陈予同的实验报告

第一步 下载年报


 from time import sleep
 from urllib import parse

 import os
 import json
 import requests



 #获取地址
 def get_address(bank_code):
    url = "http://www.cninfo.com.cn/new/information/topSearch/detailOfQuery"
    data = {
        'keyWord': bank_code,
        'maxSecNum': 10,
        'maxListNum': 5,
    }
    hd = {
        'Host': 'www.cninfo.com.cn',
        'Origin': 'http://www.cninfo.com.cn',
        'Pragma': 'no-cache',
        'Accept-Encoding': 'gzip,deflate',
        'Connection': 'keep-alive',
        'Content-Length': '70',
        'User-Agent': 'Mozilla/5.0(Windows NT 10.0;Win64;x64) AppleWebKit / 537.36(KHTML, likeGecko) Chrome / 75.0.3770.100Safari / 537.36',
        'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
        'Accept': 'application/json,text/plain,*/*',
        'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
    }
    r = requests.post(url, headers=hd, data=data)
    print(r.text)
    r = r.content
    m = str(r, encoding="utf-8")
    pk = json.loads(m)
    orgId = pk["keyBoardList"][0]["orgId"]  # 获取参数
    plate = pk["keyBoardList"][0]["plate"]
    code = pk["keyBoardList"][0]["code"]
    print(orgId, plate, code)
    return orgId, plate, code

 #下载PDF
 def download_PDF(url, file_name):
    url = url
    r = requests.get(url)
    f = open(code + "/" + file_name + ".pdf", "wb")
    f.write(r.content)


 def get_PDF(orgId, plate, code):
    url = "http://www.cninfo.com.cn/new/hisAnnouncement/query"
    data = {
        'stock': '{},{}'.format(code, orgId),
        'tabName': 'fulltext',
        'pageSize': 20,
        'pageNum': 1,
        'column': plate,
        'category': 'category_ndbg_szsh;',
        'plate': '',
        'seDate': '',
        'searchkey': '',
        'secid': '',
        'sortName': '',
        'sortType': '',
        'isHLtitle': 'true',
    }

    hd = {
        'Host': 'www.cninfo.com.cn',
        'Origin': 'http://www.cninfo.com.cn',
        'Pragma': 'no-cache',
        'Accept-Encoding': 'gzip,deflate',
        'Connection': 'keep-alive',
        # 'Content-Length': '216',
        'User-Agent': 'User-Agent:Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27',
        'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
        'Accept': 'application/json,text/plain,*/*',
        'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
        'X-Requested-With': 'XMLHttpRequest',
        # 'Cookie': cookies
    }
    data = parse.urlencode(data)
    print(data)
    r = requests.post(url, headers=hd, data=data)
    print(r.text)
    r = str(r.content, encoding="utf-8")
    r = json.loads(r)
    reports_list = r['announcements']
    for report in reports_list:
        if '摘要' in report['announcementTitle'] or "20" not in report['announcementTitle']:
            continue
        if 'H' in report['announcementTitle']:
            continue
        else:  # http://static.cninfo.com.cn/finalpage/2019-03-29/1205958883.PDF
            pdf_url = "http://static.cninfo.com.cn/" + report['adjunctUrl']
            file_name = report['announcementTitle']
            print("正在下载：" + pdf_url, "存放在当前目录：/" + code + "/" + file_name)
            download_PDF(pdf_url, file_name)
            sleep(2)

 #运行代码
 if __name__ == '__main__':
    #code list
    code_list = ['002286','002311', '002330', '002385', '002515', '002548', '002557', '002567', '002582', '002695']
    for code in code_list:
        os.mkdir(code)
        orgId, plate, code = get_adress(code)
        get_PDF(orgId, plate, code)
        print("next bank")
print("Finished")

结果展示

结果截图 结果截图

第二步 提取公司基本信息



import pdfplumber
import pandas as pd
#以002286为例
filename="C:/Users/Administrator/Desktop/大作业/002286/2013年年度报告.pdf"
pdf = pdfplumber.open(filename)
page1 = pdf.pages[5]
table1 = page1.extract_tables()[0]
df1 = pd.DataFrame(table1)

stock1=pd.concat([df1], ignore_index=True)
stock1.set_index([0],inplace=True)
stock1=stock1.iloc[:,0]
stock1=pd.DataFrame(stock1)
stock1.columns=["002286"]

allinfo= pd.concat([stock1], axis=1, ignore_index=False)
allinfo=allinfo.iloc[1:]

