Create app.py

app.py

@@ -0,0 +1,59 @@
+import streamlit as st
+import scrapy
+from scrapy.crawler import CrawlerProcess
+import pandas as pd
+import io
+
+class MySpider(scrapy.Spider):
+    name = 'myspider'
+
+    def __init__(self, start_url=None, *args, **kwargs):
+        super(MySpider, self).__init__(*args, **kwargs)
+        self.start_urls = [start_url]
+
+    def parse(self, response):
+        # Define your parsing logic here
+        # For example, extracting all text from p tags:
+        for p in response.css('p::text'):
+            yield {'text': p.get()}
+
+def run_spider(url):
+    process = CrawlerProcess(settings={
+        'FEED_FORMAT': 'csv',
+        'FEED_URI': 'output.csv'
+    })
+    process.crawl(MySpider, start_url=url)
+    process.start()
+
+def main():
+    st.title('Web Scraper and CSV Generator')
+
+    # URL input
+    url = st.text_input('Enter the URL to scrape:', 'https://example.com')
+
+    if st.button('Start Scraping'):
+        if url:
+            with st.spinner('Scraping in progress...'):
+                run_spider(url)
+            st.success('Scraping completed!')
+
+            # Read the CSV file
+            df = pd.read_csv('output.csv')
+            
+            # Display the data
+            st.write(df)
+
+            # Provide download link
+            csv = df.to_csv(index=False)
+            b = io.BytesIO(csv.encode())
+            st.download_button(
+                label="Download CSV",
+                data=b,
+                file_name="scraped_data.csv",
+                mime="text/csv"
+            )
+        else:
+            st.error('Please enter a valid URL')
+
+if __name__ == '__main__':
+    main()