先利用爬虫利用百度糯米提供的api来采集北京当天的团购信息,保存为numi.html
import xml.etree.ElementTree as ET
import os
class Nuomi():
def __init__(self):
self.numi=[]
def Parse(self,filepath):
tree=ET.parse(filepath)
root =tree.getroot()
for url in root.iter(‘url‘):
nuomi_lei={}
data=url.find(‘data‘)
if data is not None:
display=data.find(‘display‘)
if display is not None:
try:
nuomi_lei[‘title‘]=display.find(‘title‘).text
except Exception as e:
print("No title")
try:
nuomi_lei[‘businessTitle‘]=display.find(‘businessTitle‘).text
except Exception as e:
print ("No businessTitle")
try:
nuomi_lei[‘value‘] =display.find(‘value‘).text
except Exception as e:
print ("No value")
try:
nuomi_lei[‘price‘]=float(display.find(‘price‘).text)
except Exception as e:
print("No pire")
self.numi.append(nuomi_lei)
return(self.numi)
if __name__ == ‘__main__‘:
nuomi=Nuomi()
date=nuomi.Parse(‘numi.html‘)
print(len(date))