th_span_1st[1]
    th_span_2nd = get_th_span(txt[end:])
    th_span_2nd = (end + th_span_2nd[0],end + th_span_2nd[1])
    #
    s = th_span_1st[1]
    e = th_span_2nd[0]
    #
    while (txt[e] not in '0123456789'):
        e = e - 1
    return(s,e)

def get_keywords(txt):
    p = re.compile(r'\d+\s*?\n\s*?([\u2E80-\u9FFF]+)')
    keywords = p.findall(txt)
    keywords.insert(0,'营业收入')
    return(keywords)

def parse_key_fin_data(subtext,keywords):
    # kwds = ['营业收入','营业成本','毛利','归属于上市','归属于上市','经营活动']
    ss = []
    s = 0
    for kw in keywords:
        n = subtext.find(kw,s)
        ss.append(n)
        s = n + len(kw)-1
    ss.append(len(subtext))
    data = []
    #
#    p = re.compile('\D+(?:\s+\D*)?(?:(.*)|\(.*)|(.*\))?')
#    p = re.compile('\D+(?:\s+\D*)?(?:(.*)|\(.*\))?')
    p = re.compile('\D+(?:\s+\D*)?')
    p2 = re.compile('\s')
    for n in range(len(ss)-1):
        s = ss[n]
        e =ss[n+1]
        line = subtext[s:e]
        #获取可能换行的账户名称
        matchobj = p.search(line)
        account_name = p2.sub('',matchobj.group())
        #获取三年数据
        amnts = line[matchobj.end():].split()
        #加上账户名称
        amnts.insert(0,account_name)
        #追加到总数据
        data.append(amnts)
    return(data)


def get_data_csv(code,data):
    csv_name=f'{code}_data.csv'
    data.to_csv(csv_name) 
    #这一步将有用的数据保存在csv_name的CSV中
#get_data_csv(code,pd.DataFrame(all_data))
#all_data=pd.read_csv(r'C:\Users\12738\Documents\Python Scripts\nianbao\src\nianbao\all_data.csv')
    
    
    
years = ['2022','2021','2020','2019','2018','2017','2016','2015','2014','2013']
all_data=[]
def get_datas(code):
    for Y in years:
        pdf_name=f'{code}_{Y}.pdf'
        doc = fitz.open(pdf_name)
        txt = get_subtxt(doc)
        txt = txt.replace(' ','')
        span = get_bounds(txt)
        subtext = txt[span[0]:span[1]]
        #去除字符串头部的所有空格函数用法
        subtext=subtext.replace(' ','')
        keywords = get_keywords(subtext)
        data = parse_key_fin_data(subtext,keywords)
        all_data.append(data)
#    all_data=pd.DataFrame(all_data)
    get_data_csv('code',pd.DataFrame(all_data))
   
#get_datas('600035')
     
codes = ['600080','600085','600161','600195','600200','600201','600216','600267','600276','600351']

for code in codes:
    get_datas(code)

get_data_csv('code',pd.DataFrame(all_data))
all_data=pd.read_csv(r'C:\Users\12738\Documents\Python Scripts\nianbao\src\nianbao\code_data.csv') #读取df

'#########################爬取的数据把字符串转为数字便于画图###################'
import matplotlib
print (matplotlib.matplotlib_fname()) # 将会获得matplotlib配置文件

from matplotlib.font_manager import _rebuild
_rebuild()

import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif']=['SimHei']
#解决matplotlib中文显示问题


import matplotlib.pyplot as plt
from pylab import mpl

def get_sep(tr):
    data=[]
    for i in range(len(tr)):
        temp=re.search(r'\d{1,3}(,\d{3})*(\.\d+)?',tr[i]).group()
        s=re.search(r'\d{1,3}(,\d{3})*(\.\d+)?',tr[i]).start()
        e=re.search(r'\d{1,3}(,\d{3})*(\.\d+)?',tr[i]).end()
        p=re.search(r'(\.)',tr[i]).start()
        num=change_int(s,e,p,temp)
        data.append(num)
    return(data)
##该函数用于将字符串转成浮点数并存在列表里用于作图

def change_int(s,e,p,temp):
    a=int((p-s)/4)
    b=(p-s)-(a*4)
    num=(int(temp[0:b]))*(10**(3*a))
    
    for n in range(a+1):
        if n == a:
             if temp[b+1+(4*n):] =='':
                num += 0
             else:
                num += (int(temp[b+1+(4*n):]))*(10**-(len(temp[b+1+(4*n):])))

        else:
            num += (int(temp[b+1+(4*n):b+4+(4*n)]))*(10**((2-n)*a))
    return(num)
    
