voussoir/epubfile
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Add function promote_xhtml_headers.

Browse source 
Isn't used anywhere yet but may as well have it to balance out.
This commit is contained in:
Ethan Dalool 2020-01-20 17:55:49 -08:00
parent 59776e5b4e
commit 9411e8cf80
1 changed files with 33 additions and 20 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

53
epubfile.py
View file

@ -156,26 +156,6 @@ def extract_epub(epub_filepath, directory):
with zipfile.ZipFile(epub_filepath.absolute_path, 'r') as z: with zipfile.ZipFile(epub_filepath.absolute_path, 'r') as z:
z.extractall(directory.absolute_path) z.extractall(directory.absolute_path)
def demote_xhtml_headers(xhtml, return_soup=False):
if isinstance(xhtml, bs4.BeautifulSoup):
xhtml = str(xhtml)
replacements = [
(r'<h5([^>]*?>.*?)</h5>', r'<h6\1</h6>'),
(r'<h4([^>]*?>.*?)</h4>', r'<h5\1</h5>'),
(r'<h3([^>]*?>.*?)</h3>', r'<h4\1</h4>'),
(r'<h2([^>]*?>.*?)</h2>', r'<h3\1</h3>'),
(r'<h1([^>]*?>.*?)</h1>', r'<h2\1</h2>'),
]
for (re_from, re_to) in replacements:
xhtml = re.sub(re_from, re_to, xhtml, flags=re.DOTALL)
if return_soup:
soup = bs4.BeautifulSoup(xhtml, 'html5lib')
return soup
return xhtml
def fix_xhtml(xhtml, return_soup=False): def fix_xhtml(xhtml, return_soup=False):
if isinstance(xhtml, bs4.BeautifulSoup): if isinstance(xhtml, bs4.BeautifulSoup):
soup = xhtml soup = xhtml
@ -228,6 +208,39 @@ def fix_xhtml(xhtml, return_soup=False):
return soup return soup
return str(soup) return str(soup)
def xhtml_replacements(xhtml, replacements, return_soup=False):
if isinstance(xhtml, bs4.BeautifulSoup):
xhtml = str(xhtml)
for (re_from, re_to) in replacements:
xhtml = re.sub(re_from, re_to, xhtml, flags=re.DOTALL)
if return_soup:
soup = bs4.BeautifulSoup(xhtml, 'html5lib')
return soup
return xhtml
def demote_xhtml_headers(xhtml, return_soup=False):
replacements = [
(r'<h5([^>]*?>.*?)</h5>', r'<h6\1</h6>'),
(r'<h4([^>]*?>.*?)</h4>', r'<h5\1</h5>'),
(r'<h3([^>]*?>.*?)</h3>', r'<h4\1</h4>'),
(r'<h2([^>]*?>.*?)</h2>', r'<h3\1</h3>'),
(r'<h1([^>]*?>.*?)</h1>', r'<h2\1</h2>'),
]
return xhtml_replacements(xhtml, replacements, return_soup=return_soup)
def promote_xhtml_headers(xhtml, return_soup=False):
replacements = [
(r'<h2([^>]*?>.*?)</h2>', r'<h1\1</h1>'),
(r'<h3([^>]*?>.*?)</h3>', r'<h2\1</h2>'),
(r'<h4([^>]*?>.*?)</h4>', r'<h3\1</h3>'),
(r'<h5([^>]*?>.*?)</h5>', r'<h4\1</h4>'),
(r'<h6([^>]*?>.*?)</h6>', r'<h5\1</h5>'),
]
return xhtml_replacements(xhtml, replacements, return_soup=return_soup)
def get_directory_for_mimetype(mime): def get_directory_for_mimetype(mime):
directory = ( directory = (
MIMETYPE_DIRECTORIES.get(mime) or MIMETYPE_DIRECTORIES.get(mime) or