beatiful soup用法

#!/usr/bin/env Python
# coding=utf-8
import requests,os
from bs4 import BeautifulSoup as bs
from lxml import etree


"""import sys
reload(sys)
sys.setdefaultencoding("utf-8")"""


path=r"E:\historymaterials_day"
filenames=os.listdir(path)
filenameslist=[]


for i in range(len(filenames)):
filenameslist.append(filenames[i].split(".")[0])




headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'}
n=0
for code in filenameslist:
    if n<1:
        n+=1
        #r = requests.get("http://vip.stock.finance.sina.com.cn/corp/go.php/vMS_FuQuanMarketHistory/stockid/"+code+".phtml?year=2017&jidu=1")
        r=requests.get("http://money.finance.sina.com.cn/corp/go.php/vMS_FuQuanMarketHistory/stockid/600000.phtml?year=2018&jidu=1")
#        r.encoding='utf-8'
        r.encoding=r.apparent_encoding
        html=r.text#.encode("utf-8")
#        html_doc=html.decode("utf-8","ignore")
        bs222=bs(html,"html.parser")
        print type(aa)
        print aa.text

注意，bs222不能写成bs ，不能和bs模块重名

遇到乱码时的主要方法：

前边加上

#!/usr/bin/env Python

# coding=utf-8

import sys

reload(sys)

sys.setdefaultencoding("utf-8")

下载时候用r.encoding=“”进行编码

    html=r.text

        bs222=bs(html,"html.parser")

        print bs222.prettify()

r.text 解码成文本

bs222.prettify（）用来进行格式化输出