'####################得出营业收入和归属于上市公司股东的净利润###################'
ls=[]
for i in range(10):
    temp=all_data.iloc[10*i:10*i+10]
    ls.append(temp)

ls2=list(map(lambda x:x.reset_index(drop=True),ls))

revenue = []       #营业收入
for i in range(10):
    revenue.append(get_sep(ls2[i].iloc[0:10,1]))
   
netincome = []     #归属于上市公司股东的净利润
for i in range(10):
    netincome.append(get_sep(ls2[i].iloc[0:10,2]))

结果

三、图像绘制与对照

import matplotlib
print (matplotlib.matplotlib_fname()) # 将会获得matplotlib配置文件

from matplotlib.font_manager import _rebuild
_rebuild()

import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif']=['SimHei']
#解决matplotlib中文显示问题

import matplotlib.pyplot as plt
from pylab import mpl
  '###############################营业收入###############################'

years = ['2022','2021','2020','2019','2018','2017','2016','2015','2014','2013']   
x = years 
fig1 = plt.figure(figsize=(36,15))
#plt.title(u'十家公司营业收入时间序列图',fontsize=13)

ax1 = fig1.add_subplot(251)
ax1.plot(x,revenue[0],'m*-')
for a, b in zip(x,revenue[0]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax1.set_xlabel('年 份',fontsize=10)
ax1.set_ylabel('营业收入',fontsize=10)
ax1.set_title('600080金花股份',fontsize=10)


ax2 = fig1.add_subplot(252)
ax2.plot(x,revenue[1],'m*-')
for a, b in zip(x,revenue[1]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax2.set_xlabel('年 份',fontsize=10)
ax2.set_ylabel('营业收入',fontsize=10)
ax2.set_title('600085同仁堂',fontsize=10)


ax3 = fig1.add_subplot(253)
ax3.plot(x,revenue[2],'m*-')
for a, b in zip(x,revenue[2]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax3.set_xlabel('年 份',fontsize=10)
ax3.set_ylabel('营业收入',fontsize=10)
ax3.set_title('600161天坛生物',fontsize=10)


ax4 = fig1.add_subplot(254)
ax4.plot(x,revenue[3],'m*-')
for a, b in zip(x,revenue[3]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax4.set_xlabel('年 份',fontsize=10)
ax4.set_ylabel('营业收入',fontsize=10)
ax4.set_title('600195中牧股份',fontsize=10)


ax5 = fig1.add_subplot(255)
ax5.plot(x,revenue[4],'m*-')
for a, b in zip(x,revenue[4]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax5.set_xlabel('年 份',fontsize=10)
ax5.set_ylabel('营业收入',fontsize=10)
ax5.set_title('600200江苏吴中',fontsize=10)


ax6 = fig1.add_subplot(256)
ax6.plot(x,revenue[5],'m*-')
for a, b in zip(x,revenue[5]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax6.set_xlabel('年 份',fontsize=10)
ax6.set_ylabel('营业收入',fontsize=10)
ax6.set_title('600201生物股份',fontsize=10)


ax7 = fig1.add_subplot(257)
ax7.plot(x,revenue[6],'m*-')
for a, b in zip(x,revenue[6]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax7.set_xlabel('年 份',fontsize=10)
ax7.set_ylabel('营业收入',fontsize=10)
ax7.set_title('600216浙江医药',fontsize=10)



ax8 = fig1.add_subplot(258)
ax8.plot(x,revenue[7],'m*-')
for a, b in zip(x,revenue[7]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax8.set_xlabel('年 份',fontsize=10)
ax8.set_ylabel('营业收入',fontsize=10)
ax8.set_title('600267海正药业',fontsize=10)


ax9 = fig1.add_subplot(259)
ax9.plot(x,revenue[8],'m*-')
for a, b in zip(x,revenue[8]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax9.set_xlabel('年 份',fontsize=10)
ax9.set_ylabel('营业收入',fontsize=10)
ax9.set_title('600276恒瑞医药',fontsize=10)


ax10 = fig1.add_subplot(2,5,10)
ax10.plot(x,revenue[9],'m*-')
for a, b in zip(x,revenue[9]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax10.set_xlabel('年 份',fontsize=10)
ax10.set_ylabel('营业收入',fontsize=10)
ax10.set_title('600351亚宝药业',fontsize=10)

plt.show()
    
