Update app.py

app.py

@@ -1,144 +1,180 @@
-import gradio as gr
-import requests
-import pandas as pd
 import time
 import os
+import requests
+import pandas as pd
+import gradio as gr
 from urllib.parse import urlparse
 
-# ---------------- CONFIG ----------------
-API_KEY = os.getenv("HASDATA_API_KEY")
-BASE_URL = "https://api.hasdata.com/scrape/google/serp"
+# =====================================================
+# CONFIGURATION
+# =====================================================
 
-TARGET_DOMAIN = "rishabhsoft.com"
-MAX_PAGES = 10  # Top 10 pages (Top 100 results)
+# 🔐 Hugging Face Secret
+HASDATA_API_KEY = os.getenv("HASDATA_API_KEY")
 
-if not API_KEY:
-    raise ValueError("HASDATA_API_KEY is not set in Hugging Face Secrets")
+HASDATA_ENDPOINT = "https://api.hasdata.com/scrape/google/serp"
 
-# ---------------- CORE LOGIC ----------------
-def check_domain_rank(keyword):
-    """
-    Checks ranking of TARGET_DOMAIN for a keyword
-    Uses HasData SERP API
-    USA Google results only
-    Stops once domain is found
-    """
+TARGET_DOMAIN = "rishabhsoft.com"
+COUNTRY = "us"          # change to "in" for India
+LANGUAGE = "en"
+LOCATION = "United States" if COUNTRY == "us" else "India"
+
+MAX_PAGES = 10          # Top 100
+RESULTS_PER_PAGE = 10
+SLEEP_TIME = 1
+
+if not HASDATA_API_KEY:
+    raise RuntimeError("HASDATA_API_KEY not found. Add it in Hugging Face Secrets.")
+
+# =====================================================
+# HELPERS
+# =====================================================
+def normalize_domain(url: str) -> str:
+    try:
+        return urlparse(url).netloc.replace("www.", "").lower()
+    except Exception:
+        return ""
+
+# =====================================================
+# CORE RANK CHECK
+# =====================================================
+def check_domain_rank(keyword: str) -> pd.DataFrame:
+    keyword = keyword.strip()
+    results = []
 
     headers = {
-        "Accept": "application/json",
-        "X-API-KEY": API_KEY
+        "x-api-key": HASDATA_API_KEY
     }
 
     for page in range(MAX_PAGES):
+        start = page * RESULTS_PER_PAGE
+
         params = {
-            "engine": "google",
             "q": keyword,
-            "start": page * 10,
-            "num": 10,
-
-            # Force USA Google
-            "gl": "us",
-            "hl": "en",
-            "location": "United States",
-            "google_domain": "google.com"
+            "gl": COUNTRY,
+            "hl": LANGUAGE,
+            "domain": "google.com",
+            "location": LOCATION,
+            "start": start,
+            "num": RESULTS_PER_PAGE,
+            "deviceType": "desktop"
         }
 
         response = requests.get(
-            BASE_URL,
+            HASDATA_ENDPOINT,
             headers=headers,
             params=params,
             timeout=30
         )
 
         if response.status_code != 200:
-            return {
-                "Keyword": keyword,
-                "Domain": TARGET_DOMAIN,
-                "Page": "Error",
-                "Position on Page": "Error",
-                "Absolute Rank": "Error",
-                "URL": None,
-                "Title": f"API Error {response.status_code}: {response.text}"
-            }
+            print(f"API Error [{response.status_code}]: {response.text}")
+            break
 
         data = response.json()
-        organic_results = data.get("organic_results", [])
 
-        if not organic_results:
-            break
+        organic_results = (
+            data.get("organic_results")
+            or data.get("organicResults")
+            or []
+        )
 
-        for idx, result in enumerate(organic