gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-03-16 06:33:31 +01:00
Code Issues Projects Releases Wiki Activity

Convert calibre modules to ebook_converter.

Browse Source 
Here is the first batch of modules, which are needed for converting
several formats to LRF. Some of the logic has been change, more cleanups
will follow.
This commit is contained in:
gryf
2020-04-11 19:33:43 +02:00
parent 69d2e536c5
commit 0f9792df36
252 changed files with 1925 additions and 2344 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
ebook_converter/ebooks/metadata/toc.py
View File

@@ -10,12 +10,12 @@ from collections import Counter
from lxml import etree
from lxml.builder import ElementMaker
from calibre.constants import __appname__, __version__
from calibre.ebooks.chardet import xml_to_unicode
from calibre.utils.xml_parse import safe_xml_fromstring
from calibre.utils.cleantext import clean_xml_chars
from polyglot.builtins import unicode_type, getcwd
from polyglot.urllib import unquote, urlparse
from ebook_converter.constants import __appname__, __version__
from ebook_converter.ebooks.chardet import xml_to_unicode
from ebook_converter.utils.xml_parse import safe_xml_fromstring
from ebook_converter.utils.cleantext import clean_xml_chars
from ebook_converter.polyglot.builtins import unicode_type, getcwd
from ebook_converter.polyglot.urllib import unquote, urlparse
NCX_NS = "http://www.daisy.org/z3986/2005/ncx/"
CALIBRE_NS = "http://calibre.kovidgoyal.net/2009/metadata"
@@ -26,7 +26,7 @@ C = ElementMaker(namespace=CALIBRE_NS, nsmap=NSMAP)
def parse_html_toc(data):
from html5_parser import parse
from calibre.utils.cleantext import clean_xml_chars
from ebook_converter.utils.cleantext import clean_xml_chars
from lxml import etree
if isinstance(data, bytes):
data = xml_to_unicode(data, strip_encoding_pats=True, resolve_entities=True)[0]