5 files changed, 184 insertions, 0 deletions
diff --git a/scripts/crawler/tbc_web_crawler/__init__.py b/scripts/crawler/tbc_web_crawler/__init__.py
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/scripts/crawler/tbc_web_crawler/__init__.py
diff --git a/scripts/crawler/tbc_web_crawler/settings.py b/scripts/crawler/tbc_web_crawler/settings.py
new file mode 100644
index 0000000..03ba836
--- /dev/null
+++ b/scripts/crawler/tbc_web_crawler/settings.py
@@ -0,0 +1,86 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for tbc_web_crawler 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 = 'tbc_web_crawler'
+
+SPIDER_MODULES = ['tbc_web_crawler.spiders']
+NEWSPIDER_MODULE = 'tbc_web_crawler.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'tbc_web_crawler (+http://www.yourdomain.com)'
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+CONCURRENT_REQUESTS=100
+
+# 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 = {
+#    'tbc_web_crawler.middlewares.MyCustomSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+	#'scrapy.downloadermiddlewares.retry.RetryMiddleware': None
+#    'tbc_web_crawler.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+#    'tbc_web_crawler.pipelines.SomePipeline': 300,
+#}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+# NOTE: AutoThrottle will honour the standard settings for concurrency and delay
+#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
+# 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'
diff --git a/scripts/crawler/tbc_web_crawler/spiders/__init__.py b/scripts/crawler/tbc_web_crawler/spiders/__init__.py
new file mode 100644
index 0000000..ebd689a
--- /dev/null
+++ b/scripts/crawler/tbc_web_crawler/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.
diff --git a/scripts/crawler/tbc_web_crawler/spiders/items.py b/scripts/crawler/tbc_web_crawler/spiders/items.py
new file mode 100644
index 0000000..9dda20f
--- /dev/null
+++ b/scripts/crawler/tbc_web_crawler/spiders/items.py
@@ -0,0 +1,18 @@
+import scrapy
+
+
+class TbcErrorItems(scrapy.Item):
+
+
+	chapter_name = scrapy.Field()
+	chapter_urls = scrapy.Field()
+	completed_book_urls = scrapy.Field()
+	number_of_errors = scrapy.Field()
+	error_messages = scrapy.Field()
+	
+	
+
+class TbcBrokenItems(scrapy.Item):
+	
+	broken_url = scrapy.Field()
+	broken_status = scrapy.Field()
diff --git a/scripts/crawler/tbc_web_crawler/spiders/tbc_spider.py b/scripts/crawler/tbc_web_crawler/spiders/tbc_spider.py
new file mode 100644
index 0000000..9688e70
--- /dev/null
+++ b/scripts/crawler/tbc_web_crawler/spiders/tbc_spider.py
@@ -0,0 +1,76 @@
+import scrapy
+from items import TbcErrorItems, TbcBrokenItems 
+from scrapy.utils.response import get_base_url
+from scrapy.utils.url import urljoin_rfc
+from scrapy.http import Request
+
+import os, json
+
+if os.path.isfile('items.json'):
+	os.remove('items.json')
+else:
+	pass
+	
+class TbcSpider(scrapy.Spider):
+
+	name = "tbc_spider"  # Name of the crawler. Use this name when crawling from the terminal, for eg - scrapy crawl tbc_spider
+	
+	start_urls = ["http://tbc-python.fossee.aero.iitb.ac.in/completed-books/"]
+	handle_httpstatus_list = [404, 500, 502] # A list containing HTTP error codes.
+	
+	def parse(self,response):
+		""" This function looks for book links and returns the url"""
+		
+		for book_link in response.xpath('//a[contains(@href,"book-details")]/@href').extract():
+			""" Searches for links with "book-details" in it """
+		
+			first_base_url = get_base_url(response)
+			first_relative_url = urljoin_rfc(first_base_url,book_link)
+			"""creates a url to be returned to the next function."""
+		
+			yield scrapy.Request(first_relative_url,callback=self.parse_book_contents)
+		
+			
+			
+	def parse_book_contents(self, response):
+		
+		""" This function looks for chapter links through each book link and returns the url"""
+	
+		for chapter_link in response.xpath ('//a[contains(@href,"convert-notebook")]/@href').extract():
+			""" Searches for chapters in each book list"""
+			second_base_url = get_base_url(response).split('/book-details')[0]
+			second_relative_url = urljoin_rfc(second_base_url,chapter_link)
+			"""creates a url to be returned to the next function."""
+			
+			yield scrapy.Request(second_relative_url,callback=self.parse_chapter_details)
+			
+			
+
+	def parse_chapter_details(self, response):
+		 
+		if not response.xpath('//h1/text()').extract():
+			chapter_details = [response.url]
+		else:
+			chapter_details = response.xpath('//h1/text()').extract()
+
+		
+		error_tag = response.xpath('//div[@class="output_subarea output_text output_error"]') 
+		error_list = [error_notifications for error_notifications \
+		              in response.xpath \
+		              ('//div[@class="output_subarea output_text output_error"]/span/text()').extract()]
+
+		if response.status in self.handle_httpstatus_list:
+			broken_items = TbcBrokenItems()
+			broken_items['broken_url'] = response.url
+			broken_items['broken_status'] = response.status
+			yield broken_items
+		else:
+			if len(error_tag) != 0:
+				items = TbcErrorItems()
+				items ['chapter_name'] = chapter_details[0]
+				items ['chapter_urls'] = response.url
+				items ['number_of_errors'] = len (error_tag)
+				#items ['completed_book_urls'] = response.request.headers.get('Referer', None)
+				#items ['error_messages'] = error_list
+				yield items
+