def _metadata_from_opf(self, opf):
from ebook_converter.ebooks.metadata.opf2 import OPF
from ebook_converter.ebooks.oeb.transforms.metadata import \
meta_info_to_oeb_metadata
stream = io.BytesIO(
etree.tostring(opf, xml_declaration=True, encoding='utf-8'))
o = OPF(stream)
pwm = o.primary_writing_mode
if pwm:
self.oeb.metadata.primary_writing_mode = pwm
mi = o.to_book_metadata()
if not mi.language:
mi.language = get_lang().replace('_', '-')
self.oeb.metadata.add('language', mi.language)
if not mi.book_producer:
mi.book_producer = ('%(a)s (%(v)s) [http://%(a)s-ebook.com]' %
dict(a=__appname__, v=__version__))
meta_info_to_oeb_metadata(mi, self.oeb.metadata, self.logger)
m = self.oeb.metadata
m.add('identifier', str(uuid.uuid4()), id='uuid_id', scheme='uuid')
self.oeb.uid = self.oeb.metadata.identifier[-1]
if not m.title:
m.add('title', self.oeb.translate('Unknown'))
has_aut = False
for x in m.creator:
if getattr(x, 'role', '').lower() in ('', 'aut'):
has_aut = True
break
if not has_aut:
m.add('creator', self.oeb.translate('Unknown'), role='aut')
def read_embedded_metadata(self, root, elem, guide):
raw = b'<?xml version="1.0" encoding="utf-8" ?>\n<package>' + \
html.tostring(elem, encoding='utf-8') + b'</package>'
stream = io.BytesIO(raw)
opf = OPF(stream)
self.embedded_mi = opf.to_book_metadata()
if guide is not None:
for ref in guide.xpath('descendant::reference'):
if 'cover' in ref.get('type', '').lower():
href = ref.get('href', '')
if href.startswith('#'):
href = href[1:]
anchors = root.xpath('//*[@id="%s"]' % href)
if anchors:
cpos = anchors[0]
reached = False
for elem in root.iter():
if elem is cpos:
reached = True
if reached and elem.tag == 'img':
cover = elem.get('src', None)
self.embedded_mi.cover = cover
elem.getparent().remove(elem)
break
break
def opf_metadata(opfpath):
if hasattr(opfpath, 'read'):
f = opfpath
opfpath = getattr(f, 'name', os.getcwd())
else:
f = open(opfpath, 'rb')
try:
opf = OPF(f, os.path.dirname(opfpath))
if opf.application_id is not None:
mi = opf.to_book_metadata()
if hasattr(opf, 'cover') and opf.cover:
cpath = os.path.join(os.path.dirname(opfpath), opf.cover)
if os.access(cpath, os.R_OK):
fmt = cpath.rpartition('.')[-1]
with open(cpath, 'rb') as f:
data = f.read()
mi.cover_data = (fmt, data)
return mi
except Exception:
import traceback
traceback.print_exc()
pass
def convert(self, stream, options, file_ext, log, accelerators):
from ebook_converter.ebooks.chardet import xml_to_unicode
from ebook_converter.ebooks.metadata.opf2 import OPF
from ebook_converter.utils.zipfile import ZipFile
self.log = log
html = u''
top_levels = []
# Extract content from zip archive.
zf = ZipFile(stream)
zf.extractall()
# Find the HTML file in the archive. It needs to be
# top level.
index = u''
multiple_html = False
# Get a list of all top level files in the archive.
for x in os.listdir(u'.'):
if os.path.isfile(x):
top_levels.append(x)
# Try to find an index. file.
for x in top_levels:
if x.lower() in ('index.html', 'index.xhtml', 'index.htm'):
index = x
break
# Look for multiple HTML files in the archive. We look at the
# top level files only as only they matter in HTMLZ.
for x in top_levels:
if os.path.splitext(x)[1].lower() in ('.html', '.xhtml', '.htm'):
# Set index to the first HTML file found if it's not
# called index.
if not index:
index = x
else:
multiple_html = True
# Warn the user if there multiple HTML file in the archive. HTMLZ
# supports a single HTML file. A conversion with a multiple HTML file
# HTMLZ archive probably won't turn out as the user expects. With
# Multiple HTML files ZIP input should be used in place of HTMLZ.
if multiple_html:
log.warn('Multiple HTML files found in the archive. Only %s will '
'be used.' % index)
if index:
with open(index, 'rb') as tf:
html = tf.read()
else:
raise Exception('No top level HTML file found.')
