Update app.py
Browse files
app.py
CHANGED
|
@@ -81,7 +81,7 @@ def format_detailed_output(structured_data):
|
|
| 81 |
|
| 82 |
# --- Web Page Processing Functions ---
|
| 83 |
|
| 84 |
-
def download_and_process_web_page(url
|
| 85 |
"""Downloads a web page from a URL and processes its content."""
|
| 86 |
if not url.startswith("http://") and not url.startswith("https://"):
|
| 87 |
url = "http://" + url # Prepend "http://" if not present
|
|
@@ -89,7 +89,7 @@ def download_and_process_web_page(url, clean=True):
|
|
| 89 |
try:
|
| 90 |
response = get(url)
|
| 91 |
if response.status_code != 200:
|
| 92 |
-
return f"Error: Received status code {response.status_code}"
|
| 93 |
|
| 94 |
soup = response.soup()
|
| 95 |
structured_data = {
|
|
@@ -97,12 +97,12 @@ def download_and_process_web_page(url, clean=True):
|
|
| 97 |
"Links": extract_links(soup, url),
|
| 98 |
"Images": extract_images(soup, url)
|
| 99 |
}
|
| 100 |
-
return format_detailed_output(structured_data)
|
| 101 |
|
| 102 |
except urllib3.exceptions.HTTPError as e:
|
| 103 |
-
return f"Error: {e}"
|
| 104 |
except Exception as e:
|
| 105 |
-
return f"Error processing web page: {e}"
|
| 106 |
|
| 107 |
# --- Gradio Interface ---
|
| 108 |
|
|
@@ -110,11 +110,9 @@ iface = gr.Interface(
|
|
| 110 |
fn=download_and_process_web_page,
|
| 111 |
inputs=[
|
| 112 |
gr.Textbox(lines=1, placeholder="Enter URL of the web page"),
|
| 113 |
-
gr.Checkbox(label="Clean Text", value=True),
|
| 114 |
],
|
| 115 |
outputs=[
|
| 116 |
gr.Markdown(label="Web Page Content"),
|
| 117 |
-
gr.Number(label="Content Length (characters)"),
|
| 118 |
],
|
| 119 |
title="Enhanced Web Page Processor for Hugging Face Chat Tools",
|
| 120 |
description="Enter the URL of a web page. The tool will extract and format its content, including text, links, and images. This tool is designed for use with Hugging Face Chat Tools. \n [https://hf.co/chat/tools/66f1a8159d41ad4398ebb711](https://hf.co/chat/tools/66f1a8159d41ad4398ebb711)",
|
|
|
|
| 81 |
|
| 82 |
# --- Web Page Processing Functions ---
|
| 83 |
|
| 84 |
+
def download_and_process_web_page(url):
|
| 85 |
"""Downloads a web page from a URL and processes its content."""
|
| 86 |
if not url.startswith("http://") and not url.startswith("https://"):
|
| 87 |
url = "http://" + url # Prepend "http://" if not present
|
|
|
|
| 89 |
try:
|
| 90 |
response = get(url)
|
| 91 |
if response.status_code != 200:
|
| 92 |
+
return f"Error: Received status code {response.status_code}"
|
| 93 |
|
| 94 |
soup = response.soup()
|
| 95 |
structured_data = {
|
|
|
|
| 97 |
"Links": extract_links(soup, url),
|
| 98 |
"Images": extract_images(soup, url)
|
| 99 |
}
|
| 100 |
+
return format_detailed_output(structured_data)
|
| 101 |
|
| 102 |
except urllib3.exceptions.HTTPError as e:
|
| 103 |
+
return f"Error: {e}"
|
| 104 |
except Exception as e:
|
| 105 |
+
return f"Error processing web page: {e}"
|
| 106 |
|
| 107 |
# --- Gradio Interface ---
|
| 108 |
|
|
|
|
| 110 |
fn=download_and_process_web_page,
|
| 111 |
inputs=[
|
| 112 |
gr.Textbox(lines=1, placeholder="Enter URL of the web page"),
|
|
|
|
| 113 |
],
|
| 114 |
outputs=[
|
| 115 |
gr.Markdown(label="Web Page Content"),
|
|
|
|
| 116 |
],
|
| 117 |
title="Enhanced Web Page Processor for Hugging Face Chat Tools",
|
| 118 |
description="Enter the URL of a web page. The tool will extract and format its content, including text, links, and images. This tool is designed for use with Hugging Face Chat Tools. \n [https://hf.co/chat/tools/66f1a8159d41ad4398ebb711](https://hf.co/chat/tools/66f1a8159d41ad4398ebb711)",
|