结果展示

结果截图

第三步 获取数据并画图




import matplotlib.pyplot as plt
from pylab import mpl
import os
import re

file_dir = "C:\\Users\\Administrator\\Desktop\\大作业"

filepath=file_dir
filelist=[]
pdfpath=[]
list1= os.listdir(filepath)
for file1 in list1:
            path = os.path.join(filepath, file1)
            # print(file1)
            if os.path.isfile(path):
                filelist.append(file1)
                pdfpath.append(path)
            else:
                list2=os.listdir(path)
                for file2 in list2:
                    path2 = os.path.join(path, file2)
                    # print(file2)
                    if os.path.isfile(path2):
                        filelist.append(file2)
                        pdfpath.append(path2)
                        
     #start

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
            #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)
                
        
        #获取表头
def get_th_span(txt):
            nianfen='(20\d\d|199\d)\s*?年'   #2016和年之间是空格，而2016年和2015年之间是空格
            s=f'{nianfen}\s*{nianfen}.*?{nianfen}'
            p=re.compile(s,re.DOTALL)  #re.DOTALL指.遇到换行符也是可以的
            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)
            
        #获取表格边界
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]-1
            #
            while (txt[e] not in '0123456789'):  #如果最后一个不是数字
                e=e-1
            return(s,e+1)
        
        
       #获取‘营业收入’和‘归属于上市公司股\n东的净利润’
def get_account_data(account,txt):
            p_txt='%s\D*?(\d{1,3}(?:,\d{3})*(?:\.\d+)?)' % account   #%s是占位符，用‘account’替换，\D是非数字，\d{1,3}是数字1或2或3个，*可重复，？非贪婪，（）内是所要的数字，小数点后\d+表示小数点后至少一位数字
            p=re.compile(p_txt)
            matchobj=p.search(txt)
            amt=matchobj.group(1)
            return(amt)

    #获取整张表格
        # subtxt=txt[txt.find('营业收入'):txt.find('总资产')]
def get_keywords(txt):
            p=re.compile(r's\D*?(\d{1,3}(?:,\d{3})*(?:\.\d+)?)')
            keywords=p.findall(txt)
            return(keywords)
###
def parse_key_fin_data(subtxt,keywords):
            # keywords=['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=subtxt.find(kw,s)
                ss.append(n)
                s=n+len(kw)
            ss.append(len(subtxt))
            data=[]
            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=subtxt[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
        
        
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np

import matplotlib.pyplot as plt
from pylab import mpl
import datetime

mpl.rcParams['font.sans-serif']=['FangSong']
mpl.rcParams['axes.unicode_minus']=False
from pandas.plotting import register_matplotlib_converters
register_matplotlib_converters()

import fitz
#以002286为例

stock1_sr=[]
stock1_jlr=[]
filename='C:\\Users\\Administrator\\Desktop\\大作业\\002286\\2013年年度报告.pdf'
doc=fitz.open(filename)
txt=get_subtxt(doc)
span=get_bounds(txt)
subtxt=txt[txt.find('营业收入'):txt.find('总资产')]
keywords=['营业收入','归属于上市公司股东的净利润']
data=parse_key_fin_data(subtxt, keywords)
data_get=data[0]
stock1_sr.append(data_get[4])
stock1_jlr.append(data_get[10])
stock1_sr.append(data_get[2])
stock1_jlr.append(data_get[8])
stock1_sr.append(data_get[1])
stock1_jlr.append(data_get[7])
filename='C:\\Users\\Administrator\\Desktop\\大作业\\002286\\2016年年度报告.pdf'
doc=fitz.open(filename)
txt=get_subtxt(doc)
span=get_bounds(txt)
subtxt=txt[txt.find('营业收入'):txt.find('总资产')]
keywords=['营业收入','归属于上市公司股东的净利润']
data=parse_key_fin_data(subtxt, keywords)
data_get=data[0]
stock1_sr.append(data_get[5])
stock1_jlr.append(data_get[13])
stock1_sr.append(data_get[2])
stock1_jlr.append(data_get[10])
stock1_sr.append(data_get[1])
stock1_jlr.append(data_get[9])
filename='C:\\Users\\Administrator\\Desktop\\大作业\\002286\\2019年年度报告.pdf'
doc=fitz.open(filename)
txt=get_subtxt(doc)
span=get_bounds(txt)
subtxt=txt[txt.find('营业收入'):txt.find('总资产')]
keywords=['营业收入','归属于上市公司股东的净利润']
data=parse_key_fin_data(subtxt, keywords)
data_get=data[0]
stock1_sr.append(data_get[4])
stock1_jlr.append(data_get[10])
stock1_sr.append(data_get[2])
stock1_jlr.append(data_get[8])
stock1_sr.append(data_get[1])
stock1_jlr.append(data_get[7])
filename='C:\\Users\\Administrator\\Desktop\\大作业\\002286\\2022年年度报告.pdf'
doc=fitz.open(filename)
txt=get_subtxt(doc)
span=get_bounds(txt)
subtxt=txt[txt.find('营业收入'):txt.find('总资产')]
keywords=['营业收入','归属于上市公司股东的净利润']
data=parse_key_fin_data(subtxt, keywords)
data_get=data[0]
stock1_sr.append(data_get[2])
stock1_jlr.append(data_get[8])
stock1_sr.append(data_get[1])
stock1_jlr.append(data_get[7])
# year=['2013年','2016年','2019年','2022年']

