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

Change workong process of docx body

Browse Source
This commit is contained in:
Kiryl
2022-09-19 19:25:17 +03:00
parent e0e3e3199d
commit d7a9c52acd
1 changed files with 7 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
src/docx_converter/html_docx_processor.py
View File

@@ -13,16 +13,15 @@ from src.inline_style_processor import modify_html_soup_with_css_styles
class HtmlDocxProcessor: 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.html_soup = html_soup self.body_tag: BeautifulSoup = BeautifulSoup(str(html_soup.body))
self.html_preprocessor = html_preprocessor self.html_preprocessor = html_preprocessor
self.style_preprocessor = style_preprocessor self.style_preprocessor = style_preprocessor
self.content: List[Tag] = [] self.content: List[Tag] = []
def _font_to_span(self): def _font_to_span(self):
for font in self.html_soup.find_all("font"): for font in self.body_tag.find_all("font"):
font.name = "span" font.name = "span"
def _process_hrefs(self): def _process_hrefs(self):
a_tags_with_href = self.body_tag.find_all( a_tags_with_href = self.body_tag.find_all(
"a", {"href": re.compile("^.*http.+")}) "a", {"href": re.compile("^.*http.+")})
@@ -205,10 +204,9 @@ class HtmlDocxProcessor:
else: else:
h_tag.unwrap() h_tag.unwrap()
def delete_content_before_toc(self): def delete_content_before_toc(self):
# remove all tag upper the <TOC> only in content !!! body tag is not updated # remove all tag upper the <TOC> only in content !!! body tag is not updated
toc_tag = self.html_soup.new_tag("TOC") toc_tag = self.body_tag.new_tag("TOC")
if toc_tag in self.content: if toc_tag in self.content:
ind = self.content.index(toc_tag) + 1 ind = self.content.index(toc_tag) + 1
self.content = self.content[ind:] self.content = self.content[ind:]
@@ -225,12 +223,10 @@ class HtmlDocxProcessor:
self.logger.log("Inline style reading.") self.logger.log("Inline style reading.")
self.style_preprocessor.process_inline_styles_in_html_soup( self.style_preprocessor.process_inline_styles_in_html_soup(
self.html_soup) self.body_tag)
self.logger.log("Inline style processing.") self.logger.log("Inline style processing.")
self.html_soup = modify_html_soup_with_css_styles(self.html_soup) self.body_tag = modify_html_soup_with_css_styles(self.body_tag)
self.body_tag = self.html_soup.body
self.logger.log("Image processing.") self.logger.log("Image processing.")
images = process_images(access, path_to_html=html_path, images = process_images(access, path_to_html=html_path,
@@ -257,9 +253,9 @@ class HtmlDocxProcessor:
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_preprocessor=self.html_preprocessor,
html_soup=self.html_soup) html_soup=self.body_tag)
self.content = self.body_tag.find_all(recursive=False) self.content = self.body_tag.body.find_all(recursive=False)
# delete text before table of content if exists # delete text before table of content if exists
self.delete_content_before_toc() self.delete_content_before_toc()