import requests
from bs4 import BeautifulSoup
import re
import xlwt
finddata=re.compile(r'黄金价格.*收于(.*)美元/盎司;白银价格.*收于(.*)美元/盎司。')
fandlink=re.compile(r'href="(.*)" target="_blank">')
findday=re.compile(r'(中国工商银行金融市场部 (.*))</span>')
url1='http://www.icbc.com.cn/icbc/%e7%bd%91%e4%b8%8a%e9%bb%84%e9%87%91/%e8%b4%b5%e9%87%91%e5%b1%9e%e8%b5%84%e8%ae%af/%e5%b8%82%e5%9c%ba%e5%bf%ab%e6%8a%a5/default.htm'
url3='http://www.icbc.com.cn/icbc/%e7%bd%91%e4%b8%8a%e9%bb%84%e9%87%91/%e8%b4%b5%e9%87%91%e5%b1%9e%e8%b5%84%e8%ae%af/%e5%b8%82%e5%9c%ba%e5%bf%ab%e6%8a%a5/default-PageList-'
headers ={
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.64 Safari/537.36 Edg/101.0.1210.47'}
def getdata(url2):
r = requests.get(url=url2, headers=headers)
r.encoding = 'utf-8'
bs = BeautifulSoup(r.text, 'html.parser')
item = bs.find_all('span', id='MyFreeTemplateUserControl')
item2=bs.find_all('span',id="InfoPickFromFieldControl")
item = str(item)
item2=str(item2)
data = re.findall(finddata, item)
day = re.findall(findday,item2)
return data[0][1],data[0][0],day[0]
z=str(3)
y='.htm'
worlbook=xlwt .Workbook (encoding= 'utf-8')#创建一个文件
worksheet=worlbook .add_sheet('sheet2')#创建一个文件的表单
col=['黄金','白银','日期']
for i in range (3):
worksheet .write(0,i,col[i])
k=1
for x in range(4):
if x==0:
url4=url1
else:
url4=url3+z+y
z = str(int(z) - 1)
r=requests.get(url=url4,headers =headers )
r.encoding='utf-8'
bs=BeautifulSoup (r.text ,'html.parser')
for i in range(1):
for item in bs.find_all('span',class_="ChannelSummaryList-insty"):
item=str(item)
x=re.findall(fandlink,item)
url2='http://www.icbc.com.cn'+x[0]
ag,gd,day=getdata(url2)
# print(f'日期{day}')
# print(f'白银{ag}')
# print(f'黄金{gd}')
worksheet .write (k,0,gd)
worksheet .write (k,1,ag)
worksheet .write (k,2,day)
k=k+1
worlbook.save('date2.xls')
print('爬取完毕!')
#以下是我自己写的画图代码
import matplotlib as mpl
import numpy as np
import pandas as pd
import matplotlib .pyplot as plt
import matplotlib
cf=pd.read_excel ('date2.xls')
#print(cf)
ga=cf.loc [:,['黄金','日期','白银']]
#print(ga)
# #将日期转化为时间序列
ga['日期']=pd.to_datetime(cf['日期'])
#将日期升序排列
ga=ga.set_index('日期').sort_index(ascending=True )
#print(ga)
#
zhfont1 = matplotlib.font_manager.FontProperties(fname="SourceHanSansSC-Bold.otf", size=18)
y1=ga['黄金']
x1=range(len(y1))
y2=ga['白银']
x2=range(len(y2))
plt.figure(1)
plt.subplot(221)
plt.plot(x1,y1,'r-')
ypoints = np.array([1859.07075,1859.07075]*40)
plt.plot(ypoints, linestyle = 'dotted',color = 'black')
plt.xlabel("time")
plt.ylabel("ug")
plt.subplot(224)
plt.plot(x2,y2,'b-')
ypoints = np.array([23.842875,23.842875]*40)
plt.plot(ypoints, linestyle = 'dotted',color = 'black')
plt.xlabel("time")
plt.ylabel("ag")
plt.show()
python爬虫,银行数据
最新推荐文章于 2024-04-07 21:28:05 发布