crawler complete

Bikes/items.py

@@ -0,0 +1,9 @@
+import scrapy
+
+
+class BikesItem(scrapy.Item):
+
+    item_name = scrapy.Field()
+    item_url = scrapy.Field()
+    item_price = scrapy.Field()
+

Bikes/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 BikesSpiderMiddleware(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 BikesDownloaderMiddleware(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)

Bikes/pipelines.py

@@ -0,0 +1,11 @@
+# -*- 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
+
+
+class BikesPipeline(object):
+    def process_item(self, item, spider):
+        return item

Bikes/settings.py

@@ -0,0 +1,90 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for Bikes 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 = 'Bikes'
+
+SPIDER_MODULES = ['Bikes.spiders']
+NEWSPIDER_MODULE = 'Bikes.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'Bikes (+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 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 = {
+#    'Bikes.middlewares.BikesSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'Bikes.middlewares.BikesDownloaderMiddleware': 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 = {
+#    'Bikes.pipelines.BikesPipeline': 300,
+#}
+
+# 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'

Bikes/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.

Bikes/spiders/bikeallspy.py

@@ -0,0 +1,34 @@
+# -*- coding: utf-8 -*-
+import scrapy
+from ..items import BikesItem
+
+
+class BikeallspySpider(scrapy.Spider):
+    name = 'bikeallspy'
+    start_urls = [
+        'https://www.amazon.in/s?i=automotive&bbn=5258392031&rh=n%3A4772060031%2Cn%3A%214772061031%2Cn%3A5257478031%2Cn%3A5258045031%2Cn%3A5258392031%2Cp_85%3A10440599031&pf_rd_i=5258045031&pf_rd_m=A1K21FY43GMZF8&pf_rd_p=0da2298e-ae9e-4b16-8e83-6a3410e62dfd&pf_rd_r=SPESDE2T7MZ4VMQYAPGN&pf_rd_s=merchandised-search-3&pf_rd_t=101&ref=s9_acss_bw_cg_Heltype_3d1_w',
+        'https://www.amazon.in/s?i=automotive&bbn=5258390031&rh=n%3A4772060031%2Cn%3A%214772061031%2Cn%3A5257478031%2Cn%3A5258045031%2Cn%3A5258390031%2Cp_85%3A10440599031&pf_rd_i=5258045031&pf_rd_m=A1K21FY43GMZF8&pf_rd_p=0da2298e-ae9e-4b16-8e83-6a3410e62dfd&pf_rd_r=FAEFY617NZX98JQB1XA5&pf_rd_s=merchandised-search-3&pf_rd_t=101&ref=s9_acss_bw_cg_Heltype_3a1_w',
+        'https://www.amazon.in/s?i=automotive&bbn=5258042031&rh=n%3A4772060031%2Cn%3A%214772061031%2Cn%3A5257478031%2Cn%3A5257575031%2Cn%3A5258042031%2Cp_85%3A10440599031&pf_rd_i=5257478031&pf_rd_m=A1K21FY43GMZF8&pf_rd_p=bd3ba4d6-2c95-4851-9fe1-3d1d7cf71d74&pf_rd_r=75DJC694E9VZZMKAZDAN&pf_rd_s=merchandised-search-8&pf_rd_t=101&ref=s9_acss_bw_cg_BKSafety_4a1_w',
+        'https://www.amazon.in/s?i=automotive&bbn=5258050031&rh=n%3A4772060031%2Cn%3A%214772061031%2Cn%3A5257478031%2Cn%3A5257575031%2Cn%3A5258050031%2Cp_85%3A10440599031&s=price-desc-rank&pf_rd_i=5257478031&pf_rd_m=A1K21FY43GMZF8&pf_rd_p=bd3ba4d6-2c95-4851-9fe1-3d1d7cf71d74&pf_rd_r=GWY7511V5XQF6H84MHG8&pf_rd_s=merchandised-search-8&pf_rd_t=101&ref=s9_acss_bw_cg_BKSafety_4b1_w',
+        'https://www.amazon.in/s?k=biker+face+mask&i=automotive&rh=n%3A4772060031%2Cp_6%3AAT95IG9ONZD7S%2Cp_85%3A10440599031&pf_rd_i=5257478031&pf_rd_m=A1K21FY43GMZF8&pf_rd_p=bd3ba4d6-2c95-4851-9fe1-3d1d7cf71d74&pf_rd_r=E9EX8YR968BFB2SX6Y8J&pf_rd_s=merchandised-search-8&pf_rd_t=101&ref=s9_acss_bw_cg_BKSafety_4c1_w',
+        'https://www.amazon.in/s?k=crash+guard+for+bike&rh=p_85%3A10440599031&pf_rd_i=5257478031&pf_rd_m=A1K21FY43GMZF8&pf_rd_p=bd3ba4d6-2c95-4851-9fe1-3d1d7cf71d74&pf_rd_r=FKRZGAMK7SZRP0X117K1&pf_rd_s=merchandised-search-8&pf_rd_t=101&ref=s9_acss_bw_cg_BKSafety_5a1_w',
+        'https://www.amazon.in/s?k=engine+oil+for+bike&pf_rd_i=5257478031&pf_rd_m=A1K21FY43GMZF8&pf_rd_p=eca27583-bc82-4947-9754-656d407adfd0&pf_rd_r=XTNQTEXNTY139QMM8RH5&pf_rd_s=merchandised-search-10&pf_rd_t=101&ref=s9_acss_bw_cg_BKPR_3a1_w',
+        'https://www.amazon.in/s?i=automotive&bbn=5257570031&rh=n%3A4772060031%2Cn%3A%214772061031%2Cn%3A5257478031%2Cn%3A5257570031%2Cp_85%3A10440599031&pf_rd_i=5257478031&pf_rd_m=A1K21FY43GMZF8&pf_rd_p=eca27583-bc82-4947-9754-656d407adfd0&pf_rd_r=SW51S5AKQEN25HA18K3S&pf_rd_s=merchandised-search-10&pf_rd_t=101&ref=s9_acss_bw_cg_BKPR_3b1_w',
+        'https://www.amazon.in/s?k=rims+and+alloy+wheels+for+bike&i=automotive&rh=n%3A4772060031%2Cn%3A5257478031%2Cn%3A5257578031%2Cp_85%3A10440599031&pf_rd_i=5257478031&pf_rd_m=A1K21FY43GMZF8&pf_rd_p=eca27583-bc82-4947-9754-656d407adfd0&pf_rd_r=K232EBDMKR425YX4SGX6&pf_rd_s=merchandised-search-10&pf_rd_t=101&ref=s9_acss_bw_cg_BKPR_4d1_w',
+        'https://www.amazon.in/s?i=automotive&bbn=5257919031&rh=n%3A4772060031%2Cn%3A%214772061031%2Cn%3A5257478031%2Cn%3A5257561031%2Cn%3A5257919031%2Cp_85%3A10440599031&pf_rd_i=5257478031&pf_rd_m=A1K21FY43GMZF8&pf_rd_p=0588bcc2-91b8-4087-82a1-8c04de919b60&pf_rd_r=6A3CA12X74KA5W4RA41G&pf_rd_s=merchandised-search-12&pf_rd_t=101&ref=s9_acss_bw_cg_BKAcc_3a1_w',
+        'https://www.amazon.in/s?k=mobile+holder+for+bike+%7C+mobile+bike+charger&i=automotive&bbn=4772060031&rh=n%3A4772060031%2Cp_6%3AAT95IG9ONZD7S&pf_rd_i=5257478031&pf_rd_m=A1K21FY43GMZF8&pf_rd_p=0588bcc2-91b8-4087-82a1-8c04de919b60&pf_rd_r=JBZ9ZAY4SK4W682YTAZW&pf_rd_s=merchandised-search-12&pf_rd_t=101&ref=s9_acss_bw_cg_BKAcc_3b1_w',
+    ]
+
+    def parse(self, response):
+        items = BikesItem()
+        all_items = response.css('.s-include-content-margin')
+        for item in all_items:
+            item_name = item.css('.a-color-base.a-text-normal').css('::text').extract_first()
+            item_url = item.css('.s-image-square-aspect .s-image').css('::attr(src)').extract_first()
+            item_price = item.css('.a-price-whole').css('::text').extract_first()
+
+            items['item_name'] = item_name
+            items['item_url'] = item_url
+            items['item_price'] = item_price
+
+            yield items

