import streamlit as st
import pandas as pd
import json
import time
from datetime import datetime
import requests
from urllib.parse import urlparse
import io
import base64
from scraper import scraper
from youtube_scraper import youtube_scraper
from instagram_scraper import instagram_scraper
from instagram_scraper_v2 import instagram_scraper_v2

# Page configuration
st.set_page_config(
    page_title="Scrape Anythings",
    page_icon="🕷️",
    layout="wide",
    initial_sidebar_state="expanded"
)

# Custom CSS for better styling
st.markdown("""
<style>
    .main-header {
        font-size: 2.5rem;
        font-weight: bold;
        color: #1f77b4;
        text-align: center;
        margin-bottom: 2rem;
    }
    .sub-header {
        font-size: 1.2rem;
        color: #666;
        text-align: center;
        margin-bottom: 2rem;
    }
    .metric-card {
        background-color: #f0f2f6;
        padding: 1rem;
        border-radius: 0.5rem;
        border-left: 4px solid #1f77b4;
    }
    .success-box {
        background-color: #d4edda;
        border: 1px solid #c3e6cb;
        border-radius: 0.5rem;
        padding: 1rem;
        margin: 1rem 0;
    }
    .error-box {
        background-color: #f8d7da;
        border: 1px solid #f5c6cb;
        border-radius: 0.5rem;
        padding: 1rem;
        margin: 1rem 0;
    }
</style>
""", unsafe_allow_html=True)

def validate_url(url):
    """Validate if the URL is properly formatted"""
    try:
        result = urlparse(url)
        return all([result.scheme, result.netloc])
    except:
        return False

def perform_web_scraping(url, data_types, max_pages=1, rate_limit=2):
    """
    Perform actual web scraping using the WebScraper class
    """
    st.info("🔍 Starting web scraping...")
    
    data_types_lower = [dt.lower() for dt in data_types]
    with st.spinner("Crawling website..."):
        scraped_data = scraper.scrape_website(url, data_types_lower, max_pages, rate_limit)
    
    return scraped_data

def display_results(scraped_data, is_youtube=False, is_instagram=False):
    """Display the scraped data in a user-friendly format"""
    
    if is_youtube:
        display_youtube_results(scraped_data)
    elif is_instagram:
        display_instagram_results(scraped_data)
    else:
        display_regular_results(scraped_data)

def display_text_results(text_data):
    st.write(f"**Title:** {text_data.get('title', 'N/A')}")
    with st.expander("Headings"):
        for heading in text_data.get("headings", []):
            st.write(f"- **{heading.get('level', 'h?')}**: {heading.get('text', '')}")
    with st.expander("Paragraphs"):
        for para in text_data.get("paragraphs", []):
            st.write(f"- {para}")

def display_image_results(images):
    cols = st.columns(min(4, len(images)))
    for i, img in enumerate(images):
        with cols[i % 4]:
            st.image(img.get("src", ""), caption=f"{img.get('alt', 'Image')[:50]}...", use_column_width=True)

def display_table_results(tables):
    for i, table in enumerate(tables):
        with st.expander(f"Table {i+1} (Header: {table.get('header', [])})"):
            df = pd.DataFrame(table.get('rows', []))
            st.dataframe(df)

def display_link_results(links):
    for link in links:
        st.write(f"- [{link.get('text', 'N/A')}]({link.get('href', '#')})")

def display_metadata_results(metadata):
    st.json(metadata)

def display_regular_results(scraped_data):
    """Display regular website scraping results in a structured format."""

    st.subheader("📝 Text Content")
    if scraped_data.get("text_content"):
        display_text_results(scraped_data["text_content"])
    else:
        st.info("No text content was extracted.")

    st.subheader("🖼️ Images")
    if scraped_data.get("images"):
        display_image_results(scraped_data["images"])
    else:
        st.info("No images were extracted.")

    st.subheader("🔢 Numbers")
    if scraped_data.get("numbers"):
        with st.expander("Extracted Numbers", expanded=False):
            st.write(scraped_data["numbers"])
    else:
        st.info("No numbers were extracted.")

    st.subheader("📊 Tables")
    if scraped_data.get("tables"):
        display_table_results(scraped_data["tables"])
    else:
        st.info("No tables were extracted.")

    st.subheader("🔗 Links")
    if scraped_data.get("links"):
        display_link_results(scraped_data["links"])
    else:
        st.info("No links were extracted.")

    st.subheader("📄 Metadata")
    if scraped_data.get("metadata"):
        display_metadata_results(scraped_data["metadata"])
    else:
        st.info("No metadata was extracted.")