#stock1
stock11=[]
tran(stock1_sr,stock11)
stock12=[]
tran(stock1_jlr,stock12)

ykzj=['2013年','2014年','2015年','2016年','2017年','2018年','2019年','2020年','2021年','2022年']
plt.figure(figsize=(9, 6))
plt.plot(ykzj,stock11)
plt.bar(ykzj,stock11)
plt.title(u'002286营业收入')
plt.legend()
plt.show()
plt.figure(figsize=(9, 6))
plt.plot(ykzj,stock12)
plt.bar(ykzj,stock12)
plt.title(u'002285归属于上市公司股东的净利润')
plt.show()

结果展示（以002286为例）

结果截图 结果截图

多公司比较

  
  import matplotlib.pyplot as plt
   #多公司比较
    #营业收入
#form={'东鹏饮料':dp1}
a = ['2013','2014','2015','2016','2017','2018','2019','2020','2021','2022']
b_1 =stock11
b_2 = [None,None,None]+stock21
b_3 = stock31
b_4 = stock41
b_5 = [None]+stock51
b_6 = stock61
b_7 = stock71
b_8 = [None]+stock81
b_9 = stock91
b_10 = stock101
    #设置图片尺寸与清晰度
plt.figure(figsize=(10, 8), dpi=80)
    #导入数据，绘制条形图
plt.plot( a, b_1, marker = "o", mfc = "white", label='002286')
plt.plot( a,b_2,  marker = "o", mfc = "white",label='002311')
plt.plot( a,b_3,  marker = "o", mfc = "white",label='002330')
plt.plot( a,b_4, marker = "o", mfc = "white", label='002385')
plt.plot( a,b_5,  marker = "o", mfc = "white",label='002515')
plt.plot( a,b_6,  marker = "o", mfc = "white",label='002548')
plt.plot( a,b_7,  marker = "o", mfc = "white",label='002557')
plt.plot( a,b_8, marker = "o", mfc = "white", label='002567')
plt.plot( a,b_9, marker = "o", mfc = "white", label='002582')
plt.plot( a,b_10, marker = "o", mfc = "white", label='002695')
    #添加标题
plt.title('每一年的营业收入对比图', size=20)
    #添加xy轴
plt.xlabel('时间')
plt.ylabel('营业收入（元）')
    #x轴刻度
plt.grid()
plt.legend()
    #展示效果图
plt.show()

结果

十家公司营业收入对比图

心得

这次大作业对我来说很有难度，但学到的知识技能非常有用。虽然课程结束了，但我还需多多练习，直至能够熟练运用。

总代码（缺失运行代码）



import json
import os
from time import sleep
from urllib import parse

import requests


def get_adress(bank_code):
    url = "http://www.cninfo.com.cn/new/information/topSearch/detailOfQuery"
    data = {
        'keyWord': bank_code,
        'maxSecNum': 10,
        'maxListNum': 5,
    }
    hd = {
        'Host': 'www.cninfo.com.cn',
        'Origin': 'http://www.cninfo.com.cn',
        'Pragma': 'no-cache',
        'Accept-Encoding': 'gzip,deflate',
        'Connection': 'keep-alive',
        'Content-Length': '70',
        'User-Agent': 'Mozilla/5.0(Windows NT 10.0;Win64;x64) AppleWebKit / 537.36(KHTML, likeGecko) Chrome / 75.0.3770.100Safari / 537.36',
        'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
        'Accept': 'application/json,text/plain,*/*',
        'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
    }
    r = requests.post(url, headers=hd, data=data)
    print(r.text)
    r = r.content
    m = str(r, encoding="utf-8")
    pk = json.loads(m)
    orgId = pk["keyBoardList"][0]["orgId"]  # 获取参数
    plate = pk["keyBoardList"][0]["plate"]
    code = pk["keyBoardList"][0]["code"]
    print(orgId, plate, code)
    return orgId, plate, code


