def get_comic_info(tmp_file_path, original_file_name, original_file_extension):
if use_comic_meta:
archive = ComicArchive(tmp_file_path)
if archive.seemsToBeAComicArchive():
if archive.hasMetadata(MetaDataStyle.CIX):
style = MetaDataStyle.CIX
elif archive.hasMetadata(MetaDataStyle.CBI):
style = MetaDataStyle.CBI
else:
style = None
if style is not None:
loadedMetadata = archive.readMetadata(style)
lang = loadedMetadata.language
if len(lang) == 2:
loadedMetadata.language = isoLanguages.get(part1=lang).name
elif len(lang) == 3:
loadedMetadata.language = isoLanguages.get(part3=lang).name
else:
loadedMetadata.language = ""
return uploader.BookMeta(file_path=tmp_file_path,
extension=original_file_extension,
title=loadedMetadata.title
or original_file_name,
author=" & ".join([
credit["person"]
for credit in loadedMetadata.credits
if credit["role"] == "Writer"
]) or u"Unknown",
cover=extractCover(tmp_file_path,
original_file_extension),
description=loadedMetadata.comments or "",
tags="",
series=loadedMetadata.series or "",
series_id=loadedMetadata.issue or "",
languages=loadedMetadata.language)
else:
return uploader.BookMeta(file_path=tmp_file_path,
extension=original_file_extension,
title=original_file_name,
author=u"Unknown",
cover=extractCover(tmp_file_path,
original_file_extension),
description="",
tags="",
series="",
series_id="",
languages="")
def pdf_meta(tmp_file_path, original_file_name, original_file_extension):
if use_pdf_meta:
pdf = PdfFileReader(open(tmp_file_path, 'rb'))
doc_info = pdf.getDocumentInfo()
else:
doc_info = None
if doc_info is not None:
author = doc_info.author if doc_info.author is not None else u"Unknown"
title = doc_info.title if doc_info.title is not None else original_file_name
subject = doc_info.subject
else:
author = u"Unknown"
title = original_file_name
subject = ""
return uploader.BookMeta(
file_path=tmp_file_path,
extension=original_file_extension,
title=title,
author=author,
cover=pdf_preview(tmp_file_path, original_file_name),
description=subject,
tags="",
series="",
series_id="")
def get_fb2_info(tmp_file_path, original_file_name, original_file_extension):
ns = {
'fb':'http://www.gribuser.ru/xml/fictionbook/2.0',
'l':'ttp://www.w3.org/1999/xlink',
}
fb2_file = open(tmp_file_path)
tree = etree.fromstring(fb2_file.read())
authors = tree.xpath('/fb:FictionBook/fb:description/fb:title-info/fb:author', namespaces=ns)
def get_author(element):
return element.xpath('fb:first-name/text()', namespaces=ns)[0] + ' ' + element.xpath('fb:middle-name/text()', namespaces=ns)[0] + ' ' + element.xpath('fb:last-name/text()', namespaces=ns)[0]
author = ", ".join(map(get_author, authors))
title = unicode(tree.xpath('/fb:FictionBook/fb:description/fb:title-info/fb:book-title/text()', namespaces=ns)[0])
description = unicode(tree.xpath('/fb:FictionBook/fb:description/fb:publish-info/fb:book-name/text()', namespaces=ns)[0])
return uploader.BookMeta(
file_path = tmp_file_path,
extension = original_file_extension,
title = title,
author = author,
cover = None,
description = description,
tags = "",
series = "",
series_id="")
def get_fb2_info(tmp_file_path, original_file_extension):
ns = {
'fb': 'http://www.gribuser.ru/xml/fictionbook/2.0',
'l': 'http://www.w3.org/1999/xlink',
}
fb2_file = open(tmp_file_path)
tree = etree.fromstring(fb2_file.read())
authors = tree.xpath(
'/fb:FictionBook/fb:description/fb:title-info/fb:author',
namespaces=ns)
def get_author(element):
last_name = element.xpath('fb:last-name/text()', namespaces=ns)
