-
-
Save scdekov/4b47d8dfc46592403f3e2505970f9f99 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import re | |
import scrapy | |
product = { | |
'url': 'https://www.amazon.co.uk/Asmodee-ASMDOBB01EN-Dobble-Card-Game/dp/B0031QBHMA/' | |
} | |
data_selectors_map = { | |
'title': lambda response: response.xpath('//*[@id="productTitle"]/text()').strip(), | |
# validate if all group results are the same | |
'parent_asin': lambda response: re.findall(r'["\']parentAsin["\']\s*:\s*["\']([A-z0-9]{10})', | |
response.body.decode('utf8'))[0], | |
'bullets': lambda response: "\n".join(map(str.strip, | |
response.xpath('//*[@id="feature-bullets"]//li//text()').getall())), | |
'price': lambda response: response.xpath('//*[@id="priceblock_ourprice"]//text()').get()[1:], | |
# TODO | |
# 'stock': lambda response: | |
# 'is_prime': '' | |
'brand': lambda response: response.xpath('//*[@id="bylineInfo"]/text()').get(), | |
'seller_rank': lambda response:\ | |
re.findall(r'(\d+)', response.xpath('//*[@id="SalesRank"]//td[@class="value"]/text()').get().strip())[0], | |
'category_rank': lambda response:\ | |
response.xpath('//*[@id="SalesRank"]//td[@class="value"]//*[@class="zg_hrsr_rank"]/text()').get()[1:], | |
'other_category_rank': lambda response:\ | |
(response.xpath('//*[@id="SalesRank"]//td[@class="value"]//*[@class="zg_hrsr_rank"]/text()')\ | |
.getall()[1:2] or [''])[0], | |
'description_length': '' | |
} | |
class ProductDataSpidere(scrapy.Spider): | |
name = 'product-data' | |
def start_requests(self): | |
yield scrapy.Request(url=product['url'], callback=self.parse) | |
def parse(self, response): | |
pass |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment