2、爬取网页图片

"""
爬取必应壁纸数据
"""

import requests
from lxml import etree
import os

url = "https://bing.ioliu.cn/"
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.164 Safari/537.36'
}
resp = requests.get(url=url,headers=headers)
# print(type(resp.text))  # 转换为文本信息，数据类型为str
# 数据预处理
resp_html = etree.HTML(resp.text)
# 图片地址获取
img_urls_list = resp_html.xpath('//img/@data-progressive')    #  获取的数据类型为list
img_names_list = resp_html.xpath('//h3/text()')

for img_url,img_name in zip(img_urls_list,img_names_list):
    print(img_url)
    print(img_name.split('(©')[0])
    result = requests.get(img_url.split('640x480')[0] + '1920x1080.jpg' ).content
    dir_path = "picture"

    # 如果文件夹不存在，则创建新的文件夹
    if not os.path.exists(dir_path):
        os.mkdir(dir_path)

    f = open(dir_path + '/' + img_name.split('(©')[0] + '.jpg','wb')
    f.write(result)
    f.close()