mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
Fix various unicode issues
This commit is contained in:
commit
7a0359708c
@ -34,7 +34,7 @@ def _metadata_from_table(soup, searchfor):
|
||||
td = td.parent
|
||||
# there appears to be multiple ways of structuring the metadata
|
||||
# on the home page. cue some nasty special-case hacks...
|
||||
if re.match(r'^\s*'+searchfor+r'\s*$', td.renderContents(), flags=re.I):
|
||||
if re.match(r'^\s*'+searchfor+r'\s*$', td.renderContents(None), flags=re.I):
|
||||
meta = _detag(td.findNextSibling('td'))
|
||||
return re.sub('^:', '', meta).strip()
|
||||
else:
|
||||
@ -46,7 +46,7 @@ def _metadata_from_span(soup, searchfor):
|
||||
if span is None:
|
||||
return None
|
||||
# this metadata might need some cleaning up still :/
|
||||
return _detag(span.renderContents().strip())
|
||||
return _detag(span.renderContents(None).strip())
|
||||
|
||||
def _get_authors(soup):
|
||||
aut = (_metadata_from_span(soup, r'author')
|
||||
|
@ -3869,9 +3869,7 @@ class EPUB_MOBI(CatalogPlugin):
|
||||
elem.extract()
|
||||
|
||||
# Reconstruct comments w/o <div>s
|
||||
comments = soup.renderContents()
|
||||
if not isinstance(comments, unicode):
|
||||
comments = comments.decode('utf-8', 'replace')
|
||||
comments = soup.renderContents(None)
|
||||
|
||||
# Convert \n\n to <p>s
|
||||
if re.search('\n\n', comments):
|
||||
@ -3883,7 +3881,7 @@ class EPUB_MOBI(CatalogPlugin):
|
||||
pTag.insert(0,p)
|
||||
soup.insert(tsc,pTag)
|
||||
tsc += 1
|
||||
comments = soup.renderContents()
|
||||
comments = soup.renderContents(None)
|
||||
|
||||
# Convert solo returns to <br />
|
||||
comments = re.sub('[\r\n]','<br />', comments)
|
||||
|
Loading…
x
Reference in New Issue
Block a user