if not html:
raise Exception('Top level HTML file %s is empty' % index)
# Encoding
if options.input_encoding:
ienc = options.input_encoding
else:
ienc = xml_to_unicode(html[:4096])[-1]
html = html.decode(ienc, 'replace')
# Run the HTML through the html processing plugin.
from ebook_converter.customize.ui import plugin_for_input_format
html_input = plugin_for_input_format('html')
for opt in html_input.options:
setattr(options, opt.option.name, opt.recommended_value)
options.input_encoding = 'utf-8'
base = os.getcwd()
htmlfile = os.path.join(base, u'index.html')
c = 0
while os.path.exists(htmlfile):
c += 1
htmlfile = u'index%d.html' % c
with open(htmlfile, 'wb') as f:
f.write(html.encode('utf-8'))
odi = options.debug_pipeline
options.debug_pipeline = None
# Generate oeb from html conversion.
with open(htmlfile, 'rb') as f:
oeb = html_input.convert(f, options, 'html', log, {})
options.debug_pipeline = odi
os.remove(htmlfile)
# Set metadata from file.
from ebook_converter.customize.ui import get_file_type_metadata
from ebook_converter.ebooks.oeb.transforms.metadata import meta_info_to_oeb_metadata
mi = get_file_type_metadata(stream, file_ext)
meta_info_to_oeb_metadata(mi, oeb.metadata, log)
# Get the cover path from the OPF.
cover_path = None
opf = None
for x in top_levels:
if os.path.splitext(x)[1].lower() == u'.opf':
opf = x
break
if opf:
opf = OPF(opf, basedir=os.getcwd())
cover_path = opf.raster_cover or opf.cover
# Set the cover.
if cover_path:
cdata = None
with open(os.path.join(os.getcwd(), cover_path), 'rb') as cf:
cdata = cf.read()
cover_name = os.path.basename(cover_path)
id, href = oeb.manifest.generate('cover', cover_name)
oeb.manifest.add(id,
href,
mimetypes.guess_type(cover_name)[0],
data=cdata)
oeb.guide.add('cover', 'Cover', href)
return oeb
def convert(self, oeb_book, output_path, input_plugin, opts, log):
from lxml import etree
from ebook_converter.ebooks.oeb.base import OEB_IMAGES, SVG_MIME
from ebook_converter.ebooks.metadata.opf2 import OPF, metadata_to_opf
from ebook_converter.utils.zipfile import ZipFile
from ebook_converter.utils.filenames import ascii_filename
# HTML
if opts.htmlz_css_type == 'inline':
from ebook_converter.ebooks.htmlz.oeb2html import OEB2HTMLInlineCSSizer
OEB2HTMLizer = OEB2HTMLInlineCSSizer
elif opts.htmlz_css_type == 'tag':
from ebook_converter.ebooks.htmlz.oeb2html import OEB2HTMLNoCSSizer
OEB2HTMLizer = OEB2HTMLNoCSSizer
else:
from ebook_converter.ebooks.htmlz.oeb2html import OEB2HTMLClassCSSizer as OEB2HTMLizer
with TemporaryDirectory(u'_htmlz_output') as tdir:
htmlizer = OEB2HTMLizer(log)
html = htmlizer.oeb2html(oeb_book, opts)
fname = u'index'
if opts.htmlz_title_filename:
from ebook_converter.utils.filenames import shorten_components_to
fname = shorten_components_to(100, (ascii_filename(str(oeb_book.metadata.title[0])),))[0]
with open(os.path.join(tdir, fname+u'.html'), 'wb') as tf:
if isinstance(html, str):
html = html.encode('utf-8')
tf.write(html)
# CSS
if opts.htmlz_css_type == 'class' and opts.htmlz_class_style == 'external':
with open(os.path.join(tdir, u'style.css'), 'wb') as tf:
tf.write(htmlizer.get_css(oeb_book))
# Images
images = htmlizer.images
if images:
if not os.path.exists(os.path.join(tdir, u'images')):
os.makedirs(os.path.join(tdir, u'images'))
for item in oeb_book.manifest:
if item.media_type in OEB_IMAGES and item.href in images:
if item.media_type == SVG_MIME:
data = etree.tostring(item.data, encoding='unicode')
else:
data = item.data
fname = os.path.join(tdir, u'images', images[item.href])
with open(fname, 'wb') as img:
img.write(data)
# Cover
cover_path = None
try:
cover_data = None
if oeb_book.metadata.cover:
term = oeb_book.metadata.cover[0].term
cover_data = oeb_book.guide[term].item.data
if cover_data:
from ebook_converter.utils.img import save_cover_data_to
cover_path = os.path.join(tdir, u'cover.jpg')
with open(cover_path, 'w') as cf:
cf.write('')
save_cover_data_to(cover_data, cover_path)
except:
import traceback
traceback.print_exc()
# Metadata
with open(os.path.join(tdir, u'metadata.opf'), 'wb') as mdataf:
opf = OPF(io.BytesIO(etree.tostring(oeb_book.metadata.to_opf1(), encoding='UTF-8')))
mi = opf.to_book_metadata()
if cover_path:
mi.cover = u'cover.jpg'
mdataf.write(metadata_to_opf(mi))
htmlz = ZipFile(output_path, 'w')
htmlz.add_dir(tdir)