python爬虫入门学习6-xpath-netbian-图片爬取

import requests
from lxml import html
import os

if __name__ == '__main__':
	headers = {
		        'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36',
		    }
    url = 'https://pic.netbian.com/4kmeinv/'
    resp = requests.get(url=url, headers=headers)
    # resp.encoding = 'gbk' # 这里是整个数据转码
    # 解析网页
    etree = html.etree
    tree = etree.HTML(resp.text)

    detail_list = tree.xpath('//ul[@class="clearfix"]/li/a/img')
    append_url = 'https://pic.netbian.com/'
    dir_path = './pic'
    if not os.path.exists(dir_path):
        os.mkdir(dir_path)
    for detail in detail_list:
        src = append_url + detail.xpath('./@src')[0]
        title = detail.xpath('./@alt')[0] + '.jpg'
        title = title.encode('iso-8859-1').decode('gbk')  # 这里只对title字段转码
        img_path = dir_path + '/' + title
        img_data_byte = requests.get(src, hd.headers()).content
        with  open(img_path, 'wb') as fp:
            fp.write(img_data_byte)
            print(title, '下载成功')