exploitdbWebApp.py

# -*- codinig: utf-8 -*-
import scrapy
import os
from scrapy.exceptions import CloseSpider
import facebook


class exploitdbWebApp(scrapy.Spider):
    name = "exploitdbWebApp"
    allowed_domains = ["exploit-db.com"]
    start_urls = [
        "https://www.exploit-db.com/webapps/"
    ]
    global ult
    if os.path.isfile('baseWebApp.txt') and os.stat('baseWebApp.txt').st_size == 0:
        os.remove('baseWebApp.txt')        
    if os.path.isfile('baseWebApp.txt'):
        arq = open('baseWebApp.txt', 'r')
        ult = arq.readlines()[1].rstrip("\n")
        arq.close()
    else:
        os.mknod('baseWebApp.txt')
        ult = ''

    def parse(self,response):
        global ult
    	datas = response.selector.xpath('//tr/td[@class="date"]/text()').extract()
    	links = response.selector.xpath('//tr/td[5]/a/@href').extract()
    	descs = response.selector.xpath('//tr/td[5]/a[@href]/text()').extract()

    	for data, desc, link in zip(datas, descs, links):
    		if desc.encode('utf-8') != ult and ult == '':
    			with open('baseWebApp.txt', 'a+') as arq:
    				arq.write(data.strip()+'\n')
    				arq.write(desc.encode('utf-8')+'\n')
    				arq.write(link+'\n\n')
    				arq.close()
    			i = 0
    		elif desc.encode('utf-8') != ult:
    			with open('aux.txt','a+') as arq:
    				arq.write(data.strip()+'\n')
    				arq.write(desc.encode('utf-8')+'\n')
    				arq.write(link+'\n\n')
    				arq.close()
    			i = 1
    		else:
    			i = 0
    			break

    	if not i:
            if os.path.exists('aux.txt'):
                os.remove('baseWebApp.txt')
                os.rename('aux.txt', 'baseWebApp.txt')
                # HERE YOU PUT THE TOKEN OF YOUR PAGE ON FACEBOOK
                access_token = "HERE YOU PUT THE TOKEN OF YOUR PAGE ON FACEBOOK"
                api = facebook.GraphAPI(access_token)
                total = 0
                arq = open('baseWebApp.txt','r')
                linhas = arq.readlines()
                for i in linhas:
                    if i == '\n':
                        total = total + 1
                a = 0
                b = 3
                lista = []
                for i in range(total):
                    xxx = linhas[a:b]
                    lista.append(xxx)
                    xxx = ''
                    a = b + 1
                    b = a + 3
                lista.reverse() 
                for i in lista:
                    x = ''.join(i)
                    api.put_wall_post(x)

            raise CloseSpider('[+] BASE ATUALIZADA [+]')
        else:
            try:
                proxima_pagina = response.xpath(
                    '//a[@href and contains(.,"next")]/@href').extract()[0]
                if proxima_pagina:
                    yield scrapy.Request(url=proxima_pagina, callback=self.parse)
            except:
                pass