'#######################归属于上市公司股东的净利润###########################'

years = ['2022','2021','2020','2019','2018','2017','2016','2015','2014','2013']   
x = years 
fig1 = plt.figure(figsize=(36,15))
#plt.title(u'十家公司营业收入时间序列图',fontsize=13)

ax1 = fig1.add_subplot(251)
ax1.plot(x,netincome[0],'m*-')
for a, b in zip(x,netincome[0]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax1.set_xlabel('年 份',fontsize=10)
ax1.set_ylabel('归属于上市公司股东的净利润',fontsize=10)
ax1.set_title('600080金花股份',fontsize=10)


ax2 = fig1.add_subplot(252)
ax2.plot(x,netincome[1],'m*-')
for a, b in zip(x,netincome[1]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax2.set_xlabel('年 份',fontsize=10)
ax2.set_ylabel('归属于上市公司股东的净利润',fontsize=10)
ax2.set_title('600085同仁堂',fontsize=10)


ax3 = fig1.add_subplot(253)
ax3.plot(x,netincome[2],'m*-')
for a, b in zip(x,netincome[2]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax3.set_xlabel('年 份',fontsize=10)
ax3.set_ylabel('归属于上市公司股东的净利润',fontsize=10)
ax3.set_title('600161天坛生物',fontsize=10)


ax4 = fig1.add_subplot(254)
ax4.plot(x,netincome[3],'m*-')
for a, b in zip(x,netincome[3]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax4.set_xlabel('年 份',fontsize=10)
ax4.set_ylabel('归属于上市公司股东的净利润',fontsize=10)
ax4.set_title('600195中牧股份',fontsize=10)


ax5 = fig1.add_subplot(255)
ax5.plot(x,netincome[4],'m*-')
for a, b in zip(x,netincome[4]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax5.set_xlabel('年 份',fontsize=10)
ax5.set_ylabel('归属于上市公司股东的净利润',fontsize=10)
ax5.set_title('600200江苏吴中',fontsize=10)


ax6 = fig1.add_subplot(256)
ax6.plot(x,netincome[5],'m*-')
for a, b in zip(x,netincome[5]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax6.set_xlabel('年 份',fontsize=10)
ax6.set_ylabel('归属于上市公司股东的净利润',fontsize=10)
ax6.set_title('600201生物股份',fontsize=10)


ax7 = fig1.add_subplot(257)
ax7.plot(x,netincome[6],'m*-')
for a, b in zip(x,netincome[6]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax7.set_xlabel('年 份',fontsize=10)
ax7.set_ylabel('归属于上市公司股东的净利润',fontsize=10)
ax7.set_title('600216浙江医药',fontsize=10)



ax8 = fig1.add_subplot(258)
ax8.plot(x,netincome[7],'m*-')
for a, b in zip(x,netincome[7]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax8.set_xlabel('年 份',fontsize=10)
ax8.set_ylabel('归属于上市公司股东的净利润',fontsize=10)
ax8.set_title('600267海正药业',fontsize=10)


ax9 = fig1.add_subplot(259)
ax9.plot(x,netincome[8],'m*-')
for a, b in zip(x,netincome[8]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax9.set_xlabel('年 份',fontsize=10)
ax9.set_ylabel('归属于上市公司股东的净利润',fontsize=10)
ax9.set_title('600276恒瑞医药',fontsize=10)


ax10 = fig1.add_subplot(2,5,10)
ax10.plot(x,netincome[9],'m*-')
for a, b in zip(x,netincome[9]):
    plt.text(a, b+3, b, ha='center', va='bottom')
ax10.set_xlabel('年 份',fontsize=10)
ax10.set_ylabel('归属于上市公司股东的净利润',fontsize=10)
ax10.set_title('600351亚宝药业',fontsize=10)

plt.show()   

years = ['2022','2021','2020','2019','2018','2017','2016','2015','2014','2013'] 

x = years
y = revenue

fig= plt.figure(figsize=(60,35))

plt.xlabel("年份")
plt.ylabel("营业收入")
plt.title("十家公司十年营业收入对比图")

for i in range(len(y)):
       plt.plot(x,y[i],label = '股票代码 %s'%codes[i])


plt.legend()
plt.show()

x = years
y = netincome

fig= plt.figure(figsize=(60,35))

plt.xlabel("年份")
plt.ylabel("归属于上市公司股东的净利润")
plt.title("十家公司十年归属于上市公司股东的净利润对比图")

for i in range(len(y)):
       plt.plot(x,y[i],label = '股票代码 %s'%codes[i])


plt.legend()
plt.show()

结果：营业收入（图片稍小，可放大网页查看）

结果：归属于上市公司股东的净利润（图片稍小，可放大网页查看）

结果：十家公司十年营业收入对比图

结果：十家公司十年归属于上市公司股东的净利润对比图

行业分析与个人的思考

实验感想