Spaces:
Sleeping
Sleeping
Delete app (7).py
Browse files- app (7).py +0 -65
app (7).py
DELETED
@@ -1,65 +0,0 @@
|
|
1 |
-
|
2 |
-
import streamlit as st
|
3 |
-
import os
|
4 |
-
from scraper import fetch_html_selenium, format_data, save_raw_data, save_formatted_data
|
5 |
-
from pagination_detector import detect_pagination_elements
|
6 |
-
from assets import PRICING
|
7 |
-
import google.generativeai as genai
|
8 |
-
|
9 |
-
# Access API keys from Hugging Face Secrets
|
10 |
-
openai_api_key = os.getenv('OPENAI_API_KEY')
|
11 |
-
google_api_key = os.getenv('GOOGLE_API_KEY')
|
12 |
-
groq_api_key = os.getenv('GROQ_API_KEY')
|
13 |
-
|
14 |
-
# Check if the keys are available
|
15 |
-
if not openai_api_key or not google_api_key or not groq_api_key:
|
16 |
-
st.error("API keys are missing! Please add them as secrets in Hugging Face.")
|
17 |
-
|
18 |
-
# Initialize Streamlit app
|
19 |
-
st.set_page_config(page_title="Universal Web Scraper", page_icon="🦑")
|
20 |
-
st.title("Universal Web Scraper 🦑")
|
21 |
-
|
22 |
-
# Initialize session state variables if they don't exist
|
23 |
-
if 'results' not in st.session_state:
|
24 |
-
st.session_state['results'] = None
|
25 |
-
if 'perform_scrape' not in st.session_state:
|
26 |
-
st.session_state['perform_scrape'] = False
|
27 |
-
|
28 |
-
# Sidebar components
|
29 |
-
st.sidebar.title("Web Scraper Settings")
|
30 |
-
model_selection = st.sidebar.selectbox("Select Model", options=list(PRICING.keys()), index=0)
|
31 |
-
url_input = st.sidebar.text_input("Enter URL(s) separated by whitespace")
|
32 |
-
|
33 |
-
# Add toggle to show/hide tags field
|
34 |
-
show_tags = st.sidebar.checkbox("Enable Scraping", value=False)
|
35 |
-
|
36 |
-
# Conditionally show tags input based on the toggle
|
37 |
-
tags = []
|
38 |
-
if show_tags:
|
39 |
-
tags = st.sidebar.text_input("Enter Fields to Extract (comma-separated)").split(",")
|
40 |
-
|
41 |
-
st.sidebar.markdown("---")
|
42 |
-
# Add pagination toggle and input
|
43 |
-
use_pagination = st.sidebar.checkbox("Enable Pagination", value=False)
|
44 |
-
pagination_details = None
|
45 |
-
if use_pagination:
|
46 |
-
pagination_details = st.sidebar.text_input("Enter Pagination Details (optional)", help="Describe how to navigate through pages")
|
47 |
-
|
48 |
-
st.sidebar.markdown("---")
|
49 |
-
|
50 |
-
# Define the scraping function
|
51 |
-
def perform_scrape():
|
52 |
-
raw_html = fetch_html_selenium(url_input)
|
53 |
-
markdown = format_data(raw_html)
|
54 |
-
save_raw_data(markdown, "scraped_data")
|
55 |
-
|
56 |
-
if use_pagination:
|
57 |
-
pagination_data, _, _ = detect_pagination_elements(url_input, pagination_details, model_selection, markdown)
|
58 |
-
return pagination_data
|
59 |
-
|
60 |
-
return markdown
|
61 |
-
|
62 |
-
if st.sidebar.button("Scrape"):
|
63 |
-
with st.spinner("Scraping data..."):
|
64 |
-
result = perform_scrape()
|
65 |
-
st.write(result)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|