Added web scraper and updated README.md

books_scraper/items.py

@@ -0,0 +1,12 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class BooksScraperItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

books_scraper/middlewares.py

@@ -0,0 +1,103 @@
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
+
+class BooksScraperSpiderMiddleware:
+    # 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, 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 Request 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 BooksScraperDownloaderMiddleware:
+    # 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)

books_scraper/pipelines.py

@@ -0,0 +1,39 @@
+import pymongo
+
+class BooksScraperPipeline:
+    def __init__(self):
+        # MongoDB setup
+        self.client = pymongo.MongoClient("mongodb://localhost:27017/")
+        self.db = self.client["books_database"]
+        self.collection = self.db["products"]
+
+    def process_item(self, item, spider):
+        # Clean and process the product_name
+        item['product_name'] = item['product_name'].strip() if item['product_name'] else "Unknown Product"
+
+        # Clean and convert the price to float
+        if item['price']:
+            item['price'] = float(item['price'].replace('£', '').strip())
+        else:
+            item['price'] = 0.0  # Default to 0.0 if the price is missing
+
+        # Convert rating to float
+        rating_map = {'One': 1.0, 'Two': 2.0, 'Three': 3.0, 'Four': 4.0, 'Five': 5.0}
+        item['rating'] = rating_map.get(item['rating'], 0.0)  # Default to 0.0 if rating is missing
+
+        # Clean and standardize availability
+        raw_availability = item['availability'].lower() if item['availability'] else ''
+        item['availability'] = 'In Stock' if 'in stock' in raw_availability else 'Out of Stock'
+
+        # Insert the cleaned and processed item into MongoDB
+        self.collection.insert_one({
+            "product_name": item['product_name'],
+            "price": item['price'],
+            "rating": item['rating'],
+            "availability": item['availability']
+        })
+        return item
+
+    def close_spider(self, spider):
+        # Close the MongoDB connection
+        self.client.close()

books_scraper/readme.md

@@ -0,0 +1,34 @@
+# Books Web Scraper
+
+This project is a web scraper built using the Scrapy framework. It crawls the [Books to Scrape](http://books.toscrape.com/) website to extract product details such as name, price, rating, and availability. The extracted and cleaned data is stored in a MongoDB database.
+
+---
+
+## Overview
+
+The scraper performs the following tasks:
+1. Crawls the website to extract:
+   - Product Name
+   - Price
+   - Rating
+   - Availability
+2. Cleans and processes the extracted data:
+   - Converts price to float
+   - Maps ratings to numerical values
+   - Standardizes availability to "In Stock" or "Out of Stock"
+3. Stores the processed data into a MongoDB database with the schema:
+   - `product_name` (string)
+   - `price` (float)
+   - `rating` (float)
+   - `availability` (string)
+
+---
+
+## Setup and Running the Scraper
+
+### Prerequisites
+- Python 3.7 or above
+- MongoDB installed and running locally
+- pip (Python package manager)
+
+

books_scraper/settings.py

@@ -0,0 +1,91 @@
+# Scrapy settings for books_scraper project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     https://docs.scrapy.org/en/latest/topics/settings.html
+#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'books_scraper'
+
+SPIDER_MODULES = ['books_scraper.spiders']
+NEWSPIDER_MODULE = 'books_scraper.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'books_scraper (+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://docs.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://docs.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'books_scraper.middlewares.BooksScraperSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'books_scraper.middlewares.BooksScraperDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See https://docs.scrapy.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+#    'books_scraper.pipelines.BooksScraperPipeline': 300,
+#}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://docs.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://docs.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'
+ITEM_PIPELINES = {
+   'books_scraper.pipelines.BooksScraperPipeline': 300,
+}

books_scraper/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.

books_scraper/spiders/books_spider.py

@@ -0,0 +1,28 @@
+import scrapy
+
+class BooksSpider(scrapy.Spider):
+    name = "books_spider"
+    start_urls = ['http://books.toscrape.com/']
+
+    def parse(self, response):
+        for book in response.css('article.product_pod'):
+            # Extract data
+            product_name = book.css('h3 a::attr(title)').get()
+            price = book.css('p.price_color::text').get()
+            rating = book.css('p::attr(class)').re_first('star-rating (\w+)')
+            availability_raw = book.css('p.instock.availability::text').getall()
+
+            # Clean and process availability
+            availability = ''.join(availability_raw).strip()  # Combine all text and strip spaces
+
+            yield {
+                'product_name': product_name,
+                'price': price,
+                'rating': rating,
+                'availability': availability,
+            }
+
+        # Handle pagination
+        next_page = response.css('li.next a::attr(href)').get()
+        if next_page:
+            yield response.follow(next_page, self.parse)