我写了一个简单的代码来抓取网站,但即使覆盖USER_AGENT却出现了503 Service Unavailable错误,但还是出现同样的错误,请您指导我如何解决此问题, 这是我的代码:
# -*- coding: utf-8 -*-
import scrapy
class CurtainSpider(scrapy.Spider):
name = 'curtain'
allowed_domains = ['https://www.redbubble.com/shop']
#start_urls = ['https://www.redbubble.com/shop/shower-curtains/']
def start_requests(self):
yield scrapy.Request(url='https://www.redbubble.com/shop/shower-curtains/', callback=self.parse, headers={
'User-Agent' : 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.122 Safari/537.36'
})
def parse(self, response):
products = response.xpath("//div[@class='styles__grid--197Ps']/a")
for product in products:
title = product.xpath(".//div[@class='styles__box--206r9 styles__paddingRight-0--fzRHs']/div[@class='styles__textContainer--1xehi styles__disableLineHeight--3n9Fg styles__nowrap--2Vk3A']/span/text()").get()
yield {
'Title' : title
}