Python爬虫 --- 2.5 Scrapy之汽车之家爬虫实践

目的

Scrapy框架为文件和图片的下载专门提供了两个Item Pipeline 它们分别是：

FilePipeline

ImagesPipeline

这里主要介绍ImagesPipeline！！

目标分析：

这次我们要爬的是 汽车之家：car.autohome.com.cn

最近喜欢吉利博越，所以看了不少这款车的资料。。。。

我们就点开博越汽车的图片网站：

https://car.autohome.com.cn/pic/series/3788.html

传统的Scrapy框架图片下载

Scrapy 框架的实施：

1. 创建scrapy项目和爬虫： $ scrapy startproject Geely $ cd Geely $ scrapy genspider BoYue car.autohome.com.cn
2. 编写items.py: import scrapy class GeelyItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() # 存储图片分类 catagory = scrapy.Field() # 存储图片地址 image_urls = scrapy.Field() # ImagesPipeline images = scrapy.Field()
3. 编写Spider: # -*- coding: utf-8 -*- import scrapy #导入CrawlSpider模块 需改写原来的def parse(self,response)方法 from scrapy.spiders import CrawlSpider ,Rule #导入链接提取模块 from scrapy.linkextractors import LinkExtractor from Geely.items import GeelyItem class BoyueSpider(CrawlSpider): name = 'BoYue' allowed_domains = ['car.autohome.com.cn'] start_urls = ['https://car.autohome.com.cn/pic/series/3788.html'] #如需要进行页面解释则使用callback回调函数 因为有下一页，所以我们需要跟进，这里使用follow令其为True rules = { Rule(LinkExtractor(allow=r'https://car.autohome.com.cn/pic/series/3788.+'), callback= 'parse_page', follow=True), } def parse_page(self, response): catagory = response.xpath('//div[@class = "uibox"]/div/text()').get() srcs = response.xpath('//div[contains(@class,"uibox-con")]/ul/li//img/@src').getall() #map(函数，参数二)，将参数二中的每个都进行函数计算并返回一个列表 srcs = list(map(lambda x:x.replace('t_',''),srcs)) srcs = list(map(lambda x:response.urljoin(x),srcs)) yield GeelyItem(catagory=catagory, image_urls = srcs)
4. 编写PIPELINE： import os from urllib import request class GeelyPipeline(object): def __init__(self): #os.path.dirname()获取当前文件的路径,os.path.join()获取当前目录并拼接成新目录 self.path = os.path.join(os.path.dirname(__file__), 'images') # 判断路径是否存在 if not os.path.exists(self.path): os.mkdir(self.path) def process_item(self, item, spider): #分类存储 catagory = item['catagory'] urls = item['image_urls'] catagory_path = os.path.join(self.path, catagory) #如果没有该路径即创建一个 if not os.path.exists(catagory_path): os.mkdir(catagory_path) for url in urls: #以_进行切割并取最后一个单元 image_name = url.split('_')[-1] request.urlretrieve(url,os.path.join(catagory_path,image_name)) return item
5. 编写settings.py BOT_NAME = 'Geely' SPIDER_MODULES = ['Geely.spiders'] NEWSPIDER_MODULE = 'Geely.spiders' # Obey robots.txt rules ROBOTSTXT_OBEY = False ITEM_PIPELINES = { 'Geely.pipelines.GeelyPipeline': 1, }
6. 让项目跑起来： $ scrapy crawl BoYue
7. 结果展示:

使用Images_pipeline进行图片下载

使用步骤：

1. 定义好一个item,然后定义两个属性 image_urls 和 images。 image_urls是用来存储需要下载的文件的url链接，列表类型；
2. 当文件下载完成后，会把文件下载的相关信息存储到item的images属性中。例如：下载路径，下载url 和文件的效验码；
3. 再配置文件settings.py中配置FILES_STORE,指定文件下载路径；
4. 启动pipeline,在ITEM_PIPELINES中设置自定义的中间件！！！

具体步骤

在上面的基础上修改

1. 修改settings.py ITEM_PIPELINES = { # 'Geely.pipelines.GeelyPipeline': 1, # 'scrapy.pipelines.images.ImagesPipeline': 1, 'Geely.pipelines.GeelyImagesPipeline': 1, } #工程根目录 project_dir = os.path.dirname(__file__) #下载图片存储位置 IMAGES_STORE = os.path.join(project_dir, 'images')
2. 改写pipelines,py # -*- 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 os from urllib import request from scrapy.pipelines.images import ImagesPipeline from Geely import settings # class GeelyPipeline(object): # def __init__(self): # #os.path.dirname()获取当前文件的路径,os.path.join()获取当前目录并拼接成新目录 # self.path = os.path.join(os.path.dirname(__file__), 'images') # # 判断路径是否存在 # if not os.path.exists(self.path): # os.mkdir(self.path) # def process_item(self, item, spider): # #分类存储 # catagory = item['catagory'] # urls = item['image_urls'] # catagory_path = os.path.join(self.path, catagory) # #如果没有该路径即创建一个 # if not os.path.exists(catagory_path): # os.mkdir(catagory_path) # for url in urls: # #以_进行切割并取最后一个单元 # image_name = url.split('_')[-1] # request.urlretrieve(url,os.path.join(catagory_path,image_name)) # return item # 继承ImagesPipeline class GeelyImagesPipeline(ImagesPipeline): # 该方法在发送下载请求前调用，本身就是发送下载请求的 def get_media_requests(self, item, info): # super()直接调用父类对象 request_objects = super(GeelyImagesPipeline, self).get_media_requests(item, info) for request_object in request_objects: request_object.item = item return request_objects def file_path(self, request, response=None, info=None): path = super(GeelyImagesPipeline, self).file_path(request, response, info) # 该方法是在图片将要被存储时调用，用于获取图片存储的路径 catagory = request.item.get('catagory') # 拿到IMAGES_STORE images_stores = settings.IMAGES_STORE catagory_path = os.path.join(images_stores, catagory) #判断文件名是否存在,如果不存在创建文件 if not os.path.exists(catagory_path): os.mkdir(catagory_path) image_name = path.replace('full/','') image_path = os.path.join(catagory+'/',image_name) return image_path
3. 让项目跑起来： $ scrapy crawl BoYue

将会得到与原来相同的结果！！！！