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

LAW-6695|Change process of removing heading content

Browse Source
This commit is contained in:
Kibzik
2023-05-13 16:23:44 +03:00
parent 1b96b52e4c
commit d81fc18403
3 changed files with 13 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/epub_converter/html_epub_processor.py
View File

@@ -100,6 +100,11 @@ class HtmlEpubProcessor:
text = text.strip() # delete extra spaces
return text
def remove_text(found_tag: Tag):
for text_node in found_tag.find_all(text=True):
if text_node.strip():
text_node.extract()
title_of_chapter: str = title_of_chapter.lower()
title_in_text: List[Tag] = chapter_tag.find_all(lambda tag: (title_of_chapter in text_preparing(tag) and
len(text_preparing(tag)) != 0 and
@@ -110,10 +115,10 @@ class HtmlEpubProcessor:
re.findall(r"^h[1-5]$", tag.name or chapter_tag.name))
if title_in_text:
self.html_presets_processor.add_span_to_save_ids_for_links(title_in_text[-1], chapter_tag)
title_in_text[-1].extract()
remove_text(title_in_text[-1])
elif text_in_title:
[self.html_presets_processor.add_span_to_save_ids_for_links(tag, chapter_tag) for tag in text_in_title]
[tag.extract() for tag in text_in_title]
[remove_text(tag) for tag in text_in_title]
@staticmethod
def _class_removing(chapter_tag: BeautifulSoup):