Add plugin to automatically extract an ebook if it is in a zip of rar archive

src/calibre/customize/builtins.py

@@ -7,6 +7,7 @@ import os
 import glob
 from calibre.customize import FileTypePlugin, MetadataReaderPlugin, MetadataWriterPlugin
 from calibre.constants import numeric_version
+from calibre.ebooks.metadata.archive import ArchiveExtract
 
 class HTML2ZIP(FileTypePlugin):
     name = 'HTML to ZIP'
@@ -423,7 +424,7 @@ from calibre.devices.hanvon.driver import N516
 
 from calibre.ebooks.metadata.fetch import GoogleBooks, ISBNDB, Amazon
 from calibre.library.catalog import CSV_XML, EPUB_MOBI
-plugins = [HTML2ZIP, PML2PMLZ, GoogleBooks, ISBNDB, Amazon, CSV_XML, EPUB_MOBI]
+plugins = [HTML2ZIP, PML2PMLZ, ArchiveExtract, GoogleBooks, ISBNDB, Amazon, CSV_XML, EPUB_MOBI]
 plugins += [
     ComicInput,
     EPUBInput,

src/calibre/ebooks/metadata/archive.py

@@ -0,0 +1,54 @@
+#!/usr/bin/env python
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+from __future__ import with_statement
+
+__license__   = 'GPL v3'
+__copyright__ = '2010, Kovid Goyal <kovid@kovidgoyal.net>'
+__docformat__ = 'restructuredtext en'
+
+import textwrap, os
+from contextlib import closing
+
+from calibre.customize import FileTypePlugin
+
+class ArchiveExtract(FileTypePlugin):
+    name = 'Archive Extract'
+    author = 'Kovid Goyal'
+    description = textwrap.dedent(_('''\
+        Extract common e-book formats from archives (zip/rar) files.
+    '''))
+    file_types = set(['zip', 'rar'])
+    supported_platforms = ['windows', 'osx', 'linux']
+    on_import = True
+
+    def run(self, archive):
+        is_rar = archive.lower().endswith('.rar')
+        if is_rar:
+            from calibre.libunrar import extract_member, names
+        else:
+            from calibre.utils.zipfile import ZipFile
+            zf = ZipFile(archive, 'r')
+
+        if is_rar:
+            fnames = names(archive)
+        else:
+            fnames = zf.namelist()
+
+        fnames = [x for x in fnames if '.' in x]
+        if len(fnames) > 1 or not fnames:
+            return archive
+        fname = fnames[0]
+        ext = os.path.splitext(fname)[1][1:]
+        if ext.lower() not in ('lit', 'epub', 'mobi', 'prc', 'rtf', 'pdf',
+                'mp3'):
+            return archive
+
+        of = self.temporary_file('_archive_extract.'+ext)
+        with closing(of):
+            if is_rar:
+                data = extract_member(archive, match=None, name=fname)[1]
+                of.write(data)
+            else:
+                of.write(zf.read(fname))
+        return of.name
+