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

Small refactoring

Browse Source
This commit is contained in:
Kibzik
2023-03-27 14:25:23 +03:00
parent 440122c477
commit 3252131266
3 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
preset/epub_presets.json
View File

@@ -76,7 +76,7 @@
] ]
}, },
{ {
"preset_name": "attrs_remover", "preset_name": "attr_remover",
"rules": [ "rules": [
{ {
"tags": ["^sup$"], "tags": ["^sup$"],

4
src/docx_converter/html_docx_processor.py
View File

@@ -14,7 +14,7 @@ class HtmlDocxProcessor:
def __init__(self, logger: BookLogger, html_soup: BeautifulSoup, html_preprocessor, style_preprocessor): def __init__(self, logger: BookLogger, html_soup: BeautifulSoup, html_preprocessor, style_preprocessor):
self.logger = logger self.logger = logger
self.body_tag: BeautifulSoup = BeautifulSoup(str(html_soup.body)) self.body_tag: BeautifulSoup = BeautifulSoup(str(html_soup.body))
self.html_preprocessor = html_preprocessor self.html_presets_processor = html_preprocessor
self.style_preprocessor = style_preprocessor self.style_preprocessor = style_preprocessor
self.content: List[Tag] = [] self.content: List[Tag] = []
@@ -252,7 +252,7 @@ class HtmlDocxProcessor:
self._process_headings() self._process_headings()
self.logger.log(f".html using presets processing.") self.logger.log(f".html using presets processing.")
_process_presets(html_preprocessor=self.html_preprocessor, _process_presets(html_presets_processor=self.html_presets_processor,
html_soup=self.body_tag) html_soup=self.body_tag)
self.content = self.body_tag.body.find_all(recursive=False) self.content = self.body_tag.body.find_all(recursive=False)

8
src/epub_converter/html_epub_processor.py
View File

@@ -10,7 +10,7 @@ from src.html_presets_processor import _process_presets
class HtmlEpubProcessor: class HtmlEpubProcessor:
def __init__(self, logger: BookLogger = None, html_preprocessor=None): def __init__(self, logger: BookLogger = None, html_preprocessor=None):
self.logger = logger self.logger = logger
self.html_preprocessor = html_preprocessor self.html_presets_processor = html_preprocessor
@staticmethod @staticmethod
def prepare_title(title_of_chapter: str) -> str: def prepare_title(title_of_chapter: str) -> str:
@@ -109,10 +109,10 @@ class HtmlEpubProcessor:
len(text_preparing(tag)) != 0 and len(text_preparing(tag)) != 0 and
re.findall(r"^h[1-5]$", tag.name or chapter_tag.name)) re.findall(r"^h[1-5]$", tag.name or chapter_tag.name))
if title_in_text: if title_in_text:
self.html_preprocessor.add_span_to_save_ids_for_links(title_in_text[-1], chapter_tag) self.html_presets_processor.add_span_to_save_ids_for_links(title_in_text[-1], chapter_tag)
title_in_text[-1].extract() title_in_text[-1].extract()
elif text_in_title: elif text_in_title:
[self.html_preprocessor.add_span_to_save_ids_for_links(tag, chapter_tag) for tag in 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] [tag.extract() for tag in text_in_title]
@staticmethod @staticmethod
@@ -173,7 +173,7 @@ class HtmlEpubProcessor:
self._remove_headings_content(chapter_tag, title) self._remove_headings_content(chapter_tag, title)
# 4. # 4.
_process_presets( _process_presets(
html_preprocessor=self.html_preprocessor, html_soup=chapter_tag) html_presets_processor=self.html_presets_processor, html_soup=chapter_tag)
# 5. remove classes that weren't created by converter # 5. remove classes that weren't created by converter
self._class_removing(chapter_tag) self._class_removing(chapter_tag)
return chapter_tag return chapter_tag