if len(last_name):
last_name = last_name[0]
else:
last_name = u''
middle_name = element.xpath('fb:middle-name/text()', namespaces=ns)
if len(middle_name):
middle_name = middle_name[0]
else:
middle_name = u''
first_name = element.xpath('fb:first-name/text()', namespaces=ns)
if len(first_name):
first_name = first_name[0]
else:
first_name = u''
return first_name + ' ' + middle_name + ' ' + last_name
author = str(", ".join(map(get_author, authors)))
title = tree.xpath(
'/fb:FictionBook/fb:description/fb:title-info/fb:book-title/text()',
namespaces=ns)
if len(title):
title = str(title[0])
else:
title = u''
description = tree.xpath(
'/fb:FictionBook/fb:description/fb:publish-info/fb:book-name/text()',
namespaces=ns)
if len(description):
description = str(description[0])
else:
description = u''
return uploader.BookMeta(file_path=tmp_file_path,
extension=original_file_extension,
title=title.encode('utf-8').decode('utf-8'),
author=author.encode('utf-8').decode('utf-8'),
cover=None,
description=description,
tags="",
series="",
series_id="",
languages="")
def get_epub_info(tmp_file_path, original_file_name, original_file_extension):
ns = {
'n': 'urn:oasis:names:tc:opendocument:xmlns:container',
'pkg': 'http://www.idpf.org/2007/opf',
'dc': 'http://purl.org/dc/elements/1.1/'
}
zip = zipfile.ZipFile(tmp_file_path)
txt = zip.read('META-INF/container.xml')
tree = etree.fromstring(txt)
cfname = tree.xpath('n:rootfiles/n:rootfile/@full-path', namespaces=ns)[0]
cf = zip.read(cfname)
tree = etree.fromstring(cf)
coverpath = os.path.dirname(cfname)
p = tree.xpath('/pkg:package/pkg:metadata', namespaces=ns)[0]
epub_metadata = {}
for s in ['title', 'description', 'creator']:
tmp = p.xpath('dc:%s/text()' % s, namespaces=ns)
if len(tmp) > 0:
epub_metadata[s] = p.xpath('dc:%s/text()' % s, namespaces=ns)[0]
else:
epub_metadata[s] = "Unknown"
coversection = tree.xpath(
"/pkg:package/pkg:manifest/pkg:item[@id='cover-image']/@href",
namespaces=ns)
if len(coversection) > 0:
coverfile = extractCover(zip, coversection[0], coverpath,
tmp_file_path)
else:
coversection = tree.xpath(
"/pkg:package/pkg:manifest/pkg:item[@id='cover']/@href",
namespaces=ns)
if len(coversection) > 0:
coverfile = extractCover(zip, coversection[0], coverpath,
tmp_file_path)
else:
coverfile = None
if epub_metadata['title'] is None:
title = original_file_name
else:
title = epub_metadata['title']
return uploader.BookMeta(
file_path=tmp_file_path,
extension=original_file_extension,
title=title.encode('utf-8').decode('utf-8'),
author=epub_metadata['creator'].encode('utf-8').decode('utf-8'),
cover=coverfile,
description=epub_metadata['description'],
tags="",
series="",
series_id="")
def default_meta(tmp_file_path, original_file_name, original_file_extension):
return uploader.BookMeta(file_path=tmp_file_path,
extension=original_file_extension,
title=original_file_name,
author="Unknown",
cover=None,
description="",
tags="",
series="",
series_id="")
def get_comic_info(tmp_file_path, original_file_name, original_file_extension):
coverfile = extractCover(tmp_file_path, original_file_extension)
return uploader.BookMeta(file_path=tmp_file_path,
extension=original_file_extension,
title=original_file_name,
author=u"Unknown",
cover=coverfile,
description="",
tags="",
series="",
series_id="",
languages="")
def get_epub_info(tmp_file_path, original_file_name, original_file_extension):
ns = {
'n': 'urn:oasis:names:tc:opendocument:xmlns:container',
