blockchain.py

# -*- coding: utf-8 -*-
import scrapy



class BlockchainSpider(scrapy.Spider):
    name = 'blockchain'
    allowed_domains = ['www.blockchain.com']

    start_urls = ['https://www.blockchain.com/explorer']

    def parse(self, response):
        #position >=3 because div1 & div2 are the table headers
        blocks = response.xpath("//div[@class='sc-1kj8up-0 cNSdQW']/div[position() >= 3]")
        for block in blocks:
            yield {
                'height': block.xpath(".//div[1]/div[2]/a/text()").get(),
                'hash': block.xpath(".//div[2]/div[2]/a/text()").get()
            }