def to_excel(data):
    """Converts a dictionary of scraped data to an Excel file in memory."""
    output = io.BytesIO()
    with pd.ExcelWriter(output, engine='openpyxl') as writer:
        # Handle simple lists (links, images, numbers)
        for key in ["links", "images", "numbers"]:
            if data.get(key):
                pd.DataFrame({key.capitalize(): data[key]}).to_excel(writer, sheet_name=key.capitalize(), index=False)

        # Handle text content
        if data.get("text_content"):
            pd.DataFrame({'Text': [data["text_content"]]}).to_excel(writer, sheet_name='Text', index=False)

        # Handle dictionaries (metadata, video_info, profile_info)
        for key in ["metadata", "video_info", "profile_info"]:
            if data.get(key):
                pd.DataFrame(data[key].items(), columns=['Property', 'Value']).to_excel(writer, sheet_name=key.replace('_', ' ').capitalize(), index=False)

        # Handle list of dictionaries (comments)
        if data.get("comments"):
            pd.DataFrame(data["comments"]).to_excel(writer, sheet_name='Comments', index=False)

        # Handle list of DataFrames (tables)
        if data.get("tables"):
            for i, table_df in enumerate(data["tables"]):
                table_df.to_excel(writer, sheet_name=f'Table_{i+1}', index=False)

    processed_data = output.getvalue()
    return processed_data

def create_download_links(scraped_data):
    """Create download links for different formats"""
    st.header("Download Data")
    col1, col2, col3, col4 = st.columns(4)

    # JSON download
    with col1:
        json_str = json.dumps(scraped_data or {}, indent=2, default=str)
        st.download_button(
            label="Download JSON",
            data=json_str,
            file_name="scraped_data.json",
            mime="application/json",
            use_container_width=True
        )

    # CSV download
    with col2:
        if scraped_data.get("tables"):
            # For simplicity, we'll offer the first table as a CSV download
            csv = scraped_data["tables"][0].to_csv(index=False)
            st.download_button(
                label="Download CSV",
                data=csv,
                file_name="scraped_table.csv",
                mime="text/csv",
                use_container_width=True
            )
        else:
            st.button("Download CSV", disabled=True, help="No tables found to download.", use_container_width=True)

    # TXT download
    with col3:
        text_content = scraped_data.get("text_content", "")
        st.download_button(
            label="Download TXT",
            data=text_content,
            file_name="scraped_text.txt",
            mime="text/plain",
            use_container_width=True
        )

    # Excel download
    with col4:
        try:
            excel_data = to_excel(scraped_data)
            st.download_button(
                label="Download Excel",
                data=excel_data,
                file_name="scraped_data.xlsx",
                mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
                use_container_width=True
            )
        except Exception as e:
            st.button("Download Excel", disabled=True, help=f"Excel export failed: {e}", use_container_width=True)
            for heading in text_data.get("headings", []):
                txt_content += f"- {heading}\n"
            txt_content += "\nParagraphs:\n"
            for i, para in enumerate(text_data.get("paragraphs", []), 1):
                txt_content += f"{i}. {para}\n"
            
            b64_txt = base64.b64encode(txt_content.encode()).decode()
            href = f'<a href="data:file/txt;base64,{b64_txt}" download="scraped_data.txt">📝 Download TXT</a>'
            st.markdown(href, unsafe_allow_html=True)

    # Excel download
    with col4:
        try:
            excel_data = to_excel(scraped_data)
            st.download_button(
                label="Download data as Excel",
                data=excel_data,
                file_name="scraped_data.xlsx",
                mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
            )
        except Exception as e:
            st.error(f"Failed to generate Excel file: {e}")

def display_youtube_results(scraped_data):
    """Display YouTube scraping results"""
    if not scraped_data.get("video_info"):
        st.error("Could not extract YouTube video information.")
        return

    video_info = scraped_data["video_info"]
    st.subheader(f'{video_info.get("title", "Untitled")}')
    st.write(f'**Channel:** {video_info.get("channel", "N/A")}')
    st.write(f'**Views:** {video_info.get("views", "N/A")}')

    with st.expander("Video Description"):
        st.write(video_info.get("description", "No description."))

