Comic metadata: Support reading metadata from cbr files. Also read the comments and published date info from the metadata. Fixes #1082340 (Metadata in cbz and cbr files)

src/calibre/customize/builtins.py

@@ -8,7 +8,7 @@ from calibre import guess_type
 from calibre.customize import (FileTypePlugin, MetadataReaderPlugin,
     MetadataWriterPlugin, PreferencesPlugin, InterfaceActionBase, StoreBase)
 from calibre.constants import numeric_version
-from calibre.ebooks.metadata.archive import ArchiveExtract, get_cbz_metadata
+from calibre.ebooks.metadata.archive import ArchiveExtract, get_comic_metadata
 from calibre.ebooks.html.to_zip import HTML2ZIP
 
 plugins = []
@@ -150,9 +150,9 @@ class ComicMetadataReader(MetadataReaderPlugin):
         ret = extract_first(stream)
         mi = MetaInformation(None, None)
         stream.seek(0)
-        if ftype == 'cbz':
+        if ftype in {'cbr', 'cbz'}:
             try:
-                mi.smart_update(get_cbz_metadata(stream))
+                mi.smart_update(get_comic_metadata(stream, ftype))
             except:
                 pass
         if ret is not None:

src/calibre/ebooks/metadata/archive.py

@@ -110,21 +110,44 @@ def get_comic_book_info(d, mi):
                 authors.append(x)
     if authors:
         mi.authors = authors
+    comments = d.get('comments', '')
+    if comments and comments.strip():
+        mi.comments = comments.strip()
+    pubm, puby = d.get('publicationMonth', None), d.get('publicationYear', None)
+    if puby is not None:
+        from calibre.utils.date import parse_only_date
+        from datetime import date
+        try:
+            dt = date(puby, 6 if pubm is None else pubm, 15)
+            dt = parse_only_date(str(dt))
+            mi.pubdate = dt
+        except:
+            pass
 
-
+def get_comic_metadata(stream, stream_type):
-
-def get_cbz_metadata(stream):
     # See http://code.google.com/p/comicbookinfo/wiki/Example
-    from calibre.utils.zipfile import ZipFile
     from calibre.ebooks.metadata import MetaInformation
-    import json
 
-    zf = ZipFile(stream)
+    comment = None
+
     mi = MetaInformation(None, None)
-    if zf.comment:
+
-        m = json.loads(zf.comment)
+    if stream_type == 'cbz':
-        if hasattr(m, 'keys'):
+        from calibre.utils.zipfile import ZipFile
-            for cat in m.keys():
+        zf = ZipFile(stream)
+        comment = zf.comment
+    elif stream_type == 'cbr':
+        from calibre.utils.unrar import RARFile
+        f = RARFile(stream, get_comment=True)
+        comment = f.comment
+
+    if comment:
+        import json
+        m = json.loads(comment)
+        if hasattr(m, 'iterkeys'):
+            for cat in m.iterkeys():
                 if cat.startswith('ComicBookInfo'):
                     get_comic_book_info(m[cat], mi)
+                    break
     return mi
+