爬取CSDN的瀑布流

import requests
import time
from lxml import etree
import pymongo
import re


class CSDN():
    def __init__(self):
        url = 'https://blog.csdn.net/'
        self.headers = {
            'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3',
            'accept-encoding': 'gzip, deflate, br',
            'accept-language': 'zh-CN,zh;q=0.9',
            'cache-control': 'max-age=0',
            'cookie': #填自己的,
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36',
            'x-tingyun-id': 'wl4EtIR_7Is;r=364167216'
        }
        self.lst = []
        self.num = 0
        content = requests.get(url, headers=self.headers).text