python学习之图片爬虫

 1 import re
 2 import os
 3 import requests
 4 from time import sleep
 5 
 6 headers = {
 7     "User-Agent": ("Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:64.0) "
 8                    "Gecko/20100101 Firefox/64.0")
 9 }
10 
11 def get_index(resolution, index=1):
12     url = f"https://bing.ioliu.cn/ranking?p={index}"
13     res = requests.get(url, headers=headers)
14     urls = re.findall('pic=(.*?)\.jpg', res.text)
15     _old_resolution = urls[1].split("_")[-1]
16     return {url.split("/")[-1].replace(_old_resolution, resolution): url.replace(_old_resolution, resolution) + ".jpg"
17             for url in urls}
18 
19 def download_pic(pics):
20     if os.path.exists('必应壁纸'):
21         pass
22     else:
23         os.mkdir('必应壁纸')
24         print('目录创建成功')
25     try:
26         for pic_name, pic_url in pics.items():
27             res = requests.get(pic_url, headers=headers)
28             with open(f"必应壁纸\{pic_name}.jpg", mode="wb") as f:
29                 f.write(res.content)
30             print(f"{pic_name} 下载完成")
31     except Exception as e:
32         print("下载出错", e)
33 
34 def input_index():
35     print("必应壁纸下载工具, 本工具未经资源站授权.")
36     print("仅做学习和交流之用, 随时有可能停止维护.")
37     print("目前资源站收容页数为87,当前仅提供1920x1080分辨率下载")
38     while True:
39         sleep(0.1)
40         index = input("请输入要下载的页数(Max=87):")
41         try:
42             if index == "Q":
43                 exit()
44             index = 87 if int(index) > 87 else int(index)
45             return index
46         except ValueError:
47             print("请输入数字, 或输入Q退出!")
48 
49 def main():
50     index = input_index()
51     i = 1
52     while i <= index:
53         print(f"当前第{i}页,共需要下载{index}页")
54         pics = get_index("1920x1080", i)
55         download_pic(pics)
56         i += 1
57     print("下载完成,将在3秒后关闭...")
58     sleep(1)
59     print("2")
60     sleep(1)
61     print("1")
62     sleep(1)
63     print("0")
64 
65 if __name__ == '__main__':
66     main()