diff --git a/src/calibre/ebooks/chm/input.py b/src/calibre/ebooks/chm/input.py
index 820178408c..e3c3deba78 100644
--- a/src/calibre/ebooks/chm/input.py
+++ b/src/calibre/ebooks/chm/input.py
@@ -49,7 +49,6 @@ class CHMInput(InputFormatPlugin):
log.debug('stream.name=%s' % stream.name)
mainname = self._chmtohtml(tdir, chm_name, no_images, log)
mainpath = os.path.join(tdir, mainname)
- #raw_input()
metadata = get_metadata_from_reader(self._chm_reader)
@@ -141,10 +140,9 @@ class CHMInput(InputFormatPlugin):
log.debug('Found %d section nodes' % len(chapters))
htmlpath = os.path.splitext(hhcpath)[0] + ".html"
f = open(htmlpath, 'wb')
- f.write('\n')
-
if chapters:
+ f.write('\n')
path0 = chapters[0][1]
subpath = os.path.dirname(path0)
@@ -158,7 +156,9 @@ class CHMInput(InputFormatPlugin):
url = url.encode('utf-8')
f.write(url)
- f.write("")
+ f.write("")
+ else:
+ f.write(hhcdata)
f.close()
return htmlpath
diff --git a/src/calibre/ebooks/chm/reader.py b/src/calibre/ebooks/chm/reader.py
index d0a81e8e7f..67a2d36607 100644
--- a/src/calibre/ebooks/chm/reader.py
+++ b/src/calibre/ebooks/chm/reader.py
@@ -8,7 +8,7 @@ import os, re
from mimetypes import guess_type as guess_mimetype
from calibre.ebooks.BeautifulSoup import BeautifulSoup, NavigableString
-from calibre.constants import iswindows
+from calibre.constants import iswindows, filesystem_encoding
from calibre.utils.chm.chm import CHMFile
from calibre.utils.chm.chmlib import (
CHM_RESOLVE_SUCCESS, CHM_ENUMERATE_NORMAL,
@@ -78,6 +78,8 @@ class CHMError(Exception):
class CHMReader(CHMFile):
def __init__(self, input, log):
CHMFile.__init__(self)
+ if isinstance(input, unicode):
+ input = input.encode(filesystem_encoding)
if not self.LoadCHM(input):
raise CHMError("Unable to open CHM file '%s'"%(input,))
self.log = log
@@ -91,7 +93,6 @@ class CHMReader(CHMFile):
self.root, ext = os.path.splitext(self.topics.lstrip('/'))
self.hhc_path = self.root + ".hhc"
-
def _parse_toc(self, ul, basedir=os.getcwdu()):
toc = TOC(play_order=self._playorder, base_path=basedir, text='')
self._playorder += 1
@@ -152,6 +153,8 @@ class CHMReader(CHMFile):
if f.lower() == self.hhc_path.lower():
self.hhc_path = f
break
+ if self.hhc_path not in files and files:
+ self.hhc_path = files[0]
def _reformat(self, data):
try:
@@ -159,7 +162,7 @@ class CHMReader(CHMFile):
soup = BeautifulSoup(data)
except ValueError:
# hit some strange encoding problems...
- print "Unable to parse html for cleaning, leaving it :("
+ self.log.exception("Unable to parse html for cleaning, leaving it")
return data
# nuke javascript...
[s.extract() for s in soup('script')]