    if "comments" in scraped_data and scraped_data["comments"]:
        with st.expander(f'Comments ({len(scraped_data["comments"])})'):
            for comment in scraped_data["comments"]:
                st.markdown(f"**{comment.get('author', 'Unknown')}** - {comment.get('timestamp', 'Unknown')}")
                st.write(comment.get('text', ''))
                if comment.get('likes', '0') != '0':
                    st.caption(f"👍 {comment.get('likes', '0')} likes")
                st.divider()

def display_instagram_results(scraped_data):
    """Display Instagram scraping results"""
    if not scraped_data.get("profile_info"):
        st.error("Could not extract Instagram profile information.")
        return

    profile_info = scraped_data["profile_info"]
    with st.expander("Profile Information", expanded=True):
        st.write(f'**Username:** {profile_info.get("username", "N/A")}')
        st.write(f'**Display Name:** {profile_info.get("display_name", "N/A")}')
        st.write(f'**Bio:** {profile_info.get("bio", "N/A")}')
        st.write(f'**Followers:** {profile_info.get("followers", "N/A")}')

def main():
    # Header
    st.markdown('<h1 class="main-header">✨ Scrape Anythings</h1>', unsafe_allow_html=True)
    st.markdown('<p class="sub-header">Extract data from any website with ease</p>', unsafe_allow_html=True)

    # Sidebar for configuration
    with st.sidebar:
        st.header("Configuration")

        url = st.text_input("Enter Website URL", placeholder="https://example.com")

        is_youtube = "youtube.com" in url.lower() or "youtu.be" in url.lower() if url else False
        is_instagram = "instagram.com" in url.lower() if url else False

        data_types, youtube_data_types, instagram_data_types, max_comments = [], [], [], 50

        if is_youtube:
            st.info("YouTube URL detected!")
            youtube_data_types = st.multiselect("YouTube Data Types", ["video_info", "comments"], default=["video_info", "comments"])
            if "comments" in youtube_data_types:
                max_comments = st.slider("Max Comments", 10, 200, 50)
        elif is_instagram:
            st.info("Instagram URL detected!")
            instagram_data_types = st.multiselect("Instagram Data Types", ["profile_info", "images", "posts"], default=["profile_info", "images"])
        else:
            data_types = st.multiselect("Data Types", ["Text", "Images", "Links", "Tables", "Metadata", "Numbers"], default=["Text", "Links"])

        st.subheader("Advanced Options")
        max_pages = st.slider("Max Pages", 1, 10, 1)
        rate_limit = st.slider("Rate Limit (s)", 1, 10, 2)

        scrape_button = st.button("Start Scraping", type="primary", use_container_width=True)

    # Main content area
    if scrape_button:
        if not url or not validate_url(url):
            st.error("Please enter a valid URL.")
            return

        # Validate that at least one data type is selected for the given URL type
        if is_youtube and not youtube_data_types:
            st.error("Please select at least one YouTube data type to extract.")
            return
        elif is_instagram and not instagram_data_types:
            st.error("Please select at least one Instagram data type to extract.")
            return
        elif not is_youtube and not is_instagram and not data_types:
            st.error("Please select at least one data type to extract.")
            return

        with st.spinner("Scraping in progress... Please wait."):
            try:
                scraped_data = {}
                if is_youtube:
                    scraped_data = youtube_scraper.scrape_youtube_video(url, "comments" in youtube_data_types, max_comments)
                elif is_instagram:
                    try:
                        scraped_data = instagram_scraper_v2.extract_instagram_data(url)
                    except Exception:
                        st.warning("Improved scraper failed, trying fallback...")
                        scraped_data = instagram_scraper.extract_instagram_data(url)
                else:
                    data_types_lower = [dt.lower() for dt in data_types]
                    scraped_data = perform_web_scraping(url, data_types_lower, max_pages, rate_limit)

                if scraped_data.get("errors"):
                    st.error(f'Errors: {scraped_data["errors"]}')

                # Check if any data was actually scraped before showing success
                has_data = any(scraped_data.get(key) for key in ["text_content", "images", "numbers", "tables", "links", "metadata", "video_info", "profile_info"])
                
                if has_data:
                    st.success("Scraping completed successfully!")
                    st.header("Scraping Results")
                    display_results(scraped_data, is_youtube, is_instagram)
                    st.header("Download Data")
                    create_download_links(scraped_data)
                else:
                    st.warning("No data was extracted. The website might be blocking scrapers or the content is not available.")

            except Exception as e:
                st.error(f"An unexpected error occurred: {e}")

    else:
        st.markdown("""
        ### How to Use
        1. **Enter URL** and **select data types** in the sidebar.
        2. Click **Start Scraping** to begin.
        3. View and **download the results** below.
        """)

if __name__ == "__main__":
    main()