【实例】python bs4 beautifulsoup + urllib.request 提取网址

>>> import re
>>> from bs4 import BeautifulSoup
>>> import urllib.request
>>> import lxml
>>> import requests
>>> url = 'http://www1.szu.edu.cn/board/'
>>> page=requests.get(url).text
>>> pagesoup=BeautifulSoup(page,'lxml')
>>> for link  in pagesoup.find_all(name='a',attrs={"href":re.compile(r'^http:')}):
...     print(link.get('href'))
...
http://www.szu.edu.cn
http://news.szu.edu.cn
http://210.39.3.155:9090/goLogin.do
http://www.szu.edu.cn/yxjg/xyxb.htm
http://www.szu.edu.cn/yxjg/znbm.htm
http://www.miibeian.gov.cn

>>>

--------------------------------

>>> html = requests.get(url)
>>> soup = BeautifulSoup(html.text,"lxml")

>>> print(soup.get_text())

---------------------

>>> # -*- coding: utf-8 -*-
...
>>> import re
>>> from bs4 import BeautifulSoup
>>> import urllib.request
>>> import lxml
>>> import requests
>>> url = 'http://www1.szu.edu.cn/board/'
>>> html = requests.get(url)
>>> soup = BeautifulSoup(html.text,"lxml")

>>> print(soup.get_text())

-----------------------------------

>>> webdata = requests.get(url)
>>> webdata.encoding = 'GBK'

>>> print(webdata.text)

-----