Backup_Repos/calibre
1
0
Fork 0
mirror of git://github.com/kovidgoyal/calibre.git synced 2025-12-23 04:25:28 +01:00
Code Issues Projects Releases Wiki Activity

HTML Input: Handle HTML fragments more gracefully. Fixes #4854 (Imported HTML fragments get converted to ZIPs containing no HTML)

Browse source
This commit is contained in:
Kovid Goyal 2010-02-10 15:31:11 -07:00
parent a0671a64d4
commit b33bfe2e43
2 changed files with 5 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
src/calibre/ebooks/html/input.py
View file

@ -111,7 +111,7 @@ def __init__(self, path_to_html_file, level, encoding, verbose, referrer=None):
raise IOError(msg)
raise IgnoreFile(msg, err.errno)
self.is_binary = not bool(self.HTML_PAT.search(src[:4096]))
self.is_binary = level > 0 and not bool(self.HTML_PAT.search(src[:4096]))
if not self.is_binary:
if encoding is None:
encoding = xml_to_unicode(src[:4096], verbose=verbose)[-1]

6
src/calibre/ebooks/oeb/base.py
View file

@ -851,8 +851,10 @@ def first_pass(data):
self.oeb.log.warn('File %r appears to be a HTML fragment'%self.href)
nroot = etree.fromstring('<html><body/></html>')
parent = nroot[0]
for child in list(data):
child.getparent().remove(child)
for child in list(data.iter()):
oparent = child.getparent()
if oparent is not None:
oparent.remove(child)
parent.append(child)
data = nroot