moved scrapy files to unused folder

Crawler/Crawler.iml

@@ -2,13 +2,13 @@
 <module type="WEB_MODULE" version="4">
   <component name="FacetManager">
     <facet type="Python" name="Python">
-      <configuration sdkName="Python 3.9" />
+      <configuration sdkName="Python 3.9 (venv)" />
     </facet>
   </component>
   <component name="NewModuleRootManager" inherit-compiler-output="true">
     <exclude-output />
     <content url="file://$MODULE_DIR$" />
     <orderEntry type="sourceFolder" forTests="false" />
-    <orderEntry type="library" name="Python 3.9 interpreter library" level="application" />
+    <orderEntry type="library" name="Python 3.9 (venv) interpreter library" level="application" />
   </component>
 </module>

Crawler/crawler.py

@@ -1,4 +1,5 @@
 import sql
+import amazonspider
 
 
 def crawl(product_ids: [int]) -> dict:
@@ -50,13 +51,14 @@ def crawl(product_ids: [int]) -> dict:
         'products_with_problems': products_with_problems
     }
 
-
 def __crawl_amazon__(product_info: dict) -> tuple:
     """
     Crawls the price for the given product from amazon
     :param product_info: A dict with product info containing product_id, vendor_id, url
     :return: A tuple with the crawled data, containing (product_id, vendor_id, price_in_cents)
     """
+
+    amazonspider.start_crawling()
     return (product_info['product_id'], product_info['vendor_id'], 123)
 
 

Crawler/crawler/spiders/amazon.py

@@ -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}

Crawler/unused/scrapy/amazonspider.py

@@ -0,0 +1,33 @@
+import scrapy
+from scrapy.crawler import CrawlerProcess
+import re
+
+class AmazonSpider(scrapy.Spider):
+    name = 'amazon'
+    allowed_domains = ['amazon.de']
+    start_urls = ['https://amazon.de/dp/B083DRCPJG']
+
+    # def __init__(self, start_urls):
+    #   self.start_urls = start_urls
+
+    def parse(self, response):
+        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()
+
+        euros = re.match('(\d*),\d\d', price).group(1)
+        cents = re.match('\d*,(\d\d)', price).group(1)
+        priceincents = euros + cents
+
+        yield {'price': priceincents}
+
+
+def start_crawling():
+    process = CrawlerProcess(
+        settings={'COOKIES_ENABLED': 'False', 'CONCURRENT_REQUESTS_PER_IP': 1, 'ROBOTSTXT_OBEY': False,
+                  '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',
+                  'DOWNLOAD_DELAY': 3}
+        , install_root_handler=False)
+    process.crawl()
+    process.start()

Crawler/unused/scrapy/scrapy.cfg

@@ -8,4 +8,4 @@ default = crawler.settings
 
 [deploy]
 #url = http://localhost:6800/
-project = crawler
+project = crawler

Crawler/unused/scrapy/spiders/amazon.py

@@ -0,0 +1,25 @@
+import scrapy
+import re
+
+class AmazonSpider(scrapy.Spider):
+    name = 'amazon'
+    allowed_domains = ['amazon.de']
+    start_urls = ['https://amazon.de/dp/B083DRCPJG']
+
+    def parse(self, response):
+        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()
+
+        euros = re.match('(\d*),\d\d', price).group(1)
+        cents = re.match('\d*,(\d\d)', price).group(1)
+        priceincents = euros + cents
+
+        yield {'price': priceincents}
+
+
+
+
+
+