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

epub converter: change to html.parser

Browse Source
This commit is contained in:
shirshasa
2021-07-19 13:58:28 +03:00
parent 978b9b0b66
commit eff824f446
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/epub_postprocessor.py
View File

@@ -90,7 +90,8 @@ class EpubPostprocessor:
nodes = dict() nodes = dict()
for item in self.ebooklib_book.get_items_of_type(ebooklib.ITEM_DOCUMENT): for item in self.ebooklib_book.get_items_of_type(ebooklib.ITEM_DOCUMENT):
html_body_text = item.get_body_content() html_body_text = item.get_body_content()
soup = BeautifulSoup(html_body_text, features='lxml') # html.parser closes tags if needed
soup = BeautifulSoup(html_body_text, features='html.parser')
nodes[item.file_name] = soup nodes[item.file_name] = soup
return nodes return nodes