python爬虫实战教程:下载某奶茶加盟品牌产品图片

最近一直在写web的东西,想自己完成一个购物系统的demo,产品分类要一些图片,没有美学细胞的看到处理图片头就大,只好找个相关的网站爬一下,根据产品分类创建目录,以图片显示的alt属性命名图片,保存为jpg格式.

一.代码

import os
import shutil
import requests
from lxml import etree


BASEDIR = os.path.dirname(__file__)


class AshuiSpider(object):
    #产品菜单 url
    def parse_product(self):
        url = 'http://www.ashui1998.com/product/'
        html = requests.get(url).text
        selector = etree.HTML(html)
        infos = selector.xpath('//div[@class="nr"]/h4/a')
        for info in infos:
            product_name = info.xpath('text()')[0]
            product_url = info.xpath('@href')[0]
            product_item = {}
            product_item['product_name'] = product_name
            product_item['product_url'] = product_url
            yield product_item

    #产品菜单下的图片 url 名称 要写入的路径
    def parse_pic(self, product_items):
        for product_item in product_items:
            # 创建存放路径
            picture_dir = product_item['product_name']
            os.chdir(BASEDIR)
            if os.path.exists(picture_dir):
                #不论目录是否为空都删除
                shutil.rmtree(picture_dir)
            os.mkdir(picture_dir)
            # 解析图片地址
            product_url = product_item['product_url']
            html = requests.get(product_url).text
            selector = etree.HTML(html)
            pics = selector.xpath('//div[@class="pro_main"]/dl[@class="pd_index_dl"]/dt/a')
            for pic in pics:
                pic_url = pic.xpath('img/@src')[0]
                pic_name = pic.xpath('img/@alt')[0]
                pic_item = {}
                pic_item['pic_url'] = pic_url
                pic_item['pic_name'] = pic_name
                pic_item['file'] = os.path.join(BASEDIR, picture_dir, pic_name+'.jpg')
                pic_content = requests.get(pic_url).content
                pic_item['pic_content'] = pic_content
                yield pic_item

    def run(self):
        product_items = self.parse_product()
        pic_items = self.parse_pic(product_items)
        for pic_item in pic_items:
            with open(pic_item['file'],'wb') as pic:
                pic.write(pic_item['pic_content'])

if __name__ == '__main__':
    ashui = AshuiSpider()
    ashui.run()

二.图片下载保存

奶茶图.png

三.号外

新搭的微信公众号pythonfan,接入了图灵机器人,图片 语音 都支持回复...

image.png

本文git地址:https://github.com/chengcxy/spiders/blob/master/load_pics.py
喜欢的给个star,土豪的来个微信打赏~~~

image.png