爬取简书网

爬取简书网 requests ，csv

**这里只爬取了一个页面 只解析了一个 **

import requests
import pymysql
from lxml import etree

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.75 Safari/537.36'}
url = 'https://www.jianshu.com/u/9104ebf5e177?order_by=shared_at&page=3'



def get_url(url):
    resp = requests.get(url,headers=headers)
    print(resp.status_code)
    tree = etree.HTML(resp.text)
    li_list = tree.xpath('//*[@id="list-container"]/ul/li')
    for li in li_list:
        name = li.xpath('./div/a/text()')[0]
        print(name)
get_url(url)