Spaces:
Sleeping
Sleeping
Update src/streamlit_app.py
Browse files- src/streamlit_app.py +37 -39
src/streamlit_app.py
CHANGED
|
@@ -1,40 +1,38 @@
|
|
| 1 |
-
|
| 2 |
-
import numpy as np
|
| 3 |
-
import pandas as pd
|
| 4 |
import streamlit as st
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
#
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
"
|
| 28 |
-
|
| 29 |
-
"
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
|
|
|
| 1 |
+
# Import the required libraries
|
|
|
|
|
|
|
| 2 |
import streamlit as st
|
| 3 |
+
from scrapegraphai.graphs import SmartScraperGraph
|
| 4 |
+
|
| 5 |
+
# Set up the Streamlit app
|
| 6 |
+
st.title("Web Scrapping AI Agent 🕵️♂️")
|
| 7 |
+
st.caption("This app allows you to scrape a website using OpenAI API")
|
| 8 |
+
|
| 9 |
+
# Get OpenAI API key from user
|
| 10 |
+
openai_access_token = st.text_input("OpenAI API Key", type="password")
|
| 11 |
+
|
| 12 |
+
if openai_access_token:
|
| 13 |
+
model = st.radio(
|
| 14 |
+
"Select the model",
|
| 15 |
+
["gpt-3.5-turbo", "gpt-4"],
|
| 16 |
+
index=0,
|
| 17 |
+
)
|
| 18 |
+
graph_config = {
|
| 19 |
+
"llm": {
|
| 20 |
+
"api_key": openai_access_token,
|
| 21 |
+
"model": model,
|
| 22 |
+
},
|
| 23 |
+
}
|
| 24 |
+
# Get the URL of the website to scrape
|
| 25 |
+
url = st.text_input("Enter the URL of the website you want to scrape")
|
| 26 |
+
# Get the user prompt
|
| 27 |
+
user_prompt = st.text_input("What you want the AI agent to scrae from the website?")
|
| 28 |
+
|
| 29 |
+
# Create a SmartScraperGraph object
|
| 30 |
+
smart_scraper_graph = SmartScraperGraph(
|
| 31 |
+
prompt=user_prompt,
|
| 32 |
+
source=url,
|
| 33 |
+
config=graph_config
|
| 34 |
+
)
|
| 35 |
+
# Scrape the website
|
| 36 |
+
if st.button("Scrape"):
|
| 37 |
+
result = smart_scraper_graph.run()
|
| 38 |
+
st.write(result)
|