# Moz Bulk Site Metrics Checker
#
# This script fetches site metrics for a list of domains or URLs using the Moz API.
# You can customize the following parameters:
#
# 1. **Scope**: Defines the scope of the query for each domain or URL. Acceptable values are:
#    - 'domain': Analyzes the entire domain.
#    - 'subdomain': Analyzes a specific subdomain.
#    - 'subfolder': Analyzes a specific subfolder.
#    - 'url': Analyzes a specific URL.
#    Update the 'scope' parameter for each query when prompted.
#
# 2. **Headers**: Ensure you replace the 'x-moz-token' with your actual Moz API token.
#
# The script generates a CSV file with the following columns:
# - Query (Domain or URL)
# - Page
# - Title
# - Last Crawled
# - HTTP Code
# - Spam Score
# - Domain Authority
# - Page Authority
# - External Pages to Page
# - External Pages to Root Domain
# - Root Domains to Page
# - Root Domains to Root Domain

# Import necessary libraries
import json
import requests
import pandas as pd
from google.colab import files

# Define headers with your Moz token
headers = {
    "x-moz-token": "bW96c2NhcGUtemNZeVRuSTVwSDpBTnI0ejRpaTZPNzJTOVpXblRveHhUWGg4QTVWUlo0bQ==",  # Replace with your actual token
    "Content-Type": "application/json",
}

# Function to fetch metrics for a single site
def fetch_site_metrics(query, scope="domain"):
    data = {
        "jsonrpc": "2.0",
        "id": "c4357611-b3bb-4913-b4a7-0ca0eec842fb",
        "method": "data.site.metrics.fetch",
        "params": {
            "data": {
                "site_query": {
                    "query": query,
                    "scope": scope
                }
            }
        }
    }

    # Make the API request
    response = requests.post("https://api.moz.com/jsonrpc", headers=headers, data=json.dumps(data))

    if response.status_code == 200:
        response_data = response.json()
        site_metrics = response_data.get("result", {}).get("site_metrics", {})
        site_query = response_data.get("result", {}).get("site_query", {})

        # Combine all relevant metrics into a single dictionary
        return {
            "Query": site_query.get("query"),
            "Page": site_metrics.get("page"),
            "Title": site_metrics.get("title"),
            "Last Crawled": site_metrics.get("last_crawled"),
            "HTTP Code": site_metrics.get("http_code"),
            "Spam Score": site_metrics.get("spam_score"),
            "Domain Authority": site_metrics.get("domain_authority"),
            "Page Authority": site_metrics.get("page_authority"),
            "External Pages to Page": site_metrics.get("external_pages_to_page"),
            "External Pages to Root Domain": site_metrics.get("external_pages_to_root_domain"),
            "Root Domains to Page": site_metrics.get("root_domains_to_page"),
            "Root Domains to Root Domain": site_metrics.get("root_domains_to_root_domain"),
        }
    else:
        print(f"Failed to fetch data for {query}. HTTP Status Code: {response.status_code}")
        print(f"Response: {response.text}")
        return None

# User inputs bulk queries
print("Enter domains or URLs (comma-separated):")
input_queries = input().strip()
queries = [query.strip() for query in input_queries.split(",")]

# Fetch metrics for the queries
site_metrics_list = []
for query in queries:
    print(f"Fetching metrics for: {query}")
    metrics = fetch_site_metrics(query)
    if metrics:
        site_metrics_list.append(metrics)

if site_metrics_list:
    # Convert the list to a DataFrame
    df = pd.DataFrame(site_metrics_list)

    # Save the DataFrame to a CSV file
    output_file = "bulk_site_metrics.csv"
    df.to_csv(output_file, index=False)

    print(f"Metrics successfully saved to {output_file}")

    # Download the file in Google Colab
    files.download(output_file)
else:
    print("No metrics data fetched.")