Web scraping Project

hackmageddon/hackmageddon/items.py

@@ -0,0 +1,22 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class HackmageddonItem(scrapy.Item):
+    # define the fields for your item here like:
+    Year = scrapy.Field()
+    dat = scrapy.Field()
+    Author = scrapy.Field()
+    Target = scrapy.Field()
+    Description = scrapy.Field()
+    Attack = scrapy.Field()
+    Target_class = scrapy.Field()
+    Attack_class = scrapy.Field()
+    Country = scrapy.Field()
+

hackmageddon/hackmageddon/middlewares.py

@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class HackmageddonSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

hackmageddon/hackmageddon/pipelines.py

@@ -0,0 +1,45 @@
+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+from scrapy.exceptions import DropItem
+from scrapy.exporters import CsvItemExporter
+
+class ValidateItemPipeline(object):
+
+    def process_item(self, item, spider):
+        if not all(item.values()):
+            raise DropItem("Missing values!")
+        else:
+            return item
+
+class WriteItemPipeline(object):
+
+    def __init__(self):
+        self.filename = 'gplay1.csv'
+
+    def open_spider(self, spider):
+        self.csvfile = open(self.filename, 'wb')
+        self.exporter = CsvItemExporter(self.csvfile)
+        self.exporter.start_exporting()
+
+    def close_spider(self, spider):
+        self.exporter.finish_exporting()
+        self.csvfile.close()
+
+    def process_item(self, item, spider):
+        self.exporter.export_item(item)
+        return item
+

hackmageddon/hackmageddon/settings.py

@@ -0,0 +1,93 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for hackmageddon project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'hackmageddon'
+
+SPIDER_MODULES = ['hackmageddon.spiders']
+NEWSPIDER_MODULE = 'hackmageddon.spiders'
+
+ITEM_PIPELINES = {'hackmageddon.pipelines.ValidateItemPipeline': 100,
+					'hackmageddon.pipelines.WriteItemPipeline': 200}
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'hackmageddon (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+#DOWNLOAD_DELAY = 3
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+#COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'hackmageddon.middlewares.HackmageddonSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'hackmageddon.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+#    'hackmageddon.pipelines.HackmageddonPipeline': 300,
+#}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

hackmageddon/hackmageddon/spiders/__init__.py

@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

hackmageddon/hackmageddon/spiders/hack_spider.py

@@ -0,0 +1,87 @@
+from hackmageddon.items import HackmageddonItem
+from scrapy import Spider, Request
+from selenium import webdriver
+from scrapy.selector import HtmlXPathSelector
+import re
+import time
+
+
+class HackmageddonSpider(Spider):
+	name = "hackmageddon"
+	allowed_urls = ["http://www.hackmageddon.com/"]
+	start_urls = ["http://www.hackmageddon.com/2015/07/06/16-30-jun-2015-cyber-attacks-timeline/"]
+
+	# def __init__(self):
+
+	# 	self.driver = webdriver.Chrome()
+
+
+
+
+
+
+
+
+	def parse(self,response,i=[0]):
+
+		#while True:
+
+		i[0] += 1		
+
+
+		if i[0] != 1:
+			if (re.findall('^(?!.*{}).*{}.*$'.format('statistics','\d+-\d+-\w+-\d+'),response.meta['link']) == []):
+				link = response.xpath('//a[@rel="next"]/@href').extract_first()
+				yield Request(link, callback= self.parse,meta={'link': link})
+			elif (re.findall('^(?!.*{}).*{}.*$'.format('statistics','\d+-\d+-\w+'),response.meta['link']) == []):
+				link = response.xpath('//a[@rel="next"]/@href').extract_first()
+				yield Request(link, callback= self.parse,meta={'link': link})
+
+
+		rows = response.xpath('//tbody[@class="row-hover"]//tr')
+		if not rows:
+			rows = response.xpath('//tbody/tr')	
+		print('='*30)
+		print(i[0])
+		print('='*30)
+
+
+		for row in rows:
+			year = response.xpath('//a[@rel="tag"]/text()').extract()[0]
+			date = row.xpath('./td[2]/text()').extract()
+			author = row.xpath('./td[3]/text()').extract()
+			target = row.xpath('./td[4]/text()').extract()
+			description = row.xpath('./td[5]/text()').extract()
+			if not description:
+				description = row.xpath('./td[5]/a/text()').extract()
+			attack = row.xpath('./td[6]/text()').extract()
+			target_class = row.xpath('./td[7]/text()').extract()
+			attack_class = row.xpath('./td[8]/text()').extract()
+			country = row.xpath('./td[9]/text()').extract()
+
+			item = HackmageddonItem()
+			item['Year'] = year
+			item['dat'] = date
+			item['Author'] = author
+			item['Target'] = target
+			item['Description'] = description
+			item['Attack'] = attack
+			item['Target_class'] = target_class
+			item['Attack_class'] = attack_class
+			item['Country'] = country
+			yield item	
+
+		if True:	
+			link = response.xpath('//a[@rel="next"]/@href').extract_first()
+			yield Request(link,callback=self.parse,meta={'link': link})		
+
+
+
+
+
+
+
+
+
+
+

hackmageddon/scrapy.cfg

@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = hackmageddon.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = hackmageddon