网页解析三种方法（beautifulsoup）

# -*- coding:utf-8 -*-
from bs4 import BeautifulSoup
import re//正则
html_doc = '''


   


   
   happy
   baidu


'''
soup = BeautifulSoup(html_doc,'html.parser',from_encoding='utf-8')
links = soup.find_all('a')
for link in links:
    print(link.name,link.get_text(),link["href"])
print('特定')
link = soup.find('a',href='http://www.baidu.com')
print(link.name,link.get_text(),link["href"])
print('正则匹配')
link = soup.find('a',href=re.compile(r"moo"))
print(link.name,link.get_text(),link["href"])
print('获取script')
script = soup.find('script')
print(script.name,script.get_text())