爬取站酷网图片

# https://www.zcool.com.cn/
import requests,os,re
from urllib import request
from lxml import etree


class ZkSpider(object):
    def __init__(self):
        self.url='https://www.zcool.com.cn/'
        self.headers={
            'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'
        }


    def get_html(self):
        html=requests.get(self.url,headers=self.headers).text
        # print(html)
        html_obj=etree.HTML(html)
        titles=html_obj.xpath('//div[@class="work-list-box"]/div[@class="card-box"]/div/a/@title')          # 每组图片的标题
        hrefs=html_obj.xpath('//div[@class="work-list-box"]/div[@class="card-box"]/div/a/@href')            # 每组图片的链接
        print('****',titles)                # 第一页所有的标题
        self.get_detail_img(hrefs,titles)       # 嵌套函数，直接引用

    #解析详情页图片
    def get_detail_img(self,hrefs,titles):
        for index,href in enumerate(hrefs):             # 循环出每组图片的链接和索引，根据索引匹配到每组图片的标题
            title = titles[index].replace(":","").replace(" ","_").replace("×","_").replace("|", "_").replace(",", "_").replace('/','')                 # 把标题中的特殊字符替换掉
            print('*****',title)                # 打印出标题
            # if not os.path.exists(f'imgs'):
            #     os.mkdir(f'imgs')               # 先建一个总的文件夹用来存储子文件夹和图片
            if not os.path.exists(f"imgs/{title}"):
                os.mkdir(f"imgs/{title}")               # 以分组的标题为名新建文件夹
            response = requests.get(url=href, headers=self.headers)             # 请求每一组匹配到的链接
            self.html = etree.HTML(response.text)           # 生成对象树
            # imgs=self.html.xpath('//div[@class="work-show-box"]/div/img/@src')
            imgs = re.findall(re.compile(r'.*?<img src="https://img(.*?)"', re.S), response.text)           # 每组图片中每张图片的链接
            print(imgs)         # 整组图片的链接
            imgs = ["https://img" + url for url in imgs]            # 拼接每张图片的链接，存放在列表中
            for i, img in enumerate (imgs):                         # 循环出每张图片的链接和索引
                print(img)
                if img:                 # 如果存在这张图片
                    response = requests.get(img).content
                    # 打开图片文件，写进图片数据
                    with open(f"imgs/{title}/{i}.{img.split('.')[-1]}", "wb") as w:             # 以索引为图片名加上后缀名，然后写图片
                        w.write(response)
                else:
                    print(f"出问题的{img}")

        for index,title in enumerate(titles):
            print(title[index])
            for x, img in enumerate(imgs):
                print(x)
                # 获取图片数据
                response = requests.get(img).content
                # 打开图片文件，写进图片数据
                with open(f"images/{title[index]}", "wb") as w:
                    w.write(response)
                # print(f'{index}',img)
                for index,title in enumerate(titles):
                    # print(title)
                    self.title = title
                    path = self.mkdir + '/' + self.title
                    if not os.path.exists(path):
                        os.mkdir(path)
                    print('正在下载第{}张图片，请稍后。。。。'.format(index))
                    request.urlretrieve(img,f'images/{title}')


images=ZkSpider()
images.get_html()