Support for reading metadata from FB2 files thanks to Anatoly Shipitsin

src/calibre/ebooks/lrf/__init__.py

@@ -90,9 +90,9 @@ def option_parser(usage, gui_mode=False):
                     dest="author", help=_("Set the author(s). Multiple authors should be set as a comma separated list. Default: %default"), 
                     default=_('Unknown'))
     metadata.add_option("--comment", action="store", type="string", \
-                    dest="freetext", help=_("Set the comment."), default='  ')
+                    dest="freetext", help=_("Set the comment."), default='Unknown')
     metadata.add_option("--category", action="store", type="string", \
-                    dest="category", help=_("Set the category"), default='  ')    
+                    dest="category", help=_("Set the category"), default='Unknown')    
     metadata.add_option('--title-sort', action='store', default='', dest='title_sort',
                       help=_('Sort key for the title'))
     metadata.add_option('--author-sort', action='store', default='', dest='author_sort',

src/calibre/ebooks/lrf/any/convert_from.py

@@ -71,7 +71,7 @@ def handle_archive(path):
     files = []
     cdir = traverse_subdirs(tdir)
     file = None
-    for ext in ('lit', 'rtf', 'pdf', 'txt', 'epub', 'mobi', 'prc'):
+    for ext in ('lit', 'rtf', 'fb2','pdf', 'txt', 'epub', 'mobi', 'prc'):
         pat = os.path.join(cdir, '*.'+ext)
         files.extend(glob.glob(pat))
     file = largest_file(files)

src/calibre/ebooks/lrf/fb2/convert_from.py

@@ -7,6 +7,7 @@ import os, sys, tempfile, subprocess, shutil, logging, glob
 
 from calibre.ptempfile import PersistentTemporaryFile
 from calibre.ebooks.lrf import option_parser as lrf_option_parser
+from calibre.ebooks.metadata.meta import get_metadata
 from calibre.ebooks import ConversionError
 from calibre.ebooks.lrf.html.convert_from import process_file as html_process_file
 from calibre import setup_cli_handlers, __appname__
@@ -59,16 +60,29 @@ def process_file(path, options, logger=None):
         logger = logging.getLogger('fb22lrf')
         setup_cli_handlers(logger, level)
     fb2 = os.path.abspath(os.path.expanduser(path))
+    f = open(fb2, 'rb')
+    mi = get_metadata(f, 'fb2')
+    f.close()
     htmlfile = generate_html(fb2, options.encoding, logger)
     tdir = os.path.dirname(htmlfile)
     cwd = os.getcwdu()
     try:
-	if not options.output:
+        if not options.output:
-	    ext = '.lrs' if options.lrs else '.lrf'
+            ext = '.lrs' if options.lrs else '.lrf'
-	    options.output = os.path.abspath(os.path.basename(os.path.splitext(path)[0]) + ext)
+            options.output = os.path.abspath(os.path.basename(os.path.splitext(path)[0]) + ext)
-	options.output = os.path.abspath(os.path.expanduser(options.output))
+        options.output = os.path.abspath(os.path.expanduser(options.output))
+        if not mi.title:
+            mi.title = os.path.splitext(os.path.basename(rtf))[0]
+        if (not options.title or options.title == 'Unknown'):
+            options.title = mi.title
+        if (not options.author or options.author == 'Unknown') and mi.authors:
+            options.author = mi.authors.pop()
+        if (not options.category or options.category == 'Unknown') and mi.category:
+            options.category = mi.category
+        if (not options.freetext or options.freetext == 'Unknown') and mi.comments:
+            options.freetext = mi.comments
         os.chdir(tdir)
-	html_process_file(htmlfile, options, logger)
+        html_process_file(htmlfile, options, logger)
     finally:
         os.chdir(cwd)
         if hasattr(options, 'keep_intermediate_files') and options.keep_intermediate_files:

src/calibre/ebooks/metadata/fb2.py

@@ -0,0 +1,42 @@
+#!/usr/bin/env python
+from __future__ import with_statement
+__license__   = 'GPL v3'
+__copyright__ = '2008, Anatoly Shipitsin <norguhtar at gmail.com>'
+
+'''Read meta information from fb2 files'''
+
+import sys, os
+
+from calibre.ebooks.BeautifulSoup import BeautifulStoneSoup
+from calibre.ebooks.metadata import MetaInformation
+
+def get_metadata(stream):
+    """ Return metadata as a L{MetaInfo} object """
+    soup =  BeautifulStoneSoup(stream.read())
+    firstname = soup.find("first-name").contents[0]
+    lastname = soup.find("last-name").contents[0]
+    author= [firstname+" "+lastname]
+    title = soup.find("book-title").string
+    comments = soup.find("annotation")
+    if comments and len(comments) > 1:
+            comments = comments.p.contents[0]
+    series = soup.find("sequence")
+    series_name = series['name']
+ #   series_index = series.index
+    mi = MetaInformation(title, author)
+    mi.comments = comments
+    mi.category = series_name
+ #   mi.series_index = series_index
+    return mi
+
+def main(args=sys.argv):
+    if len(args) != 2 or '--help' in args or '-h' in args:
+        print >>sys.stderr, _('Usage:'), args[0], 'mybook.fb2'
+        return 1
+    
+    path = os.path.abspath(os.path.expanduser(args[1]))
+    print unicode(get_metadata(open(path, 'rb')))
+    return 0
+
+if __name__ == '__main__':
+    sys.exit(main())

src/calibre/ebooks/metadata/meta.py

@@ -4,6 +4,7 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
 import os, re, collections
 
 from calibre.ebooks.metadata.rtf  import get_metadata as rtf_metadata
+from calibre.ebooks.metadata.fb2  import get_metadata as fb2_metadata
 from calibre.ebooks.lrf.meta      import get_metadata as lrf_metadata
 from calibre.ebooks.metadata.pdf  import get_metadata as pdf_metadata
 from calibre.ebooks.metadata.lit  import get_metadata as lit_metadata
@@ -18,7 +19,7 @@ from calibre.ebooks.metadata import MetaInformation
 
 _METADATA_PRIORITIES = [
                        'html', 'htm', 'xhtml', 'xhtm',
-                       'rtf', 'pdf', 'prc',
+                       'rtf', 'fb2', 'pdf', 'prc',
                        'epub', 'lit', 'lrf', 'mobi',
                       ]
 

src/calibre/linux.py

@@ -37,6 +37,7 @@ entry_points = {
                              'pdf2lrf   = calibre.ebooks.lrf.pdf.convert_from:main',
                              'mobi2lrf  = calibre.ebooks.lrf.mobi.convert_from:main',
                              'fb22lrf   = calibre.ebooks.lrf.fb2.convert_from:main',
+                             'fb2-meta  = calibre.ebooks.metadata.fb2:main',
                              'any2lrf   = calibre.ebooks.lrf.any.convert_from:main',
                              'lrf2lrs   = calibre.ebooks.lrf.parser:main',
                              'lrs2lrf   = calibre.ebooks.lrf.lrs.convert_from:main',
@@ -347,7 +348,7 @@ def install_man_pages(fatal_errors):
     for src in entry_points['console_scripts']:
         prog = src[:src.index('=')].strip()
         if prog in ('prs500', 'pdf-meta', 'epub-meta', 'lit-meta', 
-                    'markdown-calibre', 'calibre-debug'):
+                    'markdown-calibre', 'calibre-debug', 'fb2-meta'):
             continue
         help2man = ('help2man', prog, '--name', 'part of %s'%__appname__,
                     '--section', '1', '--no-info', '--include',