如何批量獲取年報中數據?

import requests
import json
from bs4 import BeautifulSoup
import xlsxwriter
import re

def getURl(anysheet):
u = "http://xinsanban.eastmoney.com/api/F10/Finance/" + anysheet
return u

#定義一個函數用於獲取json數據
def getHTMLjson(url,stocknum):
#codeAndType是向鏈接傳遞的表單，datetype=0是默認按半年報來的，datetype=6是按年報
codeAndType = {"MSECUCODE":stocknum,"dateType":"0"}
try:
r = requests.get(url,params=codeAndType)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.json() #返回json數據格式
except:
return "爬取失敗"

#定義兩個函數將原始的json數據中我們需要的部分取出來
#第一個函數取中文標題
def getTitle(jsondata):
title = {} #l是一個空字典，用於存儲中英文標題欄
for key in jsondata["Trs"]:
title[str(key["Field"])] = key["Name"]
return title

#第二個函數取報表數據
def getYearsData(jsondata):
yearsData = [] #ls是一個空列表，用於存儲三年的數據
for k in jsondata["result"]:
yearsData.append(k)
return yearsData

#fixedData函數將標題和數據整理好
def fixedData(title,yearsData):
ds = []
count = 0
def exangeData(i):#構造這個函數用於將title，years的數據整合起來
for a,b in title.items():
for c,d in yearsData[i].items():
if a == c: #利用英文標題欄將需要的數據整合成字典
dic[b] = d
return dic
while True:
dic = {}
y = exangeData(count)
ds.append(y)
count += 1
if count == len(yearsData):
break
return ds

#finaData調用前面的函數生成最終的數據
def finalData(sheet,code):
url = getURl(sheet)
YsData = getHTMLjson(url,code)
titles = getTitle(YsData)
datas = getYearsData(YsData)
s = fixedData(titles,datas)
return s

def main(code):
BS = finalData("zcfzb",code)
CFS = finalData("xjllb",code)
PL = finalData("lrb",code)
alldata = [BS,CFS,PL]
return alldata

#writContent函數將內容寫進入
def writeContent(workbook,x,sheetName):
worksheet = workbook.add_worksheet(sheetName)
#將A1處設置為空白
worksheet.write("A1", "")
i = 0
j = 66
while True:
worksheet.write(chr(j)+"1", str(list(s[x][i].values())[0]))
i += 1
j += 1
if i == len(s[x]):
break
m = 2
#製作左側的科目
while True:
worksheet.write("A"+str(m),str((list(s[x][0]))[m]))
m +=1
if m == len(s[x][0]):
break
#oneLine函數一行一行地往下寫
def oneLine(worksheet,x,y):
e = 0
f = 66
while True:
worksheet.write(chr(f)+str(y), str(list(s[x][e].values())[y]))
e += 1
f += 1
if e == len(s[0]):
break
return worksheet
x = x
y = 2
while True:
oneLine(worksheet,x,y)
y += 1
if y == len(s[x][0]):
break

def writeAllSheets(stockcode):
s = main(stockcode)
workbook = xlsxwriter.Workbook(str(stockcode) + ".xlsx")
sheetNameList = ["BS","CFS","PL"]
g = 0
while True:
writeContent(workbook,g,sheetNameList[g])
g += 1
if g == len(sheetNameList):
break
workbook.close()

def getAstock(stockcode):
try:
writeAllSheets(stockcode)
except:
pass

#以下函數為獲取所有股票的列表
def getStockCodeText(url,page):
try:
r = requests.get(url,params=page)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
return "爬取失敗"

def getStockCodeList(html):
lst = []
soup = BeautifulSoup(html,"html.parser")
a = soup.find_all("a")
for i in a:
try:
title = i.attrs["title"]
lst.append(re.findall(r"d{6}", title)[0])
except:
continue
return lst

def endPage():
try:
r = requests.get("http://www.jingujie.com/stocklist/")
r.raise_for_status()
r.encoding = r.apparent_encoding
html = r.text
except:
return "爬取失敗"
pages = []
soup = BeautifulSoup(html,"html.parser")
a = soup.find_all("a")
for i in a:
try:
page = i.string
pages.append(re.findall(r"d{3}", page)[0])
except:
continue
return pages

def finalCodeList():
finalpages = endPage()[-1]
clst = []
v = 1
url = "http://www.jingujie.com/stocklist/"
while True:
vd = {"page":v}
htmlText = getStockCodeText(url,vd)
c = getStockCodeList(htmlText)
for j in c:
clst.append(j)
v += 1
if v == 2:
break
return clst