Traceback (most recent call last):
File "E:/www/py/h4.py", line 16, in <module>
soup=BeautifulSoup(html_doc,"html.parser",from_encoding="utf-8")
File "D:\python\lib\site-packages\bs4\__init__.py", line 153, in __init__
builder = builder_class()
File "D:\python\lib\site-packages\bs4\builder\_htmlparser.py", line 39, in __init__
return super(HTMLParserTreeBuilder, self).__init__(*args, **kwargs)
TypeError: __init__() got an unexpected keyword argument 'strict'
2016-10-30
from bs4 import BeautifulSoup
import re
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b>The Dormouse's story</b></p>
<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>
<p class="story">...</p>
"""
soup=BeautifulSoup(html_doc,"html.parser",from_encoding="utf-8")
print("a所有链接")
links=soup.find_all("a")
for link in likns:
print(link.name,link.get_text(),link["href"])
举报
