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

Add htm support in processing anchors

Browse Source
This commit is contained in:
Kiryl
2021-10-26 14:35:40 +03:00
parent a55eefc7ed
commit 24210c9999
3 changed files with 31 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
src/epub_converter/html_epub_preprocessor.py
View File

@@ -468,10 +468,11 @@ def wrap_block_tag_with_table(main_tag, old_tag, width='95', border='1px', bg_co
return table
def _clean_wiley_block(block):
def clean_wiley_block(block):
hrs = block.find_all("p", attrs={"class": re.compile(".+ hr")})
for hr in hrs:
hr.extract()
print(hr)
h = block.find(re.compile("h[1-9]"))
if h:
h.name = "p"
@@ -481,7 +482,7 @@ def _clean_wiley_block(block):
def preprocess_block_tags(chapter_tag):
for block in chapter_tag.find_all("blockquote"):
if block.attrs.get('class') in ['feature1', 'feature2', 'feature3', 'feature4']:
_clean_wiley_block(block)
clean_wiley_block(block)
color = '#DDDDDD' if block.attrs.get('class') == 'feature1' else None
color = '#EEEEEE' if block.attrs.get('class') == 'feature2' else color
@@ -490,13 +491,13 @@ def preprocess_block_tags(chapter_tag):
block.unwrap()
for future_block in chapter_tag.find_all("p", attrs={"class": re.compile("feature[1234]")}):
_clean_wiley_block(future_block)
clean_wiley_block(future_block)
color = '#DDDDDD' if future_block.attrs.get('class') == 'feature1' else None
color = '#EEEEEE' if future_block.attrs.get('class') == 'feature2' else color
wrap_block_tag_with_table(chapter_tag, future_block, bg_color=color)
def _prepare_formatted(text):
def prepare_formatted(text):
# replace <,> to save them as is in html code
text = text.replace("<", "\x3C")
text = text.replace(">", "\x3E")
@@ -515,7 +516,7 @@ def preprocess_pre_tags(chapter_tag):
for child in pre.children:
if isinstance(child, NavigableString):
cleaned_text = _prepare_formatted(str(child))
cleaned_text = prepare_formatted(str(child))
sub_strings = re.split('\r\n|\n|\r', cleaned_text)
for string in sub_strings:
new_tag.append(NavigableString(string))
@@ -523,10 +524,10 @@ def preprocess_pre_tags(chapter_tag):
else:
for sub_child in child.children:
if isinstance(sub_child, NavigableString):
cleaned_text2 = _prepare_formatted(str(sub_child))
cleaned_text2 = prepare_formatted(str(sub_child))
sub_child.replace_with(NavigableString(cleaned_text2))
else:
sub_child.string = _prepare_formatted(sub_child.text)
sub_child.string = prepare_formatted(sub_child.text)
cleaned_tag = child.extract()
new_tag.append(cleaned_tag)
if to_add_br: