#!/usr/bin/env python
import requests, bs4, urllib, sys, re, math

def getHTML(url) :
	headers = { 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36',
		'Accept-Encoding': 'gzip, deflate, br',
		'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
		'Upgrade-Insecure-Requests': '1',
		'Host': 'www.navimro.com'
	}
	resp = requests.get(url, headers = headers)
	resp.raise_for_status()
	resp.encoding='UTF-8'
	html = resp.text
	bs = bs4.BeautifulSoup(html, 'html.parser')
	return bs;

mainUrl = "https://www.navimro.com"

mainBs = getHTML(mainUrl)
tb = mainBs.select('table.category-area td')

for i in range(len(tb)) :
	dt = tb[i].select('dt')[0].getText().strip()
	dd = tb[i].select('dd')
	for j in range(len(dd)) :
		dd2Text = dd[j].getText().strip()
		dd2link = mainUrl + dd[j].select('a')[0].get('href')
		depth2bs = getHTML(dd2link)
		d3tb = depth2bs.select('ul.lv3-active a')
		for k in range(len(d3tb)) :
			d3Text = d3tb[k].getText().strip()
			d3link = mainUrl + d3tb[k].get('href')
			print(dt + ">" + dd2Text + ">" + d3Text + "\t" + d3link)