def download_PDF(url, file_name):  # 下载pdf
    url = url
    r = requests.get(url)
    f = open(code + "/" + file_name + ".pdf", "wb")
    f.write(r.content)


def get_PDF(orgId, plate, code):
    url = "http://www.cninfo.com.cn/new/hisAnnouncement/query"
    data = {
        'stock': '{},{}'.format(code, orgId),
        'tabName': 'fulltext',
        'pageSize': 20,
        'pageNum': 1,
        'column': plate,
        'category': 'category_ndbg_szsh;',
        'plate': '',
        'seDate': '',
        'searchkey': '',
        'secid': '',
        'sortName': '',
        'sortType': '',
        'isHLtitle': 'true',
    }

    hd = {
        'Host': 'www.cninfo.com.cn',
        'Origin': 'http://www.cninfo.com.cn',
        'Pragma': 'no-cache',
        'Accept-Encoding': 'gzip,deflate',
        'Connection': 'keep-alive',
        # 'Content-Length': '216',
        'User-Agent': 'User-Agent:Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27',
        'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
        'Accept': 'application/json,text/plain,*/*',
        'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
        'X-Requested-With': 'XMLHttpRequest',
        # 'Cookie': cookies
    }
    data = parse.urlencode(data)
    print(data)
    r = requests.post(url, headers=hd, data=data)
    print(r.text)
    r = str(r.content, encoding="utf-8")
    r = json.loads(r)
    reports_list = r['announcements']
    for report in reports_list:
        if '摘要' in report['announcementTitle'] or "20" not in report['announcementTitle']:
            continue
        if 'H' in report['announcementTitle']:
            continue
        else:  # http://static.cninfo.com.cn/finalpage/2019-03-29/1205958883.PDF
            pdf_url = "http://static.cninfo.com.cn/" + report['adjunctUrl']
            file_name = report['announcementTitle']
            print("正在下载：" + pdf_url, "存放在当前目录：/" + code + "/" + file_name)
            download_PDF(pdf_url, file_name)
            sleep(2)


if __name__ == '__main__':
    #code list
    code_list = ['002286','002311', '002330', '002385', '002515', '002548', '002557', '002567', '002582', '002695']
    for code in code_list:
        os.mkdir(code)
        orgId, plate, code = get_adress(code)
        get_PDF(orgId, plate, code)
        print("next bank")
    print("Finished")
    
    
import pdfplumber
import pandas as pd

filename="C:/Users/Administrator/Desktop/大作业/002286/2013年年度报告.pdf"
pdf = pdfplumber.open(filename)
page1 = pdf.pages[5]
table1 = page1.extract_tables()[0]
df1 = pd.DataFrame(table1)

stock1=pd.concat([df1], ignore_index=True)
stock1.set_index([0],inplace=True)
stock1=stock1.iloc[:,0]
stock1=pd.DataFrame(stock1)
stock1.columns=["002286"]

allinfo= pd.concat([stock1], axis=1, ignore_index=False)
allinfo=allinfo.iloc[1:]

import matplotlib.pyplot as plt
from pylab import mpl
import os
import re

file_dir = "C:\\Users\\Administrator\\Desktop\\大作业"

filepath=file_dir
filelist=[]
pdfpath=[]
list1= os.listdir(filepath)
for file1 in list1:
            path = os.path.join(filepath, file1)
            # print(file1)
            if os.path.isfile(path):
                filelist.append(file1)
                pdfpath.append(path)
            else:
                list2=os.listdir(path)
                for file2 in list2:
                    path2 = os.path.join(path, file2)
                    # print(file2)
                    if os.path.isfile(path2):
                        filelist.append(file2)
                        pdfpath.append(path2)
                        
     #start

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
            #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)
                
        
        #获取表头
def get_th_span(txt):
            nianfen='(20\d\d|199\d)\s*?年'   #2016和年之间是空格，而2016年和2015年之间是空格
            s=f'{nianfen}\s*{nianfen}.*?{nianfen}'
            p=re.compile(s,re.DOTALL)  #re.DOTALL指.遇到换行符也是可以的
            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)
            
        #获取表格边界
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]-1
            #
            while (txt[e] not in '0123456789'):  #如果最后一个不是数字
                e=e-1
            return(s,e+1)
        
