2018-11-19

from urllib import request
import time
from lxml import etree

def autoBlog():
    url = 'https://www.jianshu.com/p/0b4c9e9931f5'
    headers = {
        "Referer": "https://www.jianshu.com/",
        "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36"
    }
    req = request.Request(url=url,headers=headers)
    response = request.urlopen(req)
    content = response.read().decode()
    #复制html中的文本的XPath
    ##/html/body/div[1]/div[2]/div[1]/h1
    # print(content)
    xpath_content = etree.HTML(content)
    new_content = xpath_content.xpath('/html/body/div[1]/div[2]/div[1]/h1/text()')
    #print(new_content)
    with open('3.txt','w+',encoding='utf-8') as f:
        for i in new_content:
            f.writelines(i)
i=0
while i<100:
    autoBlog()
    i=i+1
    print(i)