网页信息数据-数据分析（6）

import urllib.request;
from bs4 import BeautifulSoup;

response = urllib.request.urlopen("file:///C:6.1/html.html")
html = response.read()
html

soup = BeautifulSoup(html,"lxml")
soup
soup.find('tr')
soup.find_all('tr')

处理json数据

# -*- coding: utf-8 -*-
import json;
import urllib.request;

response = urllib.request.urlopen('file:///D:/PA//6.2//json.json');
jsonString = response.read();

jsonObject = json.loads(jsonString.decode())

jsonObject['employees']
jsonObject['employees'][0]
jsonObject['employees'][0]['lastName']