python爬取图片

import requests
from lxml import etree
import os


# 抓取图片
class Spider_qt(object):
    def __init__(self, pageNo, pageCount):
        # 反扒
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
                          "Chrome/74.0.3729.131 Safari/537.36",
            "Referer": "https://www.58pic.com/"
        }
        self.get_page(pageNo, pageCount)

    # 获取页面
    def get_page(self, pageNo, pageCount):
        for i in range(pageNo, pageNo + pageCount):
            print("===============================开始抓取第%s页===============================" % i)
            r = requests.get("https://www.58pic.com/piccate/53-0-0-p" + str(i) + ".html", headers=self.headers)
            page = etree.HTML(r.content.decode(‘gbk‘))
            self.get_images(page)

    # 获取图片
    def get_images(self, page):
        # xpath解析
        image_url = page.xpath("///div[@class=‘image-box‘]/img/@data-original")
        image_alt = page.xpath("//div[@class=‘image-box‘]/img/@alt")
        for url, alt in zip(image_url, image_alt):
            url = "http:" + url
            file_name = alt + ".jpg"
            save_path = "F:\\python\\spider\\images\\qt\\"
            if not os.path.exists(save_path):
                os.makedirs(save_path)
            file_save_path = save_path + file_name
            r = requests.get(url, headers=self.headers)
            print("正在抓取：" + file_name)
            try:
                with open(file_save_path, ‘wb‘) as f:
                    f.write(r.content)
            except:
                print("===============================抓取错误===============================")


def main():
    pageNo = int(input("请输入下载开始页："))
    pageCount = int(input("请输入需要下载的页数："))
    Spider_qt(pageNo, pageCount)


if __name__ == ‘__main__‘:
    main()