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

epub converter: fix

Browse Source
This commit is contained in:
shirshasa
2021-09-03 14:02:45 +03:00
parent 60b83ce650
commit e6f8416516
1 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
src/html_epub_preprocessor.py
View File

@@ -302,6 +302,11 @@ def unwrap_structural_tags(body_tag):
'figure', 'footer', 'iframe', 'span', 'p' 'figure', 'footer', 'iframe', 'span', 'p'
] ]
# comments removal
for tag in body_tag.find_all():
for element in tag(text=lambda text: isinstance(text, Comment)):
element.extract()
for div in body_tag.find_all("div"): for div in body_tag.find_all("div"):
if div.attrs.get('class'): if div.attrs.get('class'):
div_class = div.attrs['class'] if not isinstance(div.attrs['class'], list) else div.attrs['class'][0] div_class = div.attrs['class'] if not isinstance(div.attrs['class'], list) else div.attrs['class'][0]
@@ -500,7 +505,7 @@ def preprocess_pre_tags(chapter_tag):
for child in pre.children: for child in pre.children:
if isinstance(child, NavigableString): if isinstance(child, NavigableString):
cleaned_text = _prepare_formatted(pre.text) cleaned_text = _prepare_formatted(str(child))
sub_strings = re.split('\r\n|\n|\r', cleaned_text) sub_strings = re.split('\r\n|\n|\r', cleaned_text)
for string in sub_strings: for string in sub_strings:
new_tag.append(NavigableString(string)) new_tag.append(NavigableString(string))
@@ -519,8 +524,7 @@ def preprocess_pre_tags(chapter_tag):
new_tag.attrs['style'] = "font-family: courier new,courier,monospace; " \ new_tag.attrs['style'] = "font-family: courier new,courier,monospace; " \
"font-size: 14px; white-space: nowrap;" "font-size: 14px; white-space: nowrap;"
pre.insert_before(new_tag) pre.replace_with(new_tag)
pre.extract()
table = wrap_preformatted_span_with_table(chapter_tag, new_tag) table = wrap_preformatted_span_with_table(chapter_tag, new_tag)
p_for_br = chapter_tag.new_tag("p") p_for_br = chapter_tag.new_tag("p")
p_for_br.string = "\xa0" p_for_br.string = "\xa0"
@@ -570,10 +574,6 @@ def prepare_title_and_content(title, chapter_tag: BeautifulSoup, remove_title_fr
if hasattr(tag, 'attrs') and tag.attrs.get('class') and (tag.attrs.get('class') not in ['link-anchor', if hasattr(tag, 'attrs') and tag.attrs.get('class') and (tag.attrs.get('class') not in ['link-anchor',
'footnote-element']): 'footnote-element']):
del tag.attrs['class'] del tag.attrs['class']
# 3. comments removal
for tag in chapter_tag.find_all():
for element in tag(text=lambda text: isinstance(text, Comment)):
element.extract()
# content_str = re.sub(r'([\n\t\xa0])', ' ', str(content_tag)) # content_str = re.sub(r'([\n\t\xa0])', ' ', str(content_tag))
title_str = clean_title_from_numbering(title_str) title_str = clean_title_from_numbering(title_str)
return title_str, str(chapter_tag) return title_str, str(chapter_tag)