improve postprocessor handling

- add pathfmt argument for __init__()
- add finalization step
- add option to keep or delete zipped files

gallery_dl/postprocessor/classify.py

@@ -14,7 +14,7 @@ import os
 
 class ClassifyPP(PostProcessor):
 
-    DEFAULT_MAP = {
+    DEFAULT_MAPPING = {
         "Music" : ("mp3", "aac", "flac", "ogg", "wma", "m4a", "wav"),
         "Video" : ("flv", "ogv", "avi", "mp4", "mpg", "mpeg", "3gp", "mkv",
                    "webm", "vob", "wmv"),
@@ -22,9 +22,9 @@ class ClassifyPP(PostProcessor):
         "Archives" : ("zip", "rar", "7z", "tar", "gz", "bz2"),
     }
 
-    def __init__(self, options):
+    def __init__(self, pathfmt, options):
         PostProcessor.__init__(self)
-        mapping = options.get("mapping", self.DEFAULT_MAP)
+        mapping = options.get("mapping", self.DEFAULT_MAPPING)
 
         self.mapping = {
             ext: directory

gallery_dl/postprocessor/common.py

@@ -12,7 +12,11 @@ from . import log
 
 
 class PostProcessor():
+    """Base class for postprocessors"""
     log = log
 
     def run(self, pathfmt):
-        raise NotImplementedError()
+        """Execute the postprocessor for a file"""
+
+    def finalize(self):
+        """Cleanup"""

gallery_dl/postprocessor/exec.py

@@ -14,7 +14,7 @@ import subprocess
 
 class ExecPP(PostProcessor):
 
-    def __init__(self, options):
+    def __init__(self, pathfmt, options):
         PostProcessor.__init__(self)
         self.args = options["command"]
         if options.get("async", False):

gallery_dl/postprocessor/zip.py

@@ -6,7 +6,7 @@
 # it under the terms of the GNU General Public License version 2 as
 # published by the Free Software Foundation.
 
-"""Add files to ZIP archives"""
+"""Store files in ZIP archives"""
 
 from .common import PostProcessor
 import zipfile
@@ -21,19 +21,31 @@ class ZipPP(PostProcessor):
         "lzma": zipfile.ZIP_LZMA,
     }
 
-    def __init__(self, options):
+    def __init__(self, pathfmt, options):
         PostProcessor.__init__(self)
+        self.delete = not options.get("keep-files", False)
         self.ext = "." + options.get("extension", "zip")
-
         algorithm = options.get("compression", "store")
         if algorithm not in self.COMPRESSION_ALGORITHMS:
+            self.log.warning(
+                "unknown compression algorithm '%s'; falling back to 'store'",
+                algorithm)
             algorithm = "store"
-        self.compression = self.COMPRESSION_ALGORITHMS[algorithm]
+
+        path = pathfmt.realdirectory + self.ext
+        self.zfile = zipfile.ZipFile(
+            path, "a", self.COMPRESSION_ALGORITHMS[algorithm], True)
 
     def run(self, pathfmt):
-        archive = pathfmt.realdirectory + self.ext
-        with zipfile.ZipFile(archive, "a", self.compression, True) as zfile:
-            zfile.write(pathfmt.temppath, pathfmt.filename)
+        # 'NameToInfo' is not officially documented, but it's available
+        # for all supported Python versions and using it directly is a lot
+        # better than calling getinfo()
+        if pathfmt.filename not in self.zfile.NameToInfo:
+            self.zfile.write(pathfmt.temppath, pathfmt.filename)
+            pathfmt.delete = self.delete
+
+    def finalize(self):
+        self.zfile.close()
 
 
 __postprocessor__ = ZipPP