python爬取军事新闻网站

使用了requests和BeautifulSoup库
文档地址: requests
bs4

---

#!usr/bin/python
# -*- coding:utf8 -*-
"""
https://mil.news.sina.com.cn/roll/index.d.html
获取”中国军情“N页的爬虫，写入json文件中, 每一页的数据写入一个json文件
"""
import os
import json
import requests
from bs4 import BeautifulSoup


class WebSpider(object):

    def __init__(self, page_count):
        print('----------------loading...-----------------')
        self.url = 'https://mil.news.sina.com.cn/roll/index.d.html'
        self.headers = {
   "User-Agent": "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)"