scrapy图片爬取--使用ImagesPipline全站爬取图片

qq_42021166

已于 2022-12-24 10:39:45 修改

阅读量180

点赞数 1

分类专栏： Python爬虫文章标签： scrapy python

于 2022-12-23 22:48:17 首次发布

本文链接：https://blog.csdn.net/qq_42021166/article/details/128425042

版权

Python爬虫专栏收录该内容

4 篇文章 0 订阅

订阅专栏

1.创建工程、爬虫文件

scrapy startproject biantuPro Projects   #biantuPro工程在Projects文件夹中
cd Projects
cd biantuPro 
scrapy genspider biantu xxx

2.编写爬虫文件 biantu.py

import scrapy

from ..items import BiantuproItem


class BiantuSpider(scrapy.Spider):
    name = 'biantu'
    # allowed_domains = ['xxx']   注释掉
    start_urls = ['https://pic.netbian.com/4kmeinv/']  #将‘xxx‘改为正确的url

    url = 'https://pic.netbian.com/4kmeinv/index_%d.html'
    pag_num =1

    def parse(self, response):
        print(f'+++++++++++++++++++++++正在爬取第{self.pag_num}页+++++++++++++')
        li_list = response.xpath('//*[@id="main"]/div[3]/ul/li')
        for li in li_list:
            name = li.xpath('./a/b/text()').extract_first()
            item = BiantuproItem()
            item['name'] = name
            href = 'https://pic.netbian.com'+li.xpath('./a/@href').extract_first()
            yield scrapy.Request(url=href,callback=self.parse_detail,meta={'item':item})

        if self.pag_num<=10:
            self.pag_num += 1
            new_url = format(self.url%self.pag_num)
            yield scrapy.Request(url=new_url,callback=self.parse)


    def parse_detail(self,response):
        pic_url = 'https://pic.netbian.com/'+response.xpath('//*[@id="img"]/img/@src').extract_first()
        item = response.meta['item']
        item['pic_url'] = pic_url
        yield item

3. 编写items.py

import scrapy


class BiantuproItem(scrapy.Item):
    # define the fields for your item here like:
    name = scrapy.Field()
    pic_url =scrapy.Field()

4.编写管道 piplines.py

import scrapy
from itemadapter import ItemAdapter


# class BiantuproPipeline:
#     def process_item(self, item, spider):
#         return item
from scrapy.pipelines.images import ImagesPipeline
class ImagesPipline(ImagesPipeline):
    def get_media_requests(self, item, info):
        yield scrapy.Request(item['pic_url'])
    def file_path(self, request, response=None, info=None, *, item=None):
        name = str(item['name']) + '.jpg'
        return name
    def item_completed(self, results, item, info):
        return item

5.修改设置 settings.py

BOT_NAME = 'biantuPro'

SPIDER_MODULES = ['biantuPro.spiders']
NEWSPIDER_MODULE = 'biantuPro.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36 Edg/108.0.1462.54'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False
LOG_LEVEL = 'ERROR'
IMAGES_STORE = './imgs'

ITEM_PIPELINES = {
   'biantuPro.pipelines.ImagesPipline': 300,
}