def get_fake_metadata_object(fn):
'''get object with metadata gleaned only from the file system
takes a full path'''
d = get_fake_metadata(fn)
obj = PieObject(title=d['title'], date=d['creation_date'])
obj.FileData_DateCreated = d['creation_date']
obj.FileData_DateModified = d['modification_date']
obj.FileData_FileType = determine_file_type(fn)
obj.FileData_FileName = os.path.basename(fn)
return obj
def pypdf_object(fn):
if sys.platform == 'win32':
newfn = os.path.join(CACHEDIR, 'Workaround', os.path.basename(fn))
if os.path.isfile(newfn):
newfn = auto_increment_fn(newfn)
shutil.copyfile(fn, newfn)
fn = newfn
data = pypdf_metadata(fn)
obj = PieObject(title=data['title'],
author=data['author'],
date=data['creation_date'])
obj.FileData_DateCreated = data['creation_date']
obj.FileData_FileType = 'pdf'
obj.FileData_FileName = os.path.basename(fn)
return obj
def pypdf_object(fn):
if sys.platform == 'win32':
newfn = os.path.join(CACHEDIR, 'Workaround', os.path.basename(fn))
if os.path.isfile(newfn):
newfn = auto_increment_fn(newfn)
shutil.copyfile(fn, newfn)
fn = newfn
data = pypdf_metadata(fn)
obj = PieObject(
title=data['title'],
author=data['author'],
date=data['creation_date']
)
obj.FileData_DateCreated = data['creation_date']
obj.FileData_FileType = 'pdf'
obj.FileData_FileName = os.path.basename(fn)
return obj
else:
creation_date = fakeobj.FileData_DateCreated
if reader.Info.Author:
author = unicode(
reader.Info.Author, 'utf8', errors=U_ERROR_BEHAV).strip('()')
else: author = u''
if reader.Info.Title:
title = unicode(
reader.Info.Title, 'utf8', errors=U_ERROR_BEHAV).strip('()')
else: title = u''
obj = PieObject(
title = title,
author = author,
date = creation_date)
obj.FileData_DateCreated = creation_date
obj.FileData_FileType = 'pdf'
obj.FileData_FileName = os.path.basename(fn)
return obj
def pdfrw_metadata(fn):
reader = PdfReader(fn)
# assert len(reader.Info.CreationDate) > 0
cd = reader.Info.CreationDate.split(':')[1] #get the 'good' bit
# md = reader.Info.ModDate.split(':')[1]
creation_date = datetime.datetime.strptime("%s %s %s %s %s" % (
cd[0:4], cd[4:6], cd[6:8], cd[8:10], cd[10:12]
), "%Y %m %d %H %M")
return {
'author': unicode(reader.Info.Author, 'utf8', errors=U_ERROR_BEHAV),
'title': unicode(reader.Info.Title, 'utf8', errors=U_ERROR_BEHAV),
'creation_date': creation_date,
