PythonStudy_爬取网页title和摘要

# coding=utf-8
import re
from urllib.request import urlopen
from bs4 import BeautifulSoup

# 获取网页标题
def get_url_Title_Description(url):
    # 获取网页全部信息content
    content = urlopen(url).read().decode('utf-8')

    # 正则表达式匹配标题
    pat = r'<title>(.*?)</title>'
    title = re.findall(pat,content)

    # 提取网页摘要
    soup = BeautifulSoup(content,"html.parser")
    description = soup.find(attrs={"name":"description"})['content']

    # 返回标题和摘要
    return (title[0],description)

# ----------test----------------
# url = "http://www.sina.com.cn/"
# title,dsp = get_url_Title_Description(url)
# print(title)
# print(dsp)