mirror of
https://github.com/Mueller-Patrick/Betterzon.git
synced 2026-10-19 04:01:16 +00:00
moved scrapy files to unused folder
This commit is contained in:
1 parent
f1d6487701
commit
dbc793cc08
9 files changed
+25
No files matched your search
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
@@ -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}
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Reference in new issue
Block a user