2、爬取网页图片

 1 """
 2 爬取必应壁纸数据
 3 """
 4 
 5 import requests
 6 from lxml import etree
 7 import os
 8 
 9 url = "https://bing.ioliu.cn/"
10 headers = {
11     ‘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‘
12 }
13 resp = requests.get(url=url,headers=headers)
14 # print(type(resp.text))  # 转换为文本信息，数据类型为str
15 # 数据预处理
16 resp_html = etree.HTML(resp.text)
17 # 图片地址获取
18 img_urls_list = resp_html.xpath(‘//img/@data-progressive‘)    #  获取的数据类型为list
19 img_names_list = resp_html.xpath(‘//h3/text()‘)
20 
21 for img_url,img_name in zip(img_urls_list,img_names_list):
22     print(img_url)
23     print(img_name.split(‘(?‘)[0])
24     result = requests.get(img_url.split(‘640x480‘)[0] + ‘1920x1080.jpg‘ ).content
25     dir_path = "picture"
26 
27     # 如果文件夹不存在，则创建新的文件夹
28     if not os.path.exists(dir_path):
29         os.mkdir(dir_path)
30 
31     f = open(dir_path + ‘/‘ + img_name.split(‘(?‘)[0] + ‘.jpg‘,‘wb‘)
32     f.write(result)
33     f.close()