Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Support for writing metadata to PDF files (thanks to John Schember)

Browse Source
This commit is contained in:
Kovid Goyal 2009-04-12 09:10:19 -07:00
commit ffa6c73c8d
2 changed files with 32 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
src/calibre/customize/builtins.py
View File

@ -251,6 +251,17 @@ class MOBIMetadataWriter(MetadataWriterPlugin):
def set_metadata(self, stream, mi, type): def set_metadata(self, stream, mi, type):
from calibre.ebooks.metadata.mobi import set_metadata from calibre.ebooks.metadata.mobi import set_metadata
set_metadata(stream, mi) set_metadata(stream, mi)
class PDFMetadataWriter(MetadataWriterPlugin):
name = 'Set PDF metadata'
file_types = set(['pdf'])
description = _('Set metadata in %s files') % 'PDF'
author = 'John Schember'
def set_metadata(self, stream, mi, type):
from calibre.ebooks.metadata.pdf import set_metadata
set_metadata(stream, mi)
plugins = [HTML2ZIP] plugins = [HTML2ZIP]

33
src/calibre/ebooks/metadata/pdf.py
View File

@ -2,10 +2,10 @@ __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>' __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
'''Read meta information from PDF files''' '''Read meta information from PDF files'''
import sys, os, re import sys, os, StringIO
from calibre.ebooks.metadata import MetaInformation, authors_to_string, get_parser from calibre.ebooks.metadata import MetaInformation, authors_to_string, get_parser
from pyPdf import PdfFileReader from pyPdf import PdfFileReader, PdfFileWriter
def get_metadata(stream): def get_metadata(stream):
""" Return metadata as a L{MetaInfo} object """ """ Return metadata as a L{MetaInfo} object """
@ -31,18 +31,27 @@ def get_metadata(stream):
def set_metadata(stream, mi): def set_metadata(stream, mi):
stream.seek(0) stream.seek(0)
raw = stream.read()
if mi.title: # Use a StringIO object for the pdf because we will want to over
tit = mi.title.encode('utf-8') if isinstance(mi.title, unicode) else mi.title # write it later and if we are working on the stream directly it
raw = re.compile(r'<<.*?/Title\((.+?)\)', re.DOTALL).sub(lambda m: m.group().replace(m.group(1), tit), raw) # could cause some issues.
if mi.authors: raw = StringIO.StringIO(stream.read())
au = authors_to_string(mi.authors) orig_pdf = PdfFileReader(raw)
if isinstance(au, unicode):
au = au.encode('utf-8') title = mi.title if mi.title else orig_pdf.documentInfo.title
raw = re.compile(r'<<.*?/Author\((.+?)\)', re.DOTALL).sub(lambda m: m.group().replace(m.group(1), au), raw) author = authors_to_string(mi.authors) if mi.authors else orig_pdf.documentInfo.author
out_pdf = PdfFileWriter(title=title, author=author)
for page in orig_pdf.pages:
out_pdf.addPage(page)
out_str = StringIO.StringIO()
out_pdf.write(out_str)
stream.seek(0) stream.seek(0)
stream.truncate() stream.truncate()
stream.write(raw) out_str.seek(0)
stream.write(out_str.read())
stream.seek(0) stream.seek(0)
def option_parser(): def option_parser():