idealspider.py

import scrapy
from scrapy.http import safeurl


class Spider(scrapy.Spider):

    name = 'loremipsum'
    start_urls = ('https://www.lipsum.com',)

    def parse(self, response):
        for lnk in response.links():
            yield scrapy.Request(lnk['url'], callback=self._parse2, meta=lnk)
            #yield response.follow(lnk['url'], callback=self._parse2, meta=lnk)
            #yield response.follow(lnk, callback=self._parse2, meta=lnk)

            #yield scrapy.Request(lnk, self._parse2, meta={'link': lnk})
            #yield lnk.click(callback=self._parse2, meta={'link': lnk})
            #yield lnk.click(callback=self._parse2)  # clicked_link is added to meta

        yield scrapy.Request('XSS?\0=badass')
        # Request.url.encode('ascii') == b'XSS%00badass'
        yield scrapy.Request(safeurl('XSS?\0=badass'))
        # Request.url.encode('ascii') == b'XSS\x00badass'

        yield scrapy.Request(b'XSS\x00badass')
        # Request._url_bytes == b'XSS\x00badass'

    def _parse2(self, response):
        for href in response.xpath('//a[class="product"]/@href').extract():
            yield response.follow(href, cookies={'foo': 'bar'})

        yield response.follow('relative/path.html', dont_filter=True)
        
        
        yield from response.follow_all(xpath='//a[class="product"]/@href')