init

EpubImageExtractor.py

@@ -0,0 +1,44 @@
+import os.path
+import re
+import ebooklib
+from ebooklib import epub
+
+def cleanWindowsPath(path, replacement="_"):
+    forbidden_chars = r'[<>:"/\\|?*]'
+    return re.sub(forbidden_chars, replacement, path)
+
+def makeDir(path):
+    if not os.path.exists(path):
+        os.makedirs(path)
+
+def extractImagesFromEpub(epubPath, imageFolderPath=None):
+    if imageFolderPath is None:
+        imageFolderPath = "\\".join(epubPath.split('\\')[:-1])
+
+    book = epub.read_epub(epubPath)
+    imageFolder = os.path.join(imageFolderPath, ".".join(epubPath.split('\\')[-1].split('.')[:-1]))
+    cleanWindowsPath(imageFolder)
+    makeDir(imageFolder)
+
+    for image in book.get_items_of_type(ebooklib.ITEM_IMAGE):
+        with open(os.path.join(imageFolder, image.file_name.split('/')[-1]), 'wb') as img:
+            img.write(image.content)
+            print(F"Extracted {img.name}")
+
+def extractImagesFromEpubDir(epubDirPath, imageFolderPath=None):
+    if imageFolderPath is None:
+        imageFolderPath = epubDirPath
+
+    for file in os.scandir(epubDirPath):
+        if file.path.endswith('.epub'):
+            print(f"Starting with \"{file.path}\"")
+            extractImagesFromEpub(file.path, imageFolderPath)
+            print(f"Finisched with \"{file.path}\"\n\n\n")
+
+def extractImagesFromEpubLib(epubLibPath, imageFolderPath=None):
+    if imageFolderPath is None:
+        imageFolderPath = epubLibPath
+
+    for folder in os.scandir(epubLibPath):
+        extractImagesFromEpubDir(folder.path, imageFolderPath)
+