Spaces:
Sleeping
Sleeping
Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
import pandas as pd
|
| 3 |
+
import base64
|
| 4 |
+
import json
|
| 5 |
+
from scrapegraphai.graphs import SmartScraperGraph
|
| 6 |
+
import google.generativeai as genai
|
| 7 |
+
# Used to securely store your API key
|
| 8 |
+
from google.colab import userdata
|
| 9 |
+
import nest_asyncio
|
| 10 |
+
import os
|
| 11 |
+
|
| 12 |
+
nest_asyncio.apply()
|
| 13 |
+
|
| 14 |
+
GOOGLE_API_KEY = os.environ['Gemini']
|
| 15 |
+
|
| 16 |
+
graph_config = {
|
| 17 |
+
"llm": {
|
| 18 |
+
"api_key": GOOGLE_API_KEY,
|
| 19 |
+
"model": "google_genai/gemini-pro",
|
| 20 |
+
},
|
| 21 |
+
}
|
| 22 |
+
|
| 23 |
+
def get_data(url):
|
| 24 |
+
"""
|
| 25 |
+
Fetches data from the given URL using scrapegraphai.
|
| 26 |
+
|
| 27 |
+
Args:
|
| 28 |
+
url: The URL to scrape.
|
| 29 |
+
|
| 30 |
+
Returns:
|
| 31 |
+
A dictionary containing the extracted data in the following format:
|
| 32 |
+
{'grants': [{'grant_name': ..., 'funding_organisation': ...,
|
| 33 |
+
'due_date': ..., 'eligible_countries': ...,
|
| 34 |
+
'eligibility_conditions': ...}, ...]}
|
| 35 |
+
"""
|
| 36 |
+
|
| 37 |
+
smart_scraper_graph = SmartScraperGraph(
|
| 38 |
+
prompt="List me all grants or funds, the organisations funding them, the due date, eligible countries and eligibility conditions for applicants.",
|
| 39 |
+
source=url,
|
| 40 |
+
config=graph_config
|
| 41 |
+
)
|
| 42 |
+
|
| 43 |
+
result = smart_scraper_graph.run()
|
| 44 |
+
return result
|
| 45 |
+
|
| 46 |
+
def convert_to_csv(data):
|
| 47 |
+
df = pd.DataFrame(data['grants'])
|
| 48 |
+
return df.to_csv(index=False).encode('utf-8')
|
| 49 |
+
|
| 50 |
+
def convert_to_excel(data):
|
| 51 |
+
df = pd.DataFrame(data['grants'])
|
| 52 |
+
buffer = io.BytesIO()
|
| 53 |
+
with pd.ExcelWriter(buffer, engine='xlsxwriter') as writer:
|
| 54 |
+
df.to_excel(writer, sheet_name='Grants', index=False)
|
| 55 |
+
return buffer.getvalue()
|
| 56 |
+
|
| 57 |
+
st.title("Quantilytix Grant Scraper")
|
| 58 |
+
|
| 59 |
+
url = st.text_input("Enter URL")
|
| 60 |
+
|
| 61 |
+
if st.button("Get grants"):
|
| 62 |
+
if url:
|
| 63 |
+
try:
|
| 64 |
+
result = get_data(url)
|
| 65 |
+
st.success("Data scraped successfully!")
|
| 66 |
+
|
| 67 |
+
selected_format = st.selectbox("Select Download Format", ("CSV", "Excel"))
|
| 68 |
+
|
| 69 |
+
if selected_format == "CSV":
|
| 70 |
+
csv_data = convert_to_csv(result)
|
| 71 |
+
b64 = base64.b64encode(csv_data).decode()
|
| 72 |
+
download_link = f"<a href='data:application/vnd.ms-excel;base64,{b64}' download='grants.csv'>Download CSV</a>"
|
| 73 |
+
st.markdown(download_link, unsafe_allow_html=True)
|
| 74 |
+
elif selected_format == "Excel":
|
| 75 |
+
excel_data = convert_to_excel(result)
|
| 76 |
+
b64 = base64.b64encode(excel_data).decode()
|
| 77 |
+
download_link = f"<a href='data:application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;base64,{b64}' download='grants.xlsx'>Download Excel</a>"
|
| 78 |
+
st.markdown(download_link, unsafe_allow_html=True)
|
| 79 |
+
|
| 80 |
+
st.dataframe(result['grants'])
|
| 81 |
+
except Exception as e:
|
| 82 |
+
st.error(f"Error scraping data: {e}")
|
| 83 |
+
else:
|
| 84 |
+
st.warning("Please enter a URL.")
|