Scracpy爬取图片实例

非常简单，直接上爬虫代码

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

class TopitComSpider(scrapy.Spider):
    name = "topit.com"
    allowed_domains = ["topit.com"]
    start_urls = [
        'http://www.topit.me',
    ]
    def parse(self, response):
        counter = 0
        image_urls1=response.xpath("//div[@class='catalog']/div[@class='e m'][position()<=8]/a/img/@src").extract()
        image_urls2=response.xpath("//div[@class='catalog']/div[@class='e m'][position()>8]/a/img/@data-original").extract()
        image_urls = image_urls1 + image_urls2
        for url in image_urls:
            urllib.urlretrieve(url, "/root/pic/"+str(counter)+'.jpg')
            logging.debug(url)
            counter=counter+1
        pass

遗留问题：

在用xpath匹配的时候用or将两个表达式连接起来匹配不到，只好分开匹配，再把结果合并。原因不明，有知道的朋友还请告知，谢谢