タグ内の全データを取得するためのBeautifulSoupとPython

# -*- coding:utf-8 -*-
# python 2.7
#XiaoDeng
#http://tieba.baidu.com/p/2460150866
#Tag manipulation


from bs4 import BeautifulSoup
import urllib.request
import re


#If it's a URL, you can use this to read the page
#html_doc = "http://tieba.baidu.com/p/2460150866"
#req = urllib.request.Request(html_doc)  
#webpage = urllib.request.urlopen(req)  
#html = webpage.read()



html = """


<タイトル

ヤマネの話




ヤマネの物語




むかしむかし、あるところに3人の姉妹がいました。



<未定義



,



ラシー


 そして



ティリー


;



レイシー



井戸の底に住んでいた。



...



"""
soup = BeautifulSoup(html, 'html.parser') # document object


#find a tag, will only find a a tag
#print(soup.a)#




for k in soup.find_all('a'):
    print(k)
    print(k['class'])# look up the class attribute of the a tag
    print(k['id'])#check the id value of the a tag
    print(k['href'])#check the href value of the a tag
    print(k.string)#check the string of the a tag
    #tag.get('calss'), which can also achieve this effect
    


<未定義





for k in soup.find_all('a'):
    print(k)
    print(k['class'])# look up the class attribute of the a tag
    print(k['id'])#check the id value of the a tag
    print(k['href'])#check the href value of the a tag
    print(k.string)#check the string of the a tag
    #tag.get('calss'), which can also achieve this effect