BETTERZON-58: Basic Functionality with scrapy (#33)

Crawler/crawler/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 CrawlerItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

Crawler/crawler/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 CrawlerSpiderMiddleware:
+    # 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 CrawlerDownloaderMiddleware:
+    # 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)

Crawler/crawler/pipelines.py

@@ -0,0 +1,13 @@
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+# useful for handling different item types with a single interface
+from itemadapter import ItemAdapter
+
+
+class CrawlerPipeline:
+    def process_item(self, item, spider):
+        return item

Crawler/crawler/settings.py

@@ -0,0 +1,88 @@
+# Scrapy settings for crawler 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 = 'crawler'
+
+SPIDER_MODULES = ['crawler.spiders']
+NEWSPIDER_MODULE = 'crawler.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = False
+
+# 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 = 1
+
+# 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 = {
+#    'crawler.middlewares.CrawlerSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'crawler.middlewares.CrawlerDownloaderMiddleware': 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 = {
+#    'crawler.pipelines.CrawlerPipeline': 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'

Crawler/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.

Crawler/crawler/spiders/amazon.py

@@ -0,0 +1,66 @@
+# -*- coding: utf-8 -*-
+import scrapy
+from urllib.parse import urlencode
+from urllib.parse import urljoin
+import re
+import json
+
+queries = ['iphone']
+API = ''
+
+
+def get_url(url):
+    payload = {'api_key': API, 'url': url, 'country_code': 'us'}
+    proxy_url = 'http://api.scraperapi.com/?' + urlencode(payload)
+    return proxy_url
+
+
+class AmazonSpider(scrapy.Spider):
+    name = 'amazon'
+
+    def start_requests(self):
+        for query in queries:
+            url = 'https://www.amazon.de/s?' + urlencode({'k': query})
+            yield scrapy.Request(url=url, callback=self.parse_keyword_response)
+
+    def parse_keyword_response(self, response):
+        products = response.xpath('//*[@data-asin]')
+
+        for product in products:
+            asin = product.xpath('@data-asin').extract_first()
+            product_url = f"https://www.amazon.de/dp/{asin}"
+            yield scrapy.Request(url=product_url, callback=self.parse_product_page, meta={'asin': asin})
+
+        next_page = response.xpath('//li[@class="a-last"]/a/@href').extract_first()
+        if next_page:
+            url = urljoin("https://www.amazon.de", next_page)
+            yield scrapy.Request(url=url, callback=self.parse_keyword_response)
+
+    def parse_product_page(self, response):
+        asin = response.meta['asin']
+        title = response.xpath('//*[@id="productTitle"]/text()').extract_first()
+        image = re.search('"large":"(.*?)"', response.text).groups()[0]
+        rating = response.xpath('//*[@id="acrPopover"]/@title').extract_first()
+        number_of_reviews = response.xpath('//*[@id="acrCustomerReviewText"]/text()').extract_first()
+        price = response.xpath('//*[@id="priceblock_ourprice"]/text()').extract_first()
+
+        if not price:
+            price = response.xpath('//*[@data-asin-price]/@data-asin-price').extract_first() or \
+                    response.xpath('//*[@id="price_inside_buybox"]/text()').extract_first()
+
+        temp = response.xpath('//*[@id="twister"]')
+        sizes = []
+        colors = []
+        if temp:
+            s = re.search('"variationValues" : ({.*})', response.text).groups()[0]
+            json_acceptable = s.replace("'", "\"")
+            di = json.loads(json_acceptable)
+            sizes = di.get('size_name', [])
+            colors = di.get('color_name', [])
+
+        bullet_points = response.xpath('//*[@id="feature-bullets"]//li/span/text()').extract()
+        seller_rank = response.xpath(
+            '//*[text()="Amazon Best Sellers Rank:"]/parent::*//text()[not(parent::style)]').extract()
+        yield {'asin': asin, 'Title': title, 'MainImage': image, 'Rating': rating, 'NumberOfReviews': number_of_reviews,
+               'Price': price, 'AvailableSizes': sizes, 'AvailableColors': colors, 'BulletPoints': bullet_points,
+               'SellerRank': seller_rank}

Crawler/requirements.txt

@@ -2,3 +2,4 @@ pymysql
 flask
 flask-sqlalchemy
 flask_restful
+scrapy

Crawler/scrapy.cfg

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