Python爬取贴吧中的图片

# -*- coding: utf-8 -*-
import scrapy
from TuBaEx.items import TubaexItem

class TubaexSpider(scrapy.Spider):
    name = "tubaex"
    #allowed_domains = ["https://tieba.baidu.com/p/4092816277"]
    baseURL="https://tieba.baidu.com/p/4092816277?pn="

    #拼接地址用 实现翻页
    offset=0
    #要爬取的网页
    start_urls = [baseURL+str(offset)]
    
    def parse(self, response):

        #获取最后一页的数字              
        end_page=response.xpath("//div[@id=‘thread_theme_5‘]/div/ul/li[2]/span[2]/text()").extract()
        #通过审查元素找到图片的类名，用xpath获取
        img_list=response.xpath("//img[@class=‘BDE_Image‘]/@src").extract()

        for img in img_list:
            item=TubaexItem()
            item[‘img_url‘]=img
            yield item

        url=self.baseURL

        #进行翻页
        if self.offset < int(end_page[0]): #通过xpath返回的是list
            self.offset+=1
            yield scrapy.Request(self.baseURL+str(self.offset),callback=self.parse)

# -*- coding: utf-8 -*-

import requests
from scrapy.pipelines.images import ImagesPipeline
from TuBaEx import settings

class TubaexPipeline(ImagesPipeline):

    def get_media_requests(self,item,info):
        img_link = item[‘img_url‘]
        yield scrapy.Request(img_link)

    def item_completed(self,results,item,info):
        images_store="C:/Users/ll/Desktop/py/TuBaEx/Images/"
        img_path=item[‘img_url‘]
        return item

IMAGES_STORE = ‘C:/Users/ll/Desktop/py/TuBaEx/Images/‘
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = ‘TuBaEx (+http://www.yourdomain.com)‘
USER_AGENT="User-Agent,Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50"
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
#开启管道
ITEM_PIPELINES = {
    ‘TuBaEx.pipelines.TubaexPipeline‘: 300,
}