Update to make it more genereic

README.md

@@ -10,34 +10,40 @@
 
 1. Clone the repo.
 1. Install calibre and edit `config.json`'s calibre key to your `calibre-debug.exe` path
-1. (Optional) install WinRAR and edit `config.json`'s rar key to your `Rar.exe` path
+1. (Optional) create some post-prosssing command and put into `config.json`'s `postprocessing` key. Remember to add quotes and escape special characters if needed! You can check the sample config.json to get an idea.
 1. Clone https://github.com/apprenticeharper/DeDRM_tools repo and place "DeDRM_plugin" folder and its content directly into this repo's root folder.
 1. Install pycryptodome (`pip install pycryptodome`)
 
-## Usage 
+## Usage
 
 ```
-usage: extract_kindle.py [-h] [-k] [-z] [-o OUTPUT] dir
+usage: extract_kindle.py [-h] [-k] [-p] [-o OUTPUT] dir
 
 positional arguments:
   dir                   choose the folder contains DRMed azw file(s)
 
 optional arguments:
   -h, --help            show this help message and exit
   -k, --keep            keep temp and useless files
-  -z, --compress        also compress the files
+  -p, --postprocessing  do some postprocessing with the file.
   -o OUTPUT, --output OUTPUT
                         output folder (default: same as dir)
 ```
 
 Examples:
 
 ```
-extract_kindle.py "G:\_temp\My Kindle Content\B00KYFFDV2_EBOK" -o "D:\output" -z
+extract_kindle.py "G:\_temp\My Kindle Content\B00KYFFDV2_EBOK" -o "D:\output" -p
 extract_kindle.py "G:\_temp\My Kindle Content\B00KYFFDV2_EBOK"
 ```
 
-You can also use it as a module by something like 
+You can also use it as a module by something like
 ```py
-extract_kindle.main(R"G:\_temp\My Kindle Content\B00KYFFDV2_EBOK", "-o", "D:\\output", "-z")
-```
+extract_kindle.main(R"G:\_temp\My Kindle Content\B00KYFFDV2_EBOK", "-o", "D:\\output", "-p")
+```
+
+## Post-processing format
+
+* $o: output root path (i.e. -o parameter)
+* $f: book name string (path-safe, extracted from Kindle info)
+* $p: full path of the folder contains the image files (basically, $o/$f)

config.json

@@ -1,4 +1,4 @@
 {
     "calibre": "calibre-debug.exe",
-    "rar": "C:\\Program Files\\WinRAR\\Rar.exe"
+    "postprocessing": "\"C:\\Program Files\\WinRAR\\Rar.exe\" a -r -ep1 -rr5p -m0 -ma4 \"$o\\$f.rar\" \"$p\\*\""
 }

extract_kindle.py

@@ -23,12 +23,12 @@ def main(*input_args):
     parser = argparse.ArgumentParser()
     parser.add_argument("dir", help="choose the folder contains DRMed azw file(s)")
     parser.add_argument("-k", "--keep", action='store_true', help="keep temp and useless files")
-    parser.add_argument("-z", "--compress", action='store_true', help="also compress the files")
+    parser.add_argument("-p", "--postprocessing", action='store_true', help="do some postprocessing with the file.")
     parser.add_argument("-o", "--output", help="output folder (default: same as dir)")
     args = parser.parse_args(input_args)
 
     # load config
-    config = dict(calibre='calibre-debug.exe', rar=R'C:\Program Files (x86)\WinRAR\Rar.exe') # default
+    config = dict(calibre='calibre-debug.exe') # default
     try:
         config_file = Path(__file__).parent / 'config.json'
         if config_file.exists():
@@ -42,11 +42,6 @@ def main(*input_args):
         print('No calibre (calibre-debug.exe) found!')
         return 1
 
-    has_rar = True
-    if not which(config['rar']):
-        print('No WinRAR (Rar.exe) found. --compress function disabled.')
-        has_rar = False
-
     p = Path(args.dir)
     if not p.exists():
         print('Please provide a path to work on!')
@@ -87,7 +82,7 @@ def main(*input_args):
         imgs = [f for f in (temp_folder / 'images').iterdir() if f.suffix.lower() in ['.jpeg', '.jpg']]
         # The last image which is always a cover thumbnail. Here just some quick check to make sure. Then remove.
         assert imgs[-1].stat().st_size <= 50*1024
-        assert int(imgs[-1].stem)  == int(imgs[-2].stem) + 2
+        # assert int(imgs[-1].stem)  == int(imgs[-2].stem) + 2 # well, sometimes it has some weird GIFs inbetween.. so this isn't reliable.
         print(f'Removing {imgs[-1]}..')
         imgs[-1].unlink()
         if deDRM:
@@ -131,9 +126,15 @@ def main(*input_args):
     # Easier to recognize which ebook is which after moving/removing the extracted files.
     (p / (title + '.txt')).open('a').close()
 
-    if args.compress and has_rar:
-        zip_name = new_folder.with_name(new_folder.name + '.rar')
-        run([config['rar'], 'a', '-r', '-ep1', '-rr5p', '-m0', zip_name, str(new_folder) + "\\*"])
+    if args.postprocessing:
+        cmd = config['postprocessing']
+        cmd = cmd.replace('$o', str(save_dir))
+        cmd = cmd.replace('$p', str(new_folder))
+        cmd = cmd.replace('$f', new_folder.name)
+        run(cmd)
+    # if
+        # zip_name = new_folder.with_name(new_folder.name + '.rar')
+        # run([config['rar'], 'a', '-r', '-ep1', '-rr5p', '-m0', '-ma4', zip_name, str(new_folder) + "\\*"])
 
     if not args.keep:
         rmtree(temp_folder)