        
       #获取‘营业收入’和‘归属于上市公司股\n东的净利润’
def get_account_data(account,txt):
            p_txt='%s\D*?(\d{1,3}(?:,\d{3})*(?:\.\d+)?)' % account   #%s是占位符，用‘account’替换，\D是非数字，\d{1,3}是数字1或2或3个，*可重复，？非贪婪，（）内是所要的数字，小数点后\d+表示小数点后至少一位数字
            p=re.compile(p_txt)
            matchobj=p.search(txt)
            amt=matchobj.group(1)
            return(amt)

    #获取整张表格
        # subtxt=txt[txt.find('营业收入'):txt.find('总资产')]
def get_keywords(txt):
            p=re.compile(r's\D*?(\d{1,3}(?:,\d{3})*(?:\.\d+)?)')
            keywords=p.findall(txt)
            return(keywords)
###
def parse_key_fin_data(subtxt,keywords):
            # keywords=['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=subtxt.find(kw,s)
                ss.append(n)
                s=n+len(kw)
            ss.append(len(subtxt))
            data=[]
            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=subtxt[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
        
        
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np

import matplotlib.pyplot as plt
from pylab import mpl
import datetime

mpl.rcParams['font.sans-serif']=['FangSong']
mpl.rcParams['axes.unicode_minus']=False
from pandas.plotting import register_matplotlib_converters
register_matplotlib_converters()

import fitz

stock1_sr=[]
stock1_jlr=[]
filename='C:\\Users\\Administrator\\Desktop\\大作业\\002286\\2013年年度报告.pdf'
doc=fitz.open(filename)
txt=get_subtxt(doc)
span=get_bounds(txt)
subtxt=txt[txt.find('营业收入'):txt.find('总资产')]
keywords=['营业收入','归属于上市公司股东的净利润']
data=parse_key_fin_data(subtxt, keywords)
data_get=data[0]
stock1_sr.append(data_get[4])
stock1_jlr.append(data_get[10])
stock1_sr.append(data_get[2])
stock1_jlr.append(data_get[8])
stock1_sr.append(data_get[1])
stock1_jlr.append(data_get[7])
filename='C:\\Users\\Administrator\\Desktop\\大作业\\002286\\2016年年度报告.pdf'
doc=fitz.open(filename)
txt=get_subtxt(doc)
span=get_bounds(txt)
subtxt=txt[txt.find('营业收入'):txt.find('总资产')]
keywords=['营业收入','归属于上市公司股东的净利润']
data=parse_key_fin_data(subtxt, keywords)
data_get=data[0]
stock1_sr.append(data_get[5])
stock1_jlr.append(data_get[13])
stock1_sr.append(data_get[2])
stock1_jlr.append(data_get[10])
stock1_sr.append(data_get[1])
stock1_jlr.append(data_get[9])
filename='C:\\Users\\Administrator\\Desktop\\大作业\\002286\\2019年年度报告.pdf'
doc=fitz.open(filename)
txt=get_subtxt(doc)
span=get_bounds(txt)
subtxt=txt[txt.find('营业收入'):txt.find('总资产')]
keywords=['营业收入','归属于上市公司股东的净利润']
data=parse_key_fin_data(subtxt, keywords)
data_get=data[0]
stock1_sr.append(data_get[4])
stock1_jlr.append(data_get[10])
stock1_sr.append(data_get[2])
stock1_jlr.append(data_get[8])
stock1_sr.append(data_get[1])
stock1_jlr.append(data_get[7])
filename='C:\\Users\\Administrator\\Desktop\\大作业\\002286\\2022年年度报告.pdf'
doc=fitz.open(filename)
txt=get_subtxt(doc)
span=get_bounds(txt)
subtxt=txt[txt.find('营业收入'):txt.find('总资产')]
keywords=['营业收入','归属于上市公司股东的净利润']
data=parse_key_fin_data(subtxt, keywords)
data_get=data[0]
stock1_sr.append(data_get[2])
stock1_jlr.append(data_get[8])
stock1_sr.append(data_get[1])
stock1_jlr.append(data_get[7])
        # year=['2013年','2016年','2019年','2022年']
        
     #stock1
stock11=[]
tran(stock1_sr,stock11)
stock12=[]
tran(stock1_jlr,stock12)


ykzj=['2013年','2014年','2015年','2016年','2017年','2018年','2019年','2020年','2021年','2022年']
plt.figure(figsize=(9, 6))
plt.plot(ykzj,stock11)
plt.bar(ykzj,stock11)
plt.title(u'002286营业收入')
plt.legend()
plt.show()
plt.figure(figsize=(9, 6))
plt.plot(ykzj,stock12)
plt.bar(ykzj,stock12)
plt.title(u'002285归属于上市公司股东的净利润')
plt.show()