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

Fix more bugs in the BD regexps.

Browse Source
This commit is contained in:
Kovid Goyal 2007-10-10 18:26:50 +00:00
parent 279510a5e7
commit 6cfd3561e6
1 changed files with 22 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
src/libprs500/ebooks/lrf/html/convert_from.py
View File

@ -110,16 +110,16 @@ class HTMLConverter(object):
(re.compile('<hr>', re.IGNORECASE), (re.compile('<hr>', re.IGNORECASE),
lambda match : '<span style="page-break-after:always"> </span>'), lambda match : '<span style="page-break-after:always"> </span>'),
# Create header tags # Create header tags
(re.compile('<h2.*?id=BookTitle.*?(align=)*(?(1)(\w+))*.*?>(.*?)</h2>', re.IGNORECASE|re.DOTALL), (re.compile('<h2[^><]*?id=BookTitle[^><]*?(align=)*(?(1)(\w+))*[^><]*?>[^><]*?</h2>', re.IGNORECASE),
lambda match : '<h1 id="BookTitle" align="%s">%s</h1>'%(match.group(2) if match.group(2) else 'center', match.group(3))), 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), (re.compile('<h2[^><]*?id=BookAuthor[^><]*?(align=)*(?(1)(\w+))*[^><]*?>[^><]*?</h2>', re.IGNORECASE),
lambda match : '<h2 id="BookAuthor" align="%s">%s</h2>'%(match.group(2) if match.group(2) else 'center', match.group(3))), lambda match : '<h2 id="BookAuthor" align="%s">%s</h2>'%(match.group(2) if match.group(2) else 'center', match.group(3))),
(re.compile('<span\s+id=title.*?>(.*?)</span>', re.IGNORECASE|re.DOTALL), (re.compile('<span[^><]*?id=title[^><]*?>(.*?)</span>', re.IGNORECASE|re.DOTALL),
lambda match : '<h2>%s</h2>'%(match.group(1),)), lambda match : '<h2>%s</h2>'%(match.group(1),)),
(re.compile('<span\s+id=subtitle.*?>(.*?)</span>', re.IGNORECASE|re.DOTALL), (re.compile('<span[^><]*?id=subtitle[^><]*?>(.*?)</span>', re.IGNORECASE|re.DOTALL),
lambda match : '<h3>%s</h3>'%(match.group(1),)), lambda match : '<h3>%s</h3>'%(match.group(1),)),
# Blank lines # Blank lines
(re.compile('<div.*?>(&nbsp;){4}</div>', re.IGNORECASE), (re.compile('<div[^><]*?>(&nbsp;){4}</div>', re.IGNORECASE),
lambda match : '<p></p>'), lambda match : '<p></p>'),
] ]
@ -229,22 +229,12 @@ class HTMLConverter(object):
return bool(soup.find('meta', attrs={'name':'Publisher', return bool(soup.find('meta', attrs={'name':'Publisher',
'content':re.compile('Baen', re.IGNORECASE)})) 'content':re.compile('Baen', re.IGNORECASE)}))
def start_on_file(self, path, is_root=True, link_level=0): def preprocess(self, raw):
self.css = HTMLConverter.CSS.copy()
self.pseudo_css = self.override_pcss.copy()
self.css.update(self.override_css)
path = os.path.abspath(path)
os.chdir(os.path.dirname(path))
self.file_name = os.path.basename(path)
self.logger.info('Processing %s\n\tParsing HTML...', self.file_name)
sys.stdout.flush()
nmassage = copy.copy(BeautifulSoup.MARKUP_MASSAGE) nmassage = copy.copy(BeautifulSoup.MARKUP_MASSAGE)
nmassage.extend(HTMLConverter.MARKUP_MASSAGE) nmassage.extend(HTMLConverter.MARKUP_MASSAGE)
if self.baen: if self.baen:
nmassage.extend(HTMLConverter.BAEN) nmassage.extend(HTMLConverter.BAEN)
raw = open(self.file_name, 'rb').read()
if self.pdftohtml: if self.pdftohtml:
nmassage.extend(HTMLConverter.PDFTOHTML) nmassage.extend(HTMLConverter.PDFTOHTML)
if self.book_designer: if self.book_designer:
@ -263,7 +253,7 @@ class HTMLConverter(object):
if not self.baen and self.is_baen(soup): if not self.baen and self.is_baen(soup):
self.baen = True self.baen = True
self.logger.info('Baen file detected. Re-parsing...') self.logger.info('Baen file detected. Re-parsing...')
return self.start_on_file(path, is_root=is_root, link_level=link_level) return self.preprocess(raw)
if self.book_designer: if self.book_designer:
t = soup.find(id='BookTitle') t = soup.find(id='BookTitle')
if t: if t:
@ -277,6 +267,21 @@ class HTMLConverter(object):
dump.write(unicode(soup).encode('utf-8')) dump.write(unicode(soup).encode('utf-8'))
self.logger.info('Written preprocessed HTML to '+dump.name) self.logger.info('Written preprocessed HTML to '+dump.name)
dump.close() dump.close()
print soup
return soup
def start_on_file(self, path, is_root=True, link_level=0):
self.css = HTMLConverter.CSS.copy()
self.pseudo_css = self.override_pcss.copy()
self.css.update(self.override_css)
path = os.path.abspath(path)
os.chdir(os.path.dirname(path))
self.file_name = os.path.basename(path)
self.logger.info('Processing %s\n\tParsing HTML...', self.file_name)
sys.stdout.flush()
soup = self.preprocess(open(self.file_name, 'rb').read())
self.logger.info('\tConverting to BBeB...') self.logger.info('\tConverting to BBeB...')
sys.stdout.flush() sys.stdout.flush()
self.current_page = None self.current_page = None