scrapy框架爬取图片并将图片保存到本地

如果基于scrapy进行图片数据的爬取

1. 在爬虫文件中只需要解析提取出图片地址，然后将地址提交给管道
2. 配置文件中：IMAGES_STORE = './imgsLib'
3. 在管道文件中进行管道类的制定：

• from scrapy.pipelines.images import ImagesPipeline
• 将管道类的父类修改成ImagesPipeline
• 重写父类的三个方法

 

# -*- coding: utf-8 -*-
import scrapy
from imgPro.items import ImgproItem

class ImgSpider(scrapy.Spider):
    name = 'img'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['http://www.521609.com/daxuemeinv/']
    url = 'http://www.521609.com/daxuemeinv/list8%d.html'
    pageNum = 1
    def parse(self, response):
        li_list = response.xpath('//*[@id="content"]/div[2]/div[2]/ul/li')
        for li in li_list:
            img_src = 'http://www.521609.com'+li.xpath('./a[1]/img/@src').extract_first()
            item = ImgproItem()
            item['src'] = img_src

            yield item

        # if self.pageNum < 3:
        #     self.pageNum += 1
        #     new_url = format(self.url%self.pageNum)
        #     yield scrapy.Request(new_url,callback=self.parse)

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

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class ImgproItem(scrapy.Item):
    # define the fields for your item here like:
    src = scrapy.Field()
    # pass

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

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html

from scrapy.pipelines.images import  ImagesPipeline
import scrapy
# class ImgproPipeline(object):
#     def process_item(self, item, spider):
#         return item
class ImgproPipeline(ImagesPipeline):

    #对某一个媒体资源进行请求发送
    #item就是接收到的spider提交过来的item
    def get_media_requests(self, item, info):
        yield scrapy.Request(item['src'])

    #制定媒体数据存储的名称
    def file_path(self, request, response=None, info=None):
        name = request.url.split('/')[-1]
        print('正在下载：',name)
        return name

    #将item传递给下一个即将给执行的管道类
    def item_completed(self, results, item, info):
        return item

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

# Scrapy settings for imgPro project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'imgPro'

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

USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'

# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'imgPro (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

LOG_LEVEL = 'ERROR'
# LOG_FILE = './log.txt'

IMAGES_STORE = './imgsLib'
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
# COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
#}

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'imgPro.middlewares.ImgproSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'imgPro.middlewares.ImgproDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'imgPro.pipelines.ImgproPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'