Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -192,14 +192,14 @@ def gradio_interface1(sitemap_file):
|
|
| 192 |
|
| 193 |
|
| 194 |
with gr.Blocks() as demo:
|
| 195 |
-
gr.Markdown("A website URL is entered into a web crawling tool, which navigates through the site's pages and extracts text content from each page. This process enables users to gather information from multiple web pages quickly and efficiently, facilitating data analysis, research, or content extraction for various purposes.")
|
| 196 |
-
with gr.Tab("Website Crawler"):
|
| 197 |
text_input1 = gr.inputs.Textbox()
|
| 198 |
progress_output = gr.outputs.Textbox(label="Progress")
|
| 199 |
file_output1 = gr.outputs.File(label="Download Text")
|
| 200 |
button1 = gr.Button("Website Crawler")
|
| 201 |
|
| 202 |
-
with gr.Tab("Website Crawler"):
|
| 203 |
text_input2 = gr.inputs.Textbox()
|
| 204 |
file_output2 = gr.outputs.File(label="Download HTML File")
|
| 205 |
button2 = gr.Button("Website Crawler")
|
|
|
|
| 192 |
|
| 193 |
|
| 194 |
with gr.Blocks() as demo:
|
| 195 |
+
gr.Markdown("A website URL is entered into a web crawling tool, which navigates through the site's pages and extracts text content from each page. This process enables users to gather information from multiple web pages quickly and efficiently, facilitating data analysis, research, or content extraction for various purposes.First website crawler generates the Text file and another website crawler is generates a HTML File, Once the server responds, the crawling tool fetches the HTML content of the webpage. The HTML is then parsed to extract the structured information present in the page's elements, such as headings, paragraphs, links, images, etc.Overall, web crawling is a valuable technique for data acquisition, empowering individuals and businesses to harness the vast knowledge available on the internet for their specific needs and objectives. However, it is essential to conduct web crawling responsibly, adhering to ethical practices and respecting the terms of service of the websites being crawled to maintain a harmonious and respectful relationship between web crawlers and website owners.")
|
| 196 |
+
with gr.Tab("Website Crawler(To generate a text file)"):
|
| 197 |
text_input1 = gr.inputs.Textbox()
|
| 198 |
progress_output = gr.outputs.Textbox(label="Progress")
|
| 199 |
file_output1 = gr.outputs.File(label="Download Text")
|
| 200 |
button1 = gr.Button("Website Crawler")
|
| 201 |
|
| 202 |
+
with gr.Tab("Website Crawler(To generate a HTML file)"):
|
| 203 |
text_input2 = gr.inputs.Textbox()
|
| 204 |
file_output2 = gr.outputs.File(label="Download HTML File")
|
| 205 |
button2 = gr.Button("Website Crawler")
|