利用python爬虫爬取图片并且制作马赛克拼图

  1 import requests
  2 import re
  3 import os
  4 import time
  5 
  6 
  7 def get_url(url):
  8     kw = {‘user-agent‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64)‘}
  9     try:
 10         r = requests.get(url, headers=kw)
 11         r.raise_for_status()
 12         r.encoding = r.apparent_encoding
 13         return r
 14     except:
 15         print(‘wrong!!!!!!!!!!!‘)
 16 
 17 
 18 def get_photourl(photo_url):
 19     kw = {‘user-agent‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64)‘}
 20     try:
 21         r = requests.get(photo_url, headers=kw)
 22         r.raise_for_status()
 23         r.encoding = r.apparent_encoding
 24         return r
 25     except:
 26         return ‘wrong‘
 27 
 28 
 29 def get_photos(url, new_fpath):
 30     result = get_url(url)
 31     # pattern = re.compile(r‘src="https://images.pexels.com/photos/(\d+)/(.*?)\.(jpg|jpeg)\?auto=compress&cs=tinysrgb&h=350"‘, re.S)
 32     pattern = re.compile(
 33         ‘src="https://images.pexels.com/photos/(\d+)/(.*?)\?auto=compress&cs=tinysrgb&h=750&w=1260"‘)
 34     # 真正的下载链接是static，不是images开头
 35 
 36     items = re.findall(pattern, result.text)
 37 
 38     print("log!");
 39     for item in items:
 40         print(item);
 41 
 42     for item in items:
 43         try:
 44             photo_url = ‘https://static.pexels.com/photos/‘ + str(item[0]) + ‘/‘ + str(item[1]) + "?auto=compress&cs=tinysrgb&h=350";
 45             print("url: " + photo_url);
 46             # 把图片链接中的images，改成了static
 47             save(photo_url, item, new_fpath)
 48             time.sleep(1)
 49         except:
 50             continue
 51 
 52 
 53 def makedir(new_fpath, i, key):
 54     E = os.path.exists(new_fpath)
 55     if not E:
 56         os.makedirs(new_fpath)
 57         os.chdir(new_fpath)
 58         print(‘文件夹‘ + key + ‘_page‘ + str(i) + ‘创建成功！‘)
 59     else:
 60         print(‘文件夹已存在！‘)
 61 
 62 
 63 def save(photo_url, item, new_fpath):
 64     Final_fpath = new_fpath + ‘/‘ + str(item[0]) + str(item[1]);
 65     print("保存文件名: " + Final_fpath)
 66 
 67     print(‘正在下载图片......‘)
 68 
 69     result = get_photourl(photo_url)
 70     if result != ‘wrong‘:
 71         print(‘下载成功！‘)
 72     else:
 73         print(‘失败‘)
 74 
 75     E = os.path.exists(Final_fpath)
 76 
 77     if not E:
 78         try:
 79             with open(Final_fpath, ‘wb‘) as f:
 80                 f.write(result.content)
 81         except:
 82             print(‘下载失败！‘)
 83     else:
 84         print(‘图片已存在‘)
 85 
 86 
 87 def main():
 88     key = input(‘请输入搜索关键词(英文)：‘)
 89 
 90     url = ‘https://www.pexels.com/search/‘ + key + ‘/‘
 91 
 92     # num = int(input(‘请输入一共要下载的页数：‘))  # 默认从第1页开始下载
 93     st = int(input(‘请输入起始页码：‘))
 94     ed = int(input(‘请输入终止页码：‘))
 95 
 96     fpath = ‘C:/python/pic‘
 97     for i in range(st, ed+1):
 98         new_fpath = fpath + ‘/‘ + key + ‘/‘ + key + ‘_page‘ + str(i)
 99         makedir(new_fpath, i, key)
100         new_url = url + ‘?page=‘ + str(i)
101         get_photos(new_url, new_fpath)
102         time.sleep(3)
103 
104 
105 main()