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

Heading removal fix

Browse Source
This commit is contained in:
Kiryl
2022-07-20 15:44:28 +03:00
parent 20fa1bfa86
commit 4f7aa69ab3
1 changed files with 12 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/epub_converter/html_epub_processor.py
View File

@@ -276,20 +276,25 @@ class HtmlEpubPreprocessor:
""" """
title_of_chapter = title_of_chapter.lower() title_of_chapter = title_of_chapter.lower()
if title_of_chapter == "chapter 1":
pass
for tag in chapter_tag.contents: for tag in chapter_tag.contents:
text = tag if isinstance(tag, NavigableString) else tag.text text = tag if isinstance(tag, NavigableString) else tag.text
if re.sub(r"[\s\xa0]", "", text): if re.sub(r"[\s\xa0]", "", text):
text = re.sub(r"[\s\xa0]", " ", text).lower() text = re.sub(r"[\s\xa0]", " ", text).lower()
text = text.strip() # delete extra spaces text = text.strip() # delete extra spaces
if not isinstance(tag, NavigableString):
if title_of_chapter == text or \ if title_of_chapter == text or \
(title_of_chapter in text and (title_of_chapter in text and
re.findall(r"^h[1-3]$", tag.name or chapter_tag.name)): re.findall(r"^h[1-3]$", tag.name or chapter_tag.name)):
self._add_span_to_save_ids_for_links(tag, chapter_tag) self._add_span_to_save_ids_for_links(tag, chapter_tag)
tag.extract() tag.extract()
return return
elif not isinstance(tag, NavigableString): elif not self._remove_headings_content(tag, title_of_chapter):
if not self._remove_headings_content(tag, title_of_chapter):
break break
else:
tag.extract()
return
@staticmethod @staticmethod
def _process_tables(chapter_tag: BeautifulSoup): def _process_tables(chapter_tag: BeautifulSoup):