Backup_Repos/FanFicFare
1
0
Fork 0
mirror of https://github.com/JimmXinu/FanFicFare.git synced 2025-12-23 17:23:40 +01:00
Code Issues Projects Releases Wiki Activity

Fix for mobi output--link to TOC works again--was broken by html5lib enforcing html5 rules.

Browse source
This commit is contained in:
Jim Miller 2018-08-09 19:54:01 -05:00
parent 6fbf3bc282
commit a93eeec5eb
2 changed files with 10 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
fanficfare/mobi.py
View file

@ -91,7 +91,9 @@ class Converter:
toc_html = []
body_html = []
PAGE_BREAK = '<mbp:pagebreak>'
## This gets broken by html5lib/bs4fixed being helpful, but we'll
## fix it inside mobihtml.py
PAGE_BREAK = '<mbp:pagebreak/>'
# pull out the title page, assumed first html_strs.
htmltitle = html_strs[0]

10
fanficfare/mobihtml.py
View file

@ -33,6 +33,12 @@ class HtmlProcessor:
self.unfill = unfill
# html = self._ProcessRawHtml(html)
self._soup = BeautifulSoup(html,'html5lib')
## mobi format wants to find this <guide> tag inside <head>.
## html5lib, on the other hand, moved it to <body>. So we'll move
## it back.
guide = self._soup.find('guide')
if guide:
self._soup.head.append(guide)
if self._soup.title.contents:
self.title = self._soup.title.contents[0]
else:
@ -66,10 +72,8 @@ class HtmlProcessor:
def _ReplaceAnchorStubs(self):
# TODO: Browsers allow extra whitespace in the href names.
# str() instead of unicode() rather than figure out how to fix
# ancient mobi.py code.
assembled_text = ensure_binary(unicode(self._soup))
# bs4 creating close tags for <mbp:pagebreak>
# html5lib/bs4 creates close tags for <mbp:pagebreak>
assembled_text = assembled_text.replace(b'<mbp:pagebreak>',b'<mbp:pagebreak/>')
assembled_text = assembled_text.replace(b'</mbp:pagebreak>',b'')