bs4数据解析基础

import requests
from bs4 import BeautifulSoup

if __name__ == "__main__":
    # headers = {
    #     'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    # }   # UA伪装

    fp = open('./text.html','r',encoding='utf-8')
    soup = BeautifulSoup(fp,'lxml') #将本地的html文档中的数据加载到该对象中
    # print(soup)
    # print(soup.input['href']) # soup.tagName 返回的是html文件第一次出现的tagname对应的标签
    # print(soup.find('div')) # 等同于 soup.div
    # print(soup.find('div',class_ = 'hzbtabs')) # 属性定位
    # print(soup.find_all("div"))
    # print(soup.select(".hzbtabs"))
    # print(soup.select('.hzbbannertxt >a')[0]['href'])