mirror of
https://github.com/Mueller-Patrick/Betterzon.git
synced 2024-12-04 19:45:12 +00:00
26ba21156a
* BETTERZON-58: Basic Functionality with scrapy * Added independent crawler function, yielding price * moved logic to amazon.py * . * moved scrapy files to unused folder * Added basic amazon crawler using beautifulsoup4 * Connected Api to Crawler * Fixed string concatenation for sql statement in getProductLinksForProduct * BETTERZON-58: Fixing SQL insert * BETTERZON-58: Adding access key verification * BETTERZON-58: Fixing API endpoint of the crawler - The list of products in the API request was treated like a string and henceforth, only the first product has been crawled * Added another selector for price on amazon (does not work for books) Co-authored-by: root <root@DESKTOP-ARBPL82.localdomain> Co-authored-by: Patrick Müller <patrick@mueller-patrick.tech> Co-authored-by: Patrick <50352812+Mueller-Patrick@users.noreply.github.com>
26 lines
694 B
Python
26 lines
694 B
Python
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}
|
|
|
|
|
|
|
|
|
|
|
|
|