Upload app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
import requests
|
| 3 |
+
import os
|
| 4 |
+
import tempfile
|
| 5 |
+
from dotenv import load_dotenv
|
| 6 |
+
from typing import Tuple
|
| 7 |
+
|
| 8 |
+
# Load environment variables from .env file
|
| 9 |
+
load_dotenv()
|
| 10 |
+
|
| 11 |
+
JINA_API_KEY = os.getenv('JINA_API_KEY')
|
| 12 |
+
|
| 13 |
+
def web_scraper(url: str) -> str:
|
| 14 |
+
"""
|
| 15 |
+
Scrape the content of a given URL using the Jina API.
|
| 16 |
+
|
| 17 |
+
Args:
|
| 18 |
+
url (str): The URL to scrape.
|
| 19 |
+
|
| 20 |
+
Returns:
|
| 21 |
+
str: The scraped content in markdown format.
|
| 22 |
+
"""
|
| 23 |
+
headers = {
|
| 24 |
+
'Authorization': f'Bearer {JINA_API_KEY}',
|
| 25 |
+
'X-Locale': 'en-US',
|
| 26 |
+
'X-Return-Format': 'text',
|
| 27 |
+
'X-With-Generated-Alt': 'true',
|
| 28 |
+
'X-With-Links-Summary': 'true'
|
| 29 |
+
}
|
| 30 |
+
scrape_pattern = f'https://r.jina.ai/{url}'
|
| 31 |
+
|
| 32 |
+
response = requests.get(scrape_pattern, headers=headers)
|
| 33 |
+
return response.text
|
| 34 |
+
|
| 35 |
+
def scrape_and_display(url: str) -> Tuple[str, tempfile._TemporaryFileWrapper]:
|
| 36 |
+
"""
|
| 37 |
+
Scrape the content of a given URL and prepare it for display and download.
|
| 38 |
+
|
| 39 |
+
Args:
|
| 40 |
+
url (str): The URL to scrape.
|
| 41 |
+
|
| 42 |
+
Returns:
|
| 43 |
+
Tuple[str, tempfile._TemporaryFileWrapper]: A tuple containing the scraped content and a temporary file for download.
|
| 44 |
+
"""
|
| 45 |
+
scraped_content = web_scraper(url)
|
| 46 |
+
|
| 47 |
+
# Create a temporary file
|
| 48 |
+
temp_file = tempfile.NamedTemporaryFile(mode="w+", suffix=".md", delete=False)
|
| 49 |
+
temp_file.write(scraped_content)
|
| 50 |
+
temp_file.flush()
|
| 51 |
+
|
| 52 |
+
return scraped_content, temp_file.name
|
| 53 |
+
|
| 54 |
+
def create_gradio_interface() -> gr.Interface:
|
| 55 |
+
"""
|
| 56 |
+
Create and configure the Gradio interface for the web scraper.
|
| 57 |
+
|
| 58 |
+
Returns:
|
| 59 |
+
gr.Interface: The configured Gradio interface.
|
| 60 |
+
"""
|
| 61 |
+
return gr.Interface(
|
| 62 |
+
fn=scrape_and_display,
|
| 63 |
+
inputs=gr.Textbox(label="Enter URL to scrape"),
|
| 64 |
+
outputs=[
|
| 65 |
+
gr.Markdown(label="Scraped Content"),
|
| 66 |
+
gr.File(label="Download Markdown")
|
| 67 |
+
],
|
| 68 |
+
title="Web Scraper",
|
| 69 |
+
description="Enter a URL to scrape and view the content in markdown format. You can also download the markdown file.",
|
| 70 |
+
examples=[["https://www.robots.ox.ac.uk/~vgg/data/flowers/102/categories.html"]],
|
| 71 |
+
allow_flagging="never"
|
| 72 |
+
)
|
| 73 |
+
|
| 74 |
+
if __name__ == "__main__":
|
| 75 |
+
iface = create_gradio_interface()
|
| 76 |
+
iface.launch()
|