From d2a4d93f54fc5ecd86c3012e717a78d04b078c3a Mon Sep 17 00:00:00 2001
From: root <root@DESKTOP-ARBPL82.localdomain>
Date: Thu, 6 May 2021 00:09:30 +0200
Subject: [PATCH] Added independent crawler function, yielding price

---
 Crawler/crawler/amazonspider.py   |  0
 Crawler/crawler/spiders/amazon.py | 66 -------------------------------
 2 files changed, 66 deletions(-)
 create mode 100644 Crawler/crawler/amazonspider.py
 delete mode 100644 Crawler/crawler/spiders/amazon.py

diff --git a/Crawler/crawler/amazonspider.py b/Crawler/crawler/amazonspider.py
new file mode 100644
index 0000000..e69de29
diff --git a/Crawler/crawler/spiders/amazon.py b/Crawler/crawler/spiders/amazon.py
deleted file mode 100644
index 12ea3d5..0000000
--- a/Crawler/crawler/spiders/amazon.py
+++ /dev/null
@@ -1,66 +0,0 @@
-# -*- 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}