Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 10:44:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix bug in BD regexp

Browse Source
This commit is contained in:
Kovid Goyal 2007-10-08 18:03:41 +00:00
parent 653551ab6f
commit 3a7a5b37f3
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/libprs500/ebooks/lrf/html/convert_from.py
View File

@ -101,9 +101,9 @@ class HTMLConverter(object):
lambda match : '<h1 id="BookTitle" align="%s">%s</h1>'%(match.group(2) if match.group(2) else 'center', match.group(3))),
(re.compile('<h2.*?id=BookAuthor.*?(align=)*(?(1)(\w+))*.*?>(.*?)</h2>', re.IGNORECASE|re.DOTALL),
lambda match : '<h2 id="BookAuthor" align="%s">%s</h2>'%(match.group(2) if match.group(2) else 'center', match.group(3))),
(re.compile('<span.*?id=title.*?>(.*?)</span>', re.IGNORECASE|re.DOTALL),
(re.compile('<span\s+id=title.*?>(.*?)</span>', re.IGNORECASE|re.DOTALL),
lambda match : '<h2>%s</h2>'%(match.group(1),)),
(re.compile('<span.*?id=subtitle.*?>(.*?)</span>', re.IGNORECASE|re.DOTALL),
(re.compile('<span\s+id=subtitle.*?>(.*?)</span>', re.IGNORECASE|re.DOTALL),
lambda match : '<h3>%s</h3>'%(match.group(1),)),
# Blank lines
(re.compile('<div.*?>(&nbsp;){4}</div>', re.IGNORECASE),
@ -231,7 +231,7 @@ class HTMLConverter(object):
soup = BeautifulSoup(raw,
convertEntities=BeautifulSoup.HTML_ENTITIES,
markupMassage=nmassage)
if not self.baen and self.is_baen(soup):
self.baen = True
self.logger.info('Baen file detected. Re-parsing...')