lxbfYeaa/BookConverter
Archived
Template
1
0
Fork 0
forked from LiveCarta/BookConverter
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

epub converter: update pre

Browse Source
This commit is contained in:
shirshasa
2021-07-09 10:53:56 +03:00
parent a5a9853b64
commit 8eda9337ef
1 changed files with 10 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
src/html_epub_preprocessor.py
View File

@@ -431,6 +431,14 @@ def preprocess_block_tags(chapter_tag):
block.unwrap() block.unwrap()
def _prepare_formatted(text):
text = text.replace("<", "\x3C;")
text = text.replace(">", "\x3E;")
text = text.replace('\t', "\xa0 \xa0 \xa0 ")
text = text.replace(' ', "\xa0 ")
return text
def preprocess_pre_tags(chapter_tag): def preprocess_pre_tags(chapter_tag):
for pre in chapter_tag.find_all("pre"): for pre in chapter_tag.find_all("pre"):
new_tag = BeautifulSoup(features='lxml').new_tag("span") new_tag = BeautifulSoup(features='lxml').new_tag("span")
@@ -441,15 +449,13 @@ def preprocess_pre_tags(chapter_tag):
for child in pre.children: for child in pre.children:
if isinstance(child, NavigableString): if isinstance(child, NavigableString):
text = pre.text text = pre.text
text = text.replace("<", "\x3C;") text = _prepare_formatted(text)
text = text.replace(">", "\x3E;")
text = text.replace('\t', "\xa0 \xa0 \xa0 ")
text = text.replace(' ', "\xa0 ")
elements = re.split('\r\n|\n|\r', text) elements = re.split('\r\n|\n|\r', text)
for i in elements: for i in elements:
new_tag.append(NavigableString(i)) new_tag.append(NavigableString(i))
new_tag.append(BeautifulSoup(features='lxml').new_tag('br')) new_tag.append(BeautifulSoup(features='lxml').new_tag('br'))
else: else:
child.string = _prepare_formatted(child.text)
new_tag.append(child.extract()) new_tag.append(child.extract())
if to_add_br: if to_add_br:
new_tag.append(BeautifulSoup(features='lxml').new_tag('br')) new_tag.append(BeautifulSoup(features='lxml').new_tag('br'))