Scrapy修改下载图片名字

源码下载:http://download.csdn.net/download/adam_zs/10167921

1.项目结构,下载图片

Scrapy修改下载图片名字_第1张图片Scrapy修改下载图片名字_第2张图片

2.代码介绍

pipelines.py

from scrapy.pipelines.images import ImagesPipeline
from scrapy.exceptions import DropItem
from scrapy.http import Request


# 下载图片Pipeline
class DownImagePipeline(ImagesPipeline):

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

    def file_path(self, request, response=None, info=None):
        item = request.meta['item']  # 通过上面的meta传递过来item
        index = request.meta['index']
        car_name = item['car_name'][index] + "." + request.url.split('/')[-1].split('.')[-1]
        down_file_name = u'full/{0}/{1}'.format(item['country'][0], car_name)
        return down_file_name

pcauto_spider.py

# -*- coding: utf-8 -*-
import scrapy
from pcauto.items import PcautoImage


class PcautoSpider(scrapy.Spider):
    name = "pcauto"
    allowed_domains = ["pcauto.com.cn"]
    start_urls = [
        'http://www.pcauto.com.cn/zt/chebiao/guochan/',
        'http://www.pcauto.com.cn/zt/chebiao/riben/',
        'http://www.pcauto.com.cn/zt/chebiao/deguo/',
        'http://www.pcauto.com.cn/zt/chebiao/faguo/',
        'http://www.pcauto.com.cn/zt/chebiao/yidali/',
        'http://www.pcauto.com.cn/zt/chebiao/yingguo/',
        'http://www.pcauto.com.cn/zt/chebiao/meiguo/',
        'http://www.pcauto.com.cn/zt/chebiao/hanguo/',
        'http://www.pcauto.com.cn/zt/chebiao/qita/',
    ]

    def parse(self, response):
        item = PcautoImage()
        srcs = response.xpath('//div[@class="dPic"]/i[@class="iPic"]/a/img/@src').extract()
        car_name = response.xpath('//div[@class="dTxt"]/i[@class="iTit"]/a//text()').extract()
        country = response.xpath('//div[@class="th"]/span/a//text()').extract()
        item['image_urls'] = srcs
        item['car_name'] = car_name
        item['country'] = country
        yield item


3.运行项目

pycharm中运行begin.py

from scrapy import cmdline

# cmdline.execute("scrapy crawl dmoz".split())

cmdline.execute("scrapy crawl pcauto".split())



你可能感兴趣的:(python)