#!/Users/maddiekorea/Workspace/bin/python
#version 201904
import requests, bs4, urllib, sys, re, math, logging, os
from urllib import parse
from datetime import datetime
import subprocess
startTime = datetime.now()

url = "https://www.vitsonmro.com/goods/goodsDetail.do"

def query(keyword) :
	query = keyword.encode('utf-8')
	return query

def parameters( query ) :
	data = {
		'goodsNo': query
	}
	return data

def headers() :
	headers = { 
		'Content-Type': 'application/x-www-form-urlencoded',
		'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
		'Accept-Encoding': 'gzip, deflate',
		'Accept-Language': 'ko-KR,ko;q=0.9,en-US;q=0.8,en;q=0.7',
		'Cache-Control': 'no-cache',
		'Connection': 'keep-alive',
		'Host': 'www.vitsonmro.com',
		'Pragma': 'no-cache',
		'Referer': 'https://www.vitsonmro.com',
		'Save-Data': 'on',
		'Upgrade-Insecure-Requests': '1',
		'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'
	}
	return headers

def pageRequest( url, parameters, headers ) :
	resp = requests.get(url, params = parameters, headers = headers)
	resp.raise_for_status()
	resp.encoding='utf-8'
	html = resp.text
	return html

term = str(sys.argv[1])

htmlHead = pageRequest(url, parameters(query(term)), headers())
bs = bs4.BeautifulSoup(htmlHead, 'html.parser')

img = []

imgArr = bs.select('div#product_photo ul.goods_view_slider li img')

for i in range(len(imgArr)) :
	Rimg = imgArr[i].get('src')
	img.insert(i,Rimg)

directory = '/home/maddiekorea/imgs/crawl/' + datetime.now().strftime("%Y%m%d") + "_vitson"
if not os.path.exists(directory) : os.makedirs(directory)

for i in range(len(img)) :
	ext = img[i].split(".")
	index = len(ext) - 1
	extension = ext[index]
	filename = directory + "/" + term + "_" + str(i) + "." + extension
	shellcmd = "wget -O " + filename + " " + '"' + img[i] + '"'
	print(term + "\t" + img[i])
	executeCrawl = subprocess.Popen(shellcmd,stdout=subprocess.PIPE,shell=True)
	try: 
		executeCrawl.communicate(timeout=80)
	except subprocess.TimeoutExpired:
		executeCrawl.terminate()
	continue

consumtime	 = datetime.now() - startTime
logging.warning(term + "\t" + str(consumtime))