爬取簡書標題和摘要

有些小瑕疵不知道爲啥爬取的標題個數與摘要個數不是整個頁面的，而且兩者也不相等，不過是第一次做出來，簡單記錄一下啦~~~~

import urllib.request
import re
import os

def url_open(url):
    req=urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36')
    response=urllib.request.urlopen(url)
    html=response.read().decode('utf-8')
    return html

def get_title(html):
    p=r'<a.*?class="title".*?target="_blank".*?href=".*?">(.*?)</a>'
    t=r'<p.*?class="abstract">(.*?)</p>'
    titlelist=re.findall(p,html,re.S)
    abstractlist=re.findall(t,html,re.S)
    '''
    for each in titlelist:
        print(each)

    for each in abstractlist:
        print(each)
    '''
    i=len(titlelist)

    with open(r'essay.txt','w') as f:
        for x in range(i-1):
            f.write(str(x+1)+titlelist[x]+'\n'+abstractlist[x]+'\n')

if __name__=='__main__':
    os.mkdir("E:\Title")
    os.chdir("E:\Title")
    url='http://www.jianshu.com/'
    get_title(url_open(url))