'pkg': 'http://www.idpf.org/2007/opf',
'dc': 'http://purl.org/dc/elements/1.1/'
}
epub_zip = zipfile.ZipFile(tmp_file_path)
txt = epub_zip.read('META-INF/container.xml')
tree = etree.fromstring(txt)
cfname = tree.xpath('n:rootfiles/n:rootfile/@full-path', namespaces=ns)[0]
cf = epub_zip.read(cfname)
tree = etree.fromstring(cf)
coverpath = os.path.dirname(cfname)
p = tree.xpath('/pkg:package/pkg:metadata', namespaces=ns)[0]
epub_metadata = {}
for s in ['title', 'description', 'creator', 'language', 'subject']:
tmp = p.xpath('dc:%s/text()' % s, namespaces=ns)
if len(tmp) > 0:
epub_metadata[s] = p.xpath('dc:%s/text()' % s, namespaces=ns)[0]
else:
epub_metadata[s] = "Unknown"
if epub_metadata['subject'] == "Unknown":
epub_metadata['subject'] = ''
if epub_metadata['description'] == "Unknown":
description = tree.xpath("//*[local-name() = 'description']/text()")
if len(description) > 0:
epub_metadata['description'] = description
else:
epub_metadata['description'] = ""
if epub_metadata['language'] == "Unknown":
epub_metadata['language'] = ""
else:
lang = epub_metadata['language'].split('-', 1)[0].lower()
if len(lang) == 2:
epub_metadata['language'] = iso_languages.get(part1=lang).name
elif len(lang) == 3:
epub_metadata['language'] = iso_languages.get(part3=lang).name
else:
epub_metadata['language'] = ""
series = tree.xpath(
"/pkg:package/pkg:metadata/pkg:meta[@name='calibre:series']/@content",
namespaces=ns)
if len(series) > 0:
epub_metadata['series'] = series[0]
else:
epub_metadata['series'] = ''
series_id = tree.xpath(
"/pkg:package/pkg:metadata/pkg:meta[@name='calibre:series_index']/@content",
namespaces=ns)
if len(series_id) > 0:
epub_metadata['series_id'] = series_id[0]
else:
epub_metadata['series_id'] = '1'
coversection = tree.xpath(
"/pkg:package/pkg:manifest/pkg:item[@id='cover-image']/@href",
namespaces=ns)
coverfile = None
if len(coversection) > 0:
coverfile = extract_cover(epub_zip, coversection[0], coverpath,
tmp_file_path)
else:
meta_cover = tree.xpath(
"/pkg:package/pkg:metadata/pkg:meta[@name='cover']/@content",
namespaces=ns)
if len(meta_cover) > 0:
coversection = tree.xpath(
"/pkg:package/pkg:manifest/pkg:item[@id='" + meta_cover[0] +
"']/@href",
namespaces=ns)
if len(coversection) > 0:
filetype = coversection[0].rsplit('.', 1)[-1]
if filetype == "xhtml" or filetype == "html": # if cover is (x)html format
markup = epub_zip.read(
os.path.join(coverpath, coversection[0]))
markup_tree = etree.fromstring(markup)
# no matter xhtml or html with no namespace
imgsrc = markup_tree.xpath(
"//*[local-name() = 'img']/@src")
# imgsrc maybe startwith "../"" so fullpath join then relpath to cwd
filename = os.path.relpath(
os.path.join(
os.path.dirname(
os.path.join(coverpath, coversection[0])),
imgsrc[0]))
coverfile = extract_cover(epub_zip, filename, "",
tmp_file_path)
else:
coverfile = extract_cover(epub_zip, coversection[0],
coverpath, tmp_file_path)
if not epub_metadata['title']:
title = original_file_name
else:
title = epub_metadata['title']
return uploader.BookMeta(
file_path=tmp_file_path,
extension=original_file_extension,
title=title.encode('utf-8').decode('utf-8'),
author=epub_metadata['creator'].encode('utf-8').decode('utf-8'),
cover=coverfile,
description=epub_metadata['description'],
tags=epub_metadata['subject'].encode('utf-8').decode('utf-8'),
series=epub_metadata['series'].encode('utf-8').decode('utf-8'),
series_id=epub_metadata['series_id'].encode('utf-8').decode('utf-8'),
languages=epub_metadata['language'])
