数据获取beautifulSoup

1  代码

from requests import get
from bs4 import BeautifulSoup
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.pyplot as plt2
 
headers = {
 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36 QIHU 360SE'
}
url="http://fund.eastmoney.com/GP_jzzzl.html#os_0;isall_0;ft_;pt_2"
response=get(url,headers=headers)
#print(response.status_code)
response.encoding = 'utf8'
html=response.text
soup=BeautifulSoup(html,"html.parser")

#获取基金代码
listBZDM=[]
a6=soup.find_all("td",class_="bzdm")
for i in range(10):
    listBZDM.append(a6[i].getText())
 
#获取单位净值
listDWJZ1=[]
listDWJZ2=[]
a6=soup.find_all("td",class_="dwjz")
for i in range(0,20,2):
    listDWJZ2.append(a6[i].getText())
    listDWJZ1.append(a6[i+1].getText())
 
df=pd.DataFrame()
df["bzdm"]=listBZDM
df["dwjz2"]=listDWJZ2
df["dwjz1"]=listDWJZ1
#转换成数字
df["dwjz2"]=df["dwjz2"].map(lambda x: float(x))
df["dwjz1"]=df["dwjz1"].map(lambda x: float(x))

#计算差值
df["cha"]=df["dwjz2"]-df["dwjz1"]
df.plot()
plt.show()
#print(df)
    

2  结果

       bzdm   dwjz2   dwjz1
0  005106  1.9773  1.8988
1  014064  1.9759  1.8975
2  161724  1.7032  1.6446
3  013596  1.7020  1.6435
4  001678  1.2946  1.2539
5  003634  1.9762  1.9143
6  015468  0.9186  0.8899
7  013471  0.9340  0.9082
8  013472  0.9328  0.9070
9  013275  1.7940  1.7450