def get_metadata(self, stream, ftype):
if hasattr(stream, 'seek') and hasattr(stream, 'tell'):
pos = stream.tell()
id_ = stream.read(3)
stream.seek(pos)
if id_ == b'Rar':
ftype = 'cbr'
elif id_.startswith(b'PK'):
ftype = 'cbz'
if ftype == 'cbr':
from ebook_converter.utils.unrar import extract_cover_image
else:
from ebook_converter.libunzip import extract_cover_image
from ebook_converter.ebooks.metadata import MetaInformation
ret = extract_cover_image(stream)
mi = MetaInformation(None, None)
stream.seek(0)
if ftype in {'cbr', 'cbz'}:
series_index = self.site_customization
if series_index not in {'volume', 'issue'}:
series_index = 'volume'
try:
mi.smart_update(
get_comic_metadata(stream,
ftype,
series_index=series_index))
except:
pass
if ret is not None:
path, data = ret
ext = os.path.splitext(path)[1][1:]
mi.cover_data = (ext.lower(), data)
return mi
def get_metadata(stream, cover=True):
with TemporaryDirectory('_pdf_metadata_read') as pdfpath:
stream.seek(0)
with open(os.path.join(pdfpath, 'src.pdf'), 'wb') as f:
shutil.copyfileobj(stream, f)
info = read_info(pdfpath, bool(cover))
if info is None:
raise ValueError('Could not read info dict from PDF')
covpath = os.path.join(pdfpath, 'cover.jpg')
cdata = None
if cover and os.path.exists(covpath):
with open(covpath, 'rb') as f:
cdata = f.read()
title = info.get('Title', None) or 'Unknown'
au = info.get('Author', None)
if au is None:
au = ['Unknown']
else:
au = string_to_authors(au)
mi = MetaInformation(title, au)
creator = info.get('Creator', None)
if creator:
mi.book_producer = creator
keywords = info.get('Keywords', None)
mi.tags = []
if keywords:
mi.tags = [x.strip() for x in keywords.split(',')]
isbn = [check_isbn(x) for x in mi.tags if check_isbn(x)]
if isbn:
mi.isbn = isbn = isbn[0]
mi.tags = [x for x in mi.tags if check_isbn(x) != isbn]
subject = info.get('Subject', None)
if subject:
mi.tags.insert(0, subject)
if 'xmp_metadata' in info:
from ebook_converter.ebooks.metadata.xmp import consolidate_metadata
mi = consolidate_metadata(mi, info)
# Look for recognizable identifiers in the info dict, if they were not
# found in the XMP metadata
for scheme, check_func in {'doi': check_doi, 'isbn': check_isbn}.items():
if scheme not in mi.get_identifiers():
for k, v in info.items():
if k != 'xmp_metadata':
val = check_func(v)
if val:
mi.set_identifier(scheme, val)
break
if cdata:
mi.cover_data = ('jpeg', cdata)
return mi
def get_metadata(stream):
"""
Return basic meta-data about the LRF file in C{stream} as a
L{MetaInformation} object.
@param stream: A file like object or an instance of L{LRFMetaFile}
"""
lrf = stream if isinstance(stream, LRFMetaFile) else LRFMetaFile(stream)
authors = string_to_authors(lrf.author)
mi = MetaInformation(lrf.title.strip(), authors)
mi.author = lrf.author.strip()
mi.comments = lrf.free_text.strip()
mi.category = lrf.category.strip() + ', ' + lrf.classification.strip()
tags = [x.strip() for x in mi.category.split(',') if x.strip()]
if tags:
mi.tags = tags
if mi.category.strip() == ',':
mi.category = None
mi.publisher = lrf.publisher.strip()
mi.cover_data = lrf.get_cover()
try:
mi.title_sort = lrf.title_reading.strip()
if not mi.title_sort:
mi.title_sort = None
except Exception:
pass
try:
mi.author_sort = lrf.author_reading.strip()
if not mi.author_sort:
mi.author_sort = None
except Exception:
pass
if not mi.title or 'unknown' in mi.title.lower():
mi.title = None
if not mi.authors:
mi.authors = None
if not mi.author or 'unknown' in mi.author.lower():
mi.author = None
if not mi.category or 'unknown' in mi.category.lower():
mi.category = None
if not mi.publisher or 'unknown' in mi.publisher.lower() or \
'some publisher' in mi.publisher.lower():
mi.publisher = None
return mi