Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Improved character encoding detection for html2lrf

Browse Source
This commit is contained in:
Kovid Goyal 2008-01-17 16:11:52 +00:00
parent 5a36f6a755
commit 9a79f6f4a3
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/libprs500/ebooks/lrf/html/convert_from.py
View File

@ -33,7 +33,8 @@ except ImportError:
import Image as PILImage
from libprs500.ebooks.BeautifulSoup import BeautifulSoup, Comment, Tag, \
NavigableString, Declaration, ProcessingInstruction
NavigableString, Declaration, ProcessingInstruction, \
UnicodeDammit
from libprs500.ebooks.lrf.pylrs.pylrs import Paragraph, CR, Italic, ImageStream, \
TextBlock, ImageBlock, JumpButton, CharButton, \
Plot, Image, BlockSpace, RuledLine, BookSetting, Canvas, DropCaps, \
@ -348,7 +349,7 @@ class HTMLConverter(object):
upath = path.encode('utf-8') if isinstance(path, unicode) else path
if not os.path.exists(upath):
upath = upath.replace('&', '%26') #convertlit replaces & with %26 in file names
raw = open(upath, 'rb').read()
raw = UnicodeDammit(open(upath, 'rb').read()).unicode
soup = self.preprocess(raw)
self.logger.info('\tConverting to BBeB...')
self.current_page = None