discours.io/core
5
0
Fork 0
Code Pull Requests Actions Projects Activity

html wrap fix
All checks were successful
Deploy on push / deploy (push) Successful in 48s
Details

Browse Source
This commit is contained in:
Untone 2025-04-27 12:53:49 +03:00
parent b735bf8cab
commit bcbfdd76e9
4 changed files with 53 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
resolvers/draft.py
View File

@ -21,6 +21,7 @@ from services.db import local_session
from services.notify import notify_shout from services.notify import notify_shout
from services.schema import mutation, query from services.schema import mutation, query
from services.search import search_service from services.search import search_service
from utils.html_wrapper import wrap_html_fragment
from utils.logger import root_logger as logger from utils.logger import root_logger as logger
def create_shout_from_draft(session, draft, author_id): def create_shout_from_draft(session, draft, author_id):
@ -183,7 +184,8 @@ async def create_draft(_, info, draft_input):
return {"error": f"Failed to create draft: {str(e)}"} return {"error": f"Failed to create draft: {str(e)}"}
def generate_teaser(body, limit=300): def generate_teaser(body, limit=300):
body_text = trafilatura.extract(body, include_comments=False, include_tables=False) body_html = wrap_html_fragment(body)
body_text = trafilatura.extract(body_html, include_comments=False, include_tables=False)
body_teaser = ". ".join(body_text[:limit].split(". ")[:-1]) body_teaser = ". ".join(body_text[:limit].split(". ")[:-1])
return body_teaser return body_teaser
@ -270,10 +272,12 @@ async def update_draft(_, info, draft_id: int, draft_input):
if "seo" not in filtered_input and not draft.seo: if "seo" not in filtered_input and not draft.seo:
body_src = filtered_input.get("body", draft.body) body_src = filtered_input.get("body", draft.body)
lead_src = filtered_input.get("lead", draft.lead) lead_src = filtered_input.get("lead", draft.lead)
body_html = wrap_html_fragment(body_src)
lead_html = wrap_html_fragment(lead_src)
try: try:
body_text = trafilatura.extract(body_src, include_comments=False, include_tables=False) if body_src else None body_text = trafilatura.extract(body_html, include_comments=False, include_tables=False) if body_src else None
lead_text = trafilatura.extract(lead_src, include_comments=False, include_tables=False) if lead_src else None lead_text = trafilatura.extract(lead_html, include_comments=False, include_tables=False) if lead_src else None
body_teaser = generate_teaser(body_text, 300) if body_text else "" body_teaser = generate_teaser(body_text, 300) if body_text else ""
filtered_input["seo"] = lead_text if lead_text else body_teaser filtered_input["seo"] = lead_text if lead_text else body_teaser
@ -347,6 +351,7 @@ def validate_html_content(html_content: str) -> tuple[bool, str]:
return False, "Content is empty" return False, "Content is empty"
try: try:
html_content = wrap_html_fragment(html_content)
extracted = trafilatura.extract(html_content) extracted = trafilatura.extract(html_content)
if not extracted: if not extracted:
return False, "Invalid HTML structure or empty content" return False, "Invalid HTML structure or empty content"

9
resolvers/editor.py
View File

@ -23,6 +23,7 @@ from services.db import local_session
from services.notify import notify_shout from services.notify import notify_shout
from services.schema import mutation, query from services.schema import mutation, query
from services.search import search_service from services.search import search_service
from utils.html_wrapper import wrap_html_fragment
from utils.logger import root_logger as logger from utils.logger import root_logger as logger
@ -180,9 +181,11 @@ async def create_shout(_, info, inp):
# Создаем публикацию без topics # Создаем публикацию без topics
body = inp.get("body", "") body = inp.get("body", "")
lead = inp.get("lead", "") lead = inp.get("lead", "")
body_text = trafilatura.extract(body) body_html = wrap_html_fragment(body)
lead_text = trafilatura.extract(lead) lead_html = wrap_html_fragment(lead)
seo = inp.get("seo", lead_text or body_text[:300].split(". ")[:-1].join(". ")) body_text = trafilatura.extract(body_html)
lead_text = trafilatura.extract(lead_html)
seo = inp.get("seo", lead_text.strip() or body_text.strip()[:300].split(". ")[:-1].join(". "))
new_shout = Shout( new_shout = Shout(
slug=slug, slug=slug,
body=body, body=body,

1
utils/__init__.py Normal file
View File

@ -0,0 +1 @@

38
utils/html_wrapper.py Normal file
View File

@ -0,0 +1,38 @@
"""
Модуль для обработки HTML-фрагментов
"""
def wrap_html_fragment(fragment: str) -> str:
"""
Оборачивает HTML-фрагмент в полную HTML-структуру для корректной обработки.
Args:
fragment: HTML-фрагмент для обработки
Returns:
str: Полный HTML-документ
Example:
>>> wrap_html_fragment("<p>Текст параграфа</p>")
'<!DOCTYPE html><html><head><meta charset="utf-8"></head><body><p>Текст параграфа</p></body></html>'
"""
if not fragment or not fragment.strip():
return fragment
# Проверяем, является ли контент полным HTML-документом
is_full_html = fragment.strip().startswith('<!DOCTYPE') or fragment.strip().startswith('<html')
# Если это фрагмент, оборачиваем его в полный HTML-документ
if not is_full_html:
return f"""<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title></title>
</head>
<body>
{fragment}
</body>
</html>"""
return fragment