spider的代碼
from scrapy import Request
from scrapy.spiders import Spider
from shetu_spider.items import ShetuSpiderItem
class image_download(Spider):
name = 'image'
def start_requests(self):
url = 'http://699pic.com/photo/'
yield Request(url)
def parse(self, response):#決議函式-圖片串列頁
urls = response.xpath("//div[@class='pl-list']/a[1]/@href").extract()
for i in range(len(urls)):
yield Request(('http:'+urls[i]),callback=self.parse_image)
def parse_image(self,response):
item = ShetuSpiderItem()
#獲取所有圖片url地址
url = response.xpath("//li[@class='list']/a/img/@src").extract()
if url:
title = response.xpath("//li[@class='list']/a/img/@title").extract()
item['title'] = title
item['image_urls']=url
yield item
#獲取下一頁地址
next_url = response.xpath("//a[@class='downPage']/@href").extract()
if next_url:
next_url = response.urljoin(next_url[0])
yield Request(next_url,callback=self.parse_image)
網上的方法也采取了，但是還是這個錯誤，請各位大神，給點指示性的意見
uj5u.com熱心網友回復：
問題解決了，大家有同樣的問題，請參考我的博客https://blog.csdn.net/wenquan19960602/article/details/104860522
轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/76682.html