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

Fix #5132 (CHM to EPUB for Nook fails)

Browse Source
This commit is contained in:
Kovid Goyal 2010-03-30 23:35:00 +05:30
parent f871846e18
commit 799c647c8d
2 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/calibre/ebooks/chm/metadata.py
View File

@ -103,7 +103,8 @@ def _get_cover(soup, rdr):
r[0] = img['src'] r[0] = img['src']
l = r.keys() l = r.keys()
l.sort() l.sort()
ans = r[l[0]] if l:
ans = r[l[0]]
# this link comes from the internal html, which is in a subdir # this link comes from the internal html, which is in a subdir
if ans is not None: if ans is not None:
try: try:

8
src/calibre/ebooks/chm/reader.py
View File

@ -7,7 +7,7 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>,' \
import os, re import os, re
from mimetypes import guess_type as guess_mimetype from mimetypes import guess_type as guess_mimetype
from BeautifulSoup import BeautifulSoup, NavigableString from calibre.ebooks.BeautifulSoup import BeautifulSoup, NavigableString
from calibre.utils.chm.chm import CHMFile from calibre.utils.chm.chm import CHMFile
from calibre.utils.chm.chmlib import ( from calibre.utils.chm.chmlib import (
@ -17,6 +17,7 @@ from calibre.utils.chm.chmlib import (
from calibre.utils.config import OptionParser from calibre.utils.config import OptionParser
from calibre.ebooks.metadata.toc import TOC from calibre.ebooks.metadata.toc import TOC
from calibre.ebooks.chardet import xml_to_unicode
def match_string(s1, s2_already_lowered): def match_string(s1, s2_already_lowered):
@ -145,8 +146,9 @@ class CHMReader(CHMFile):
def _reformat(self, data): def _reformat(self, data):
try: try:
data = xml_to_unicode(data, strip_encoding_pats=True)[0]
soup = BeautifulSoup(data) soup = BeautifulSoup(data)
except UnicodeEncodeError: except ValueError:
# hit some strange encoding problems... # hit some strange encoding problems...
print "Unable to parse html for cleaning, leaving it :(" print "Unable to parse html for cleaning, leaving it :("
return data return data
@ -184,7 +186,7 @@ class CHMReader(CHMFile):
# and some don't even have a src= ?! # and some don't even have a src= ?!
pass pass
# now give back some pretty html. # now give back some pretty html.
return soup.prettify() return soup.prettify('utf-8')
def Contents(self): def Contents(self):
if self._contents is not None: if self._contents is not None: