Bugfix: Removed imagehdr as its deprecated. Used Filetype. Bumped Ver…

README.md

@@ -111,3 +111,8 @@ This project is licensed under the terms of the MIT license.
 ### Contact
 
 If you have any questions or feedback, please contact us at [email](mailto:shentharkrishnatejaswi@gmail.com).
+
+### Changelog
+
+- 1.1.3:
+  - Fixed issue with invalid image types. Deleted imghdr and used filetype to check image types.

better_bing_image_downloader/bing.py

@@ -1,11 +1,11 @@
 from pathlib import Path
 import urllib.request
 import urllib
-import imghdr
 import posixpath
 import re
 import logging
 from tqdm import tqdm
+import filetype
 
 '''
 
@@ -123,8 +123,8 @@ def save_image(self, link, file_path) -> None:
         try:
             request = urllib.request.Request(link, None, self.headers)
             image = urllib.request.urlopen(request, timeout=self.timeout).read()
-            if not imghdr.what(None, image):
-                
+            kind = filetype.guess(image)
+            if kind is None or not kind.mime.startswith('image/'):
                 logging.error('Invalid image, not saving %s', link)
                 raise ValueError('Invalid image, not saving %s' % link)
             with open(str(file_path), 'wb') as f:

better_bing_image_downloader/helperdownload.py

@@ -5,11 +5,11 @@
 from __future__ import print_function
 
 import shutil
-import imghdr
 import os
 import concurrent.futures
 import requests
 import socket
+import filetype
 
 headers = {
     "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
@@ -39,16 +39,15 @@ def download_image(image_url, dst_dir, file_name, timeout=20, proxy_type=None, p
             with open(file_path, 'wb') as f:
                 f.write(response.content)
             response.close()
-            file_type = imghdr.what(file_path)
-            # if file_type is not None:
-            if file_type in ["jpg", "jpeg", "png", "bmp", "webp"]:
-                new_file_name = "{}.{}".format(file_name, file_type)
+            kind = filetype.guess(file_path)
+            if kind and kind.extension in ["jpg", "jpeg", "png", "bmp", "webp"]:
+                new_file_name = "{}.{}".format(file_name, kind.extension)
                 new_file_path = os.path.join(dst_dir, new_file_name)
                 shutil.move(file_path, new_file_path)
                 print("## OK:  {}  {}".format(new_file_name, image_url))
             else:
                 os.remove(file_path)
-                print("## Err: TYPE({})  {}".format(file_type, image_url))
+                print("## Err: Invalid image type  {}".format(image_url))
             break
         except Exception as e:
             if try_times < 3:

requirements.txt

@@ -5,6 +5,7 @@ charset-normalizer==3.3.2
 chromedriver-autoinstaller==0.6.4
 cryptography==42.0.2
 docutils==0.20.1
+filetype==1.2.0
 h11==0.14.0
 idna==3.6
 importlib-metadata==6.0.0

setup.py

@@ -5,7 +5,7 @@
 
 setuptools.setup(
     name="better_bing_image_downloader",
-    version="1.1.2",
+    version="1.1.3",
     author="Krishnatejaswi S",
     author_email="shentharkrishnatejaswi@gmail.com",
     description="This package is built on top of bing-image-downloader by gaurav singh",