mirror of
https://github.com/gryf/ebook-converter.git
synced 2026-03-05 08:25:46 +01:00
gryf
1465e4267f
Every mime related function in main __init__.py has a flag check for the check if initialization has already done. This is nonsense, since it should be done implicitly early on the converter is starting. This commit straight the things out, and initialization is done in cli module. Also, function guess_type was removed, since it's just a proxy for mimetypes.guess_type function.
52 lines
2.0 KiB
Python
52 lines
2.0 KiB
Python
import mimetypes
|
|
import re
|
|
from ebook_converter.ebooks.oeb.base import XPath, urlunquote
|
|
from ebook_converter.polyglot.builtins import as_bytes
|
|
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2014, Kovid Goyal <kovid at kovidgoyal.net>'
|
|
|
|
|
|
class DataURL(object):
|
|
|
|
def __call__(self, oeb, opts):
|
|
from ebook_converter.utils.imghdr import what
|
|
self.log = oeb.log
|
|
attr_path = XPath('//h:img[@src]')
|
|
for item in oeb.spine:
|
|
root = item.data
|
|
if not hasattr(root, 'xpath'):
|
|
continue
|
|
for img in attr_path(root):
|
|
raw = img.get('src', '')
|
|
if not raw.startswith('data:'):
|
|
continue
|
|
header, data = raw.partition(',')[0::2]
|
|
if not header.startswith('data:image/') or not data:
|
|
continue
|
|
if ';base64' in header:
|
|
data = re.sub(r'\s+', '', data)
|
|
from ebook_converter.polyglot.binary import from_base64_bytes
|
|
try:
|
|
data = from_base64_bytes(data)
|
|
except Exception:
|
|
self.log.error('Found invalid base64 encoded data URI, ignoring it')
|
|
continue
|
|
else:
|
|
data = urlunquote(data)
|
|
data = as_bytes(data)
|
|
fmt = what(None, data)
|
|
if not fmt:
|
|
self.log.warn('Image encoded as data URL has unknown format, ignoring')
|
|
continue
|
|
img.set('src', item.relhref(self.convert_image_data_uri(data, fmt, oeb)))
|
|
|
|
def convert_image_data_uri(self, data, fmt, oeb):
|
|
self.log('Found image encoded as data URI converting it to normal image')
|
|
from ebook_converter import guess_type
|
|
item_id, item_href = oeb.manifest.generate('data-url-image', 'data-url-image.' + fmt)
|
|
oeb.manifest.add(item_id, item_href,
|
|
mimetypes.guess_type(item_href)[0], data=data)
|
|
return item_href
|