爬虫 scrapy图片下载

﹏ヽ暗。殇╰゛Y 2021-11-01 02:54 445阅读 0赞

彼岸网 图片下载

img.py

# -*- coding: utf-8 -*-
    import scrapy
    
    from imgPro.items import ImgproItem
    
    
    class ImgSpider(scrapy.Spider):
        name = 'img'
        # allowed_domains = ['www.xxx.com']
        # 起始的url
        start_urls = ['http://www.netbian.com/meinv/index.htm']
    
        # 其他url
        url = 'http://www.netbian.com/meinv/index_%d.htm'
        page = 2
    
        def parse(self, response):
            li_list = response.xpath('//*[@id="main"]/div[2]/ul/li')
            for li in li_list:
                img_src = li.xpath('./a/img/@src').extract_first()
    
                item = ImgproItem()
                item['img_src'] = img_src
                print(img_src)
                yield item
    
            if self.page <= 3:
                new_url = format(self.url % self.page)
    
                self.page+=1
    
                yield scrapy.Request(url=new_url,callback=self.parse)

items.py

# -*- 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:
        img_src = scrapy.Field()

piplines.py

# -*- 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
    
    
    class ImgproPipeline(object):
        def process_item(self, item, spider):
            return item
    
    
    
    # 导入模块
    import scrapy
    from scrapy.pipelines.images import ImagesPipeline
    class ImgPileLine(ImagesPipeline):
        # 接收item且将item中存储的img_src进行请求发送
        def get_media_requests(self,item,info):
            yield scrapy.Request(url=item['img_src'])
    
        # 指定数据存储的路径(文件夹【在配置文件中指定】+图片名称【该方法中返回】)
        def file_path(self,request,response=None,info=None):
            img_name=request.url.split('/')[-1]
            return img_name
        # 将item传递给下一个即将被执行的管道类
        def item_completed(self,result,item,info):
            return item

settings.py

注意更改  开启的管道类   设置文件路径   IMG\_STORE

# -*- 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'
    
    
    # Crawl responsibly by identifying yourself (and your website) on the user-agent
    #USER_AGENT = 'imgPro (+http://www.yourdomain.com)' # UA 伪装 USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.87 Safari/537.36' # Obey robots.txt rules # 不遵从robot协议 ROBOTSTXT_OBEY = False # 日志等级 LOG_LEVEL='ERROR' # 设置文件存储路径 IMAGES_STORE='./imgs'
    
    
    # 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
    
    
    #更改对应的管道名
    ITEM_PIPELINES = { 'imgPro.pipelines.ImgPileLine': 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'

转载于:https://www.cnblogs.com/XLHIT/p/11328424.html