SiskelDev/WattpadDownloader
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(api): Stopped extra newlines from appearing with bold/italics (#40)

Browse Source
This commit is contained in:
AaronBenDaniel
2025-04-03 22:16:05 -04:00
committed by GitHub
parent e79453ab5f
commit 52faaf54c2
1 changed files with 15 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/api/src/create_book.py
+15 -29
View File
@@ -151,6 +151,7 @@ def generate_clean_part_html(part: Part, content: str) -> bs4.Tag:
raise Exception() raise Exception()
for child in html.find_all("p"): for child in html.find_all("p"):
current_paragraph = clean.new_tag("p")
for p_child in list(child.children): for p_child in list(child.children):
if not p_child: if not p_child:
continue continue
@@ -161,37 +162,22 @@ def generate_clean_part_html(part: Part, content: str) -> bs4.Tag:
src = p_child["src"] src = p_child["src"]
img_tag = clean.new_tag("img") img_tag = clean.new_tag("img")
img_tag["src"] = src img_tag["src"] = src
break_tag = clean.new_tag("br")
section.append(img_tag) section.append(img_tag)
section.append(break_tag) section.append(clean.new_tag("br"))
elif p_child.name == "b": elif p_child.name in ["b", "i"]:
content = p_child.text styled_tag = clean.new_tag(p_child.name)
p_tag = clean.new_tag("p") styled_content = clean.new_string(p_child.text)
bold_tag = clean.new_tag("b") styled_tag.append(styled_content)
bold_content = clean.new_string(content) current_paragraph.append(styled_tag)
else:
bold_tag.append(bold_content) # Append any other tags as-is
p_tag.append(bold_tag) current_paragraph.append(p_child)
section.append(p_tag)
elif p_child.name == "i":
content = p_child.text
p_tag = clean.new_tag("p")
italic_tag = clean.new_tag("i")
italic_content = clean.new_string(content)
italic_tag.append(italic_content)
p_tag.append(italic_tag)
section.append(p_tag)
elif isinstance(p_child, bs4.element.NavigableString): elif isinstance(p_child, bs4.element.NavigableString):
content = p_child.text content = clean.new_string(p_child)
p_tag = clean.new_tag("p") current_paragraph.append(content)
p_content = clean.new_string(content)
p_tag.append(p_content) if current_paragraph.contents:
section.append(p_tag) section.append(current_paragraph)
if not list(child.children): if not list(child.children):
# Some p tags only contain brs, once brs are removed, they are empty and can be removed as well. # Some p tags only contain brs, once brs are removed, they are empty and can be removed as well.