Boston_Spyder.py

#-*- coding：utf-8 -*-
# &Author AnFany

frombs4importBeautifulSoupasbs
importurllib

html=urllib.request.urlopen("http://lib.stat.cmu.edu/datasets/boston")
bsObj=bs(html.read(), "html5lib")
namest=str(bsObj.body.get_text())


sign=0
name= []
forhhinnamest.split('\n'):
if6<sign<21:
#获取字段名字
name.append(hh[:7].replace(' ',''))

ifsign==21:
fornaminname:
exec('%s = []'%nam)

ifsign>21:
#获得字段对应的数据
datalist= [datafordatainhh.split(' ') ifdata!='']
ifsign%2==0:
foriinrange(len(datalist)):
eval(name[i]).append(datalist[i])
else:
foriinrange(len(datalist)):
eval(name[11+i]).append(datalist[i])
sign+=1

#有序的字典形式,按添加的序列输出
fromcollectionsimportOrderedDict
datadict=OrderedDict({})

forkeynameinname:
datadict[keyname] =eval(keyname)


#写入文件
importpandasaspd
df=pd.DataFrame(datadict)
df.to_csv(r'C:\Users\GWT9\Desktop\Boston.csv', index=False)
print('完毕')