Python爬取知乎网站

import urllib.request
import re

url = 'http://daily.zhihu.com/'
def get_html(url):
    html = urllib.request.urlopen(url).read()
    html = html.decode('utf-8')
    return html

def get_url_num(html):
    res = re.compile('<a href="/story/(.*?)"')
    url_nums = re.findall(res,html)
    urls = []
    for url_num in url_nums:
        urls.append('http://daily.zhihu.com/story/' + url_num)
    return urls

def get_content(newurl):
    newurl_html = get_html(newurl)
    re_title = re.compile('<title>(.*?)</title>')
    title = re.findall(re_title,newurl_html)
    re_content =  re.compile('<div class="content">\\n<p>(.*?)</div>',re.S)
    contents = re.findall(re_content,newurl_html)
    print(title)
    for content in contents:
        content = content.replace('<p>','')
        content = content.replace('</p>','')
        content = content.replace('<strong>','')
        print(content)


for newurl in get_url_num(get_html(url)):
    get_content(newurl)

PS：

　　1、爬取的内容里面还有链接没有处理干净，虽然别人给了个源码，但是自己看不懂！（还要加油！↖(^ω^)↗↖(^ω^)↗）

　　2、视频里面说要模拟浏览器登入，但是我这里没有模拟还是可以正常的爬取（我用的是Python3）