From 0a11b2b45396c05ed4e195852343f72506886d02 Mon Sep 17 00:00:00 2001
From: henningxtro <henning.sextro@gmail.com>
Date: Sun, 16 May 2021 15:41:39 +0200
Subject: [PATCH] moved logic to amazon.py

---
 Crawler/amazonspider.py         | 33 +++++++++++++++++++++++++++++++++
 Crawler/crawler/amazonspider.py |  0
 2 files changed, 33 insertions(+)
 create mode 100644 Crawler/amazonspider.py
 delete mode 100644 Crawler/crawler/amazonspider.py

diff --git a/Crawler/amazonspider.py b/Crawler/amazonspider.py
new file mode 100644
index 0000000..5f88e20
--- /dev/null
+++ b/Crawler/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()
diff --git a/Crawler/crawler/amazonspider.py b/Crawler/crawler/amazonspider.py
deleted file mode 100644
index e69de29..0000000