Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
|
@@ -15,16 +15,16 @@ def main_fn(html: str, check: list[int]):
|
|
| 15 |
for t in soup.find_all(tag):
|
| 16 |
t.decompose()
|
| 17 |
|
|
|
|
| 18 |
body = soup.find("body")
|
| 19 |
main = soup.find("main")
|
|
|
|
| 20 |
|
| 21 |
-
strip_tags = [] #
|
| 22 |
|
| 23 |
-
|
| 24 |
-
markdown = md(main, strip=strip_tags)
|
| 25 |
-
else:
|
| 26 |
-
markdown = md(body, strip=strip_tags)
|
| 27 |
|
|
|
|
| 28 |
title_tag = soup.find("title")
|
| 29 |
title = title_tag.get_text(strip=True) if title_tag else "Sem t铆tulo"
|
| 30 |
|
|
@@ -49,7 +49,7 @@ demo = gr.Interface(
|
|
| 49 |
outputs=[
|
| 50 |
gr.TextArea(label="Markdown gerado", show_copy_button=True)
|
| 51 |
],
|
| 52 |
-
|
| 53 |
)
|
| 54 |
|
| 55 |
demo.launch(server_name="0.0.0.0")
|
|
|
|
| 15 |
for t in soup.find_all(tag):
|
| 16 |
t.decompose()
|
| 17 |
|
| 18 |
+
# Tenta usar <main>, depois <body>, ou como fallback o pr贸prio soup
|
| 19 |
body = soup.find("body")
|
| 20 |
main = soup.find("main")
|
| 21 |
+
target = main or body or soup
|
| 22 |
|
| 23 |
+
strip_tags = [] # Pode usar `check` no futuro se quiser ignorar certas tags
|
| 24 |
|
| 25 |
+
markdown = md(target, strip=strip_tags)
|
|
|
|
|
|
|
|
|
|
| 26 |
|
| 27 |
+
# Tenta extrair o t铆tulo da p谩gina
|
| 28 |
title_tag = soup.find("title")
|
| 29 |
title = title_tag.get_text(strip=True) if title_tag else "Sem t铆tulo"
|
| 30 |
|
|
|
|
| 49 |
outputs=[
|
| 50 |
gr.TextArea(label="Markdown gerado", show_copy_button=True)
|
| 51 |
],
|
| 52 |
+
flagging_mode="never",
|
| 53 |
)
|
| 54 |
|
| 55 |
demo.launch(server_name="0.0.0.0")
|