Bikes/spiders/bikehelmetspy.py

@@ -0,0 +1,28 @@
+# -*- coding: utf-8 -*-
+import scrapy
+from ..items import BikesItem
+
+
+class BikespySpider(scrapy.Spider):
+    name = 'bikehelmetspy'
+    start_urls = [
+        'https://www.amazon.in/s?i=automotive&bbn=5258392031&rh=n%3A4772060031%2Cn%3A%214772061031%2Cn%3A5257478031%2Cn%3A5258045031%2Cn%3A5258392031%2Cp_85%3A10440599031&pf_rd_i=5258045031&pf_rd_m=A1K21FY43GMZF8&pf_rd_p=0da2298e-ae9e-4b16-8e83-6a3410e62dfd&pf_rd_r=SPESDE2T7MZ4VMQYAPGN&pf_rd_s=merchandised-search-3&pf_rd_t=101&ref=s9_acss_bw_cg_Heltype_3d1_w',
+        'https://www.amazon.in/s?i=automotive&bbn=5258392031&rh=n%3A4772060031%2Cn%3A4772061031%2Cn%3A5257478031%2Cn%3A5258045031%2Cn%3A5258392031%2Cp_85%3A10440599031&page=2&pf_rd_i=5258045031&pf_rd_m=A1K21FY43GMZF8&pf_rd_p=0da2298e-ae9e-4b16-8e83-6a3410e62dfd&pf_rd_r=SPESDE2T7MZ4VMQYAPGN&pf_rd_s=merchandised-search-3&pf_rd_t=101&qid=1567426649&ref=sr_pg_2',
+        'https://www.amazon.in/s?i=automotive&bbn=5258390031&rh=n%3A4772060031%2Cn%3A%214772061031%2Cn%3A5257478031%2Cn%3A5258045031%2Cn%3A5258390031%2Cp_85%3A10440599031&pf_rd_i=5258045031&pf_rd_m=A1K21FY43GMZF8&pf_rd_p=0da2298e-ae9e-4b16-8e83-6a3410e62dfd&pf_rd_r=FAEFY617NZX98JQB1XA5&pf_rd_s=merchandised-search-3&pf_rd_t=101&ref=s9_acss_bw_cg_Heltype_3a1_w',
+        '',
+    ]
+
+    def parse(self, response):
+        items = BikesItem()
+        all_items = response.css('.s-include-content-margin')
+        for item in all_items:
+            item_name = item.css('.a-color-base.a-text-normal').css('::text').extract_first()
+            item_url = item.css('.s-image-square-aspect .s-image').css('::attr(src)').extract_first()
+            item_price = item.css('.a-price-whole').css('::text').extract_first()
+
+            items['item_name'] = item_name
+            items['item_url'] = item_url
+            items['item_price'] = item_price
+
+            yield items
+