sports_scrapy/hg3535/spiders/hgjieshu.py

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

import scrapy


class HgjieshuSpider(scrapy.Spider):
    name = 'hgjieshu'
    allowed_domains = ['hg3535z.com']
    start_urls = ['https://hg3535z.com/zh-cn/info-centre/sportsbook-info/results/1/normal/1']

    def parse(self, response):
        # a = response.xpath('//*[@id="dt-cmp-66148"]/div[1]/div[3]/span[3]/text()')[0].extract_first()
        if response.status == 200:
            tema = response.xpath('//div[@class="rt-event"]//span[@class="pt"]/text()')
            # print(tema)
            aa = [i.extract() for i in tema ]

            # b = response.xpath('//div[@class="rt-ft "]/text()')  #比分
            b = response.xpath('//div[contains(@class,"rt-ft")]')#比分')]/text()')  #比分
            # print(b)
            # for i in tema:
            #     print(i.extract())
            #     c = i.xpath('//div/text()')
            #     # yield c
            #     i = i.extract()
            #     print(i)
            # aa = [(x, y, z.extract().split('">')[1].split('</')[0].strip())for x in tema if x % 2 == 0 for y in tema if x % 2 == 1 for z in b]
            cc = [z.extract().split('">')[1].split('</')[0].strip() for z in b]
            print(cc)
            # dd = [(aa[x], aa[y], z) for x in range(len(aa)) if x % 2 == 0 for y in range(len(aa)) if y % 2 == 1 for z in cc]
            print(cc)
            print(len(cc))
            print(len(tema))
            print(len(aa))
            print(aa)
            # print(dd)
                # print(type(cc))
                # break

                # i = i
                # yield i
                # print(i.extract())
                # c = i.xpath()
                # print(i.xpath('//div/text()'))
                # print(type(i.extract()))
            # d = i.xpath('//div/text()')

            # print(c)
            # print(a)
            # print(len(a))
            # # print(b)
            # print(len(b))
            # for e in d:
            #     print(e)

            pass