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

Get mobi2oeb to produce nicer looking HTML output

Browse Source
This commit is contained in:
Kovid Goyal 2008-03-08 19:10:38 +00:00
parent 8e0a8f1375
commit dc09be0385
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/libprs500/ebooks/mobi/reader.py
View File

@ -26,6 +26,7 @@ except ImportError:
import Image as PILImage import Image as PILImage
from libprs500 import __appname__ from libprs500 import __appname__
from libprs500.ebooks.BeautifulSoup import BeautifulSoup
from libprs500.ebooks.mobi import MobiError from libprs500.ebooks.mobi import MobiError
from libprs500.ebooks.mobi.huffcdic import HuffReader from libprs500.ebooks.mobi.huffcdic import HuffReader
from libprs500.ebooks.mobi.palmdoc import decompress_doc from libprs500.ebooks.mobi.palmdoc import decompress_doc
@ -177,9 +178,12 @@ class MobiReader(object):
self.processed_html = re.compile('<head>', re.IGNORECASE).sub( self.processed_html = re.compile('<head>', re.IGNORECASE).sub(
'<head>\n<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />\n', '<head>\n<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />\n',
self.processed_html) self.processed_html)
soup = BeautifulSoup(self.processed_html.replace('> <', '>\n<'))
for elem in soup.findAll(['metadata', 'guide']):
elem.extract()
htmlfile = os.path.join(output_dir, self.name+'.html') htmlfile = os.path.join(output_dir, self.name+'.html')
open(htmlfile, 'wb').write(self.processed_html.encode('utf8')) open(htmlfile, 'wb').write(unicode(soup).encode('utf8'))
self.htmlfile = htmlfile self.htmlfile = htmlfile
if self.book_header.exth is not None: if self.book_header.exth is not None: