Scrapy爬取两万张小姐姐并按文件夹保存

一、创建scrapy项目

scrapy startproject tupian

 二、各个组件的编写

• items.py 定义你要爬取的字段

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

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

import scrapy


class TupianItem(scrapy.Item):
    name = scrapy.Field()  #图片的名称
    url = scrapy.Field()  #图片的链接
    image_paths = scrapy.Field() #图片的路径

 

• spiders文件夹下面新建picSpider.py

import scrapy

import tupian.items


class pic(scrapy.Spider):
    name = 'picSpider'  #自定义爬虫的名称
    allow_domain = ['https://tp.388g.com']
    start_urls = ['https://tp.388g.com/special/bizhi.html']  #开始爬取的地址

    def parse(self, response):
        list = response.css('.plist13 li')  #获取图集的url集合的链接
        for img in list:  #循环取出每个图集的url
            imgname = img.css('p ::text').extract_first() #图集的名称
            imgurl = img.css('a ::attr(href)').extract_first() #图集的url
            print('imgname:'+imgname+'\t''imgurl:'+str(imgurl)+'\n') #打印图集的名称和链接
            next_url = response.css('.next a ::attr(href)').extract_first() #下一页的url
            if next_url is not None:
                yield response.follow('https://tp388g.com'+next_url, callback = self.parse) #解析下一页

            yield scrapy.Request(imgurl, callback=self.content)#解析当页的图集

    def content(self, response):
        item = tupian.items.TupianItem()
        item['name'] = response.css('.img img ::attr(alt)').extract_first()#获取图片的名称
        item['url'] = response.css('.img img ::attr(src)').extract()#获取图片的url列表
        yield item
        nex_url = response.css('a.nexts ::attr(href)').extract_first()#下一张图片
        if nex_url is not None:
            yield response.follow(nex_url, callback=self.content)

•  pipelines.py对获取到的图片名称以及url进行处理

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

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

import scrapy
import scrapy.exceptions
import scrapy.pipelines.images


class TupianPipeline(scrapy.pipelines.images.ImagesPipeline):

    def get_media_requests(self, item, info):
        for image_url in item['url']:
            yield scrapy.Request(image_url, meta={'item': item['name']})

    def file_path(self, request, response=None, info=None):
        name = request.meta['item']
        name = re.sub(r'[？\\*|“<>:/()0123456789]', '', name)
        image_guid = request.url.split('/')[-1]
        filename = u'full/{0}/{1}'.format(name, image_guid)
        return filename

    def item_completed(self, results, item, info):
        image_path = [x['path'] for ok, x in results if ok]
        if not image_path:
            raise scrapy.exceptions.DropItem('Item contains no images')
        item['image_paths'] = image_path
        return item

• setting.py设置代理以及打开pipe（在原有的基础上添加）

IMAGES_STORE = 'E:\Img'
USER_AGENTS = [ "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)", "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)", "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)", "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)", "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)", "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)", "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6", "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1", "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0", "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5", "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20", "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER", "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)", "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)", "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1", "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5", "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre", "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11", "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10" ]
ITEM_PIPELINES = {
   'tupian.pipelines.TupianPipeline': 300,
}

三、项目运行