added cleaned code

Jason/Scrapy_BloomingDale/blmdl/items.py

@@ -0,0 +1,18 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/items.html
+
+from scrapy import Item, Field
+
+
+class BlmdlItem(Item):
+	brand = Field()
+	prod_name = Field()
+	price_reg = Field()
+	price_dis = Field()
+#	desc_list = Field()
+#	prod_image = Field()
+#	full_file_name = Field()

Jason/Scrapy_BloomingDale/blmdl/middlewares.py

@@ -0,0 +1,103 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class BlmdlSpiderMiddleware(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(self, 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(self, 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(self, 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(self, 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)
+
+
+class BlmdlDownloaderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the downloader 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_request(self, request, spider):
+        # Called for each request that goes through the downloader
+        # middleware.
+
+        # Must either:
+        # - return None: continue processing this request
+        # - or return a Response object
+        # - or return a Request object
+        # - or raise IgnoreRequest: process_exception() methods of
+        #   installed downloader middleware will be called
+        return None
+
+    def process_response(self, request, response, spider):
+        # Called with the response returned from the downloader.
+
+        # Must either;
+        # - return a Response object
+        # - return a Request object
+        # - or raise IgnoreRequest
+        return response
+
+    def process_exception(self, request, exception, spider):
+        # Called when a download handler or a process_request()
+        # (from other downloader middleware) raises an exception.
+
+        # Must either:
+        # - return None: continue processing this exception
+        # - return a Response object: stops process_exception() chain
+        # - return a Request object: stops process_exception() chain
+        pass
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

Jason/Scrapy_BloomingDale/blmdl/pipelines.py

@@ -0,0 +1,27 @@
+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+from scrapy.exporters import CsvItemExporter
+
+class WriteItemPipeline(object):
+
+    def __init__(self):
+        self.filename = 'bloomingdale_0916.csv'
+
+    def open_spider(self, spider):
+        self.csvfile = open(self.filename, 'wb')
+        self.exporter = CsvItemExporter(self.csvfile, delimiter='\t')
+        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

Jason/Scrapy_BloomingDale/blmdl/settings.py

@@ -0,0 +1,90 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for blmdl project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     https://doc.scrapy.org/en/latest/topics/settings.html
+#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'blmdl'
+
+SPIDER_MODULES = ['blmdl.spiders']
+NEWSPIDER_MODULE = 'blmdl.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
+
+# 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 https://doc.scrapy.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 https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'blmdl.middlewares.BlmdlSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'blmdl.middlewares.BlmdlDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See https://doc.scrapy.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+    'blmdl.pipelines.WriteItemPipeline': 200,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://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 https://doc.scrapy.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'

Jason/Scrapy_BloomingDale/blmdl/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.

Jason/Scrapy_BloomingDale/blmdl/spiders/blmdl_spider.py

@@ -0,0 +1,91 @@
+from scrapy import Spider, Request
+from blmdl.items import BlmdlItem
+import re
+import numpy as np
+import urllib.request 
+import urllib.error
+import os.path
+
+class BlmdlSpider(Spider):
+	name = 'blmdl_spider'
+	allowed_urls = ['https://www.bloomingdales.com/']
+	start_urls = ['https://www.bloomingdales.com/shop/womens-apparel/tops-tees/Pageindex,Productsperpage/1,96?id=5619']
+
+	def parse(self, response):
+
+
+		pagelist_urls = ["https://www.bloomingdales.com/shop/womens-apparel/tops-tees/Pageindex,Productsperpage/{},96?id=5619".format(i) for i in range(1, 6)]
+
+		# Loop all the different product pages
+		for url in pagelist_urls:
+			print('#'*50)
+			print(url)
+			print('#'*50)
+
+		#  Look into a particular page	
+			yield Request(url = url, callback = self.parse_product_page)
+
+	def parse_product_page(self, response):
+
+		# Collect all the products into a list
+		products = response.xpath('//li[@class="small-6 medium-4 large-3 columns"]')
+
+		# Loop into the list to see the information of each product
+		for product in products:
+			# Get the link to the detailed page for a single item. 
+			url_product = product.xpath('.//a[@class="productDescLink"]/@href').extract_first()
+			price_reg = product.xpath('.//div[@class="productDetail"]//span[@class="regular"]/text()').extract_first().strip()
+
+			# If there is a discount price then use it. If not just use the regular price. 
+			if product.xpath('.//div[@class="productDetail"]//span[@class="discount"]/text()').extract_first() != None:
+				price_dis = product.xpath('.//div[@class="productDetail"]//span[@class="discount"]/text()').extract_first().split()[1]
+			else:
+				price_dis = price_reg
+
+			# Carry the price information into the next level. 
+			# Get into the detailed product page. 
+			yield Request(url = "https://www.bloomingdales.com"+url_product, meta={'price_reg':price_reg, 'price_dis':price_dis}, callback = self.parse_detail_page)
+
+	def parse_detail_page(self, response):
+
+		# Grab different information of a product
+		brand = response.xpath('//h1/a[@id="brandNameLink"]/text()').extract_first()
+		prod_name = response.xpath('//div[@id="productName"]/text()').extract_first()
+		desc_list = response.xpath('//ul[@class="product-details-bullet-list"]/li/text()').extract()
+		prod_image = response.xpath('//img[@itemprop="image"]/@src').extract_first()
+		prod_img_full = prod_image+'?wid=1200&qlt=90,0&layer=comp&op_sharpen=0&resMode=sharp2&op_usm=0.7,1.0,0.5,0&fmt=jpeg'
+
+		# Received the price information from the upper level. 
+		price_reg = response.meta['price_reg']
+		price_dis = response.meta['price_dis']
+		print('#'*50)
+		print(prod_image)
+		print('#'*50)
+
+		# This is for extracting product image################################		
+		if prod_image != '':
+			try:
+				full_file_name =  'img' + re.split("\/", prod_image)[-1].replace('.','_')
+				if ( not os.path.exists(full_file_name)):
+					urllib.request.urlretrieve(prod_img_full,full_file_name) #download img
+			except urllib.error.HTTPError as err:
+				if err.code == 404:
+					pass
+				else:
+					raise
+		######################################################################
+
+
+
+		item = BlmdlItem()
+		item['brand'] = brand
+		item['prod_name'] = prod_name
+		item['price_reg'] = price_reg
+		item['price_dis'] = price_dis
+		item['desc_list'] = desc_list
+		item['prod_image'] = prod_image
+		item['full_file_name'] = full_file_name
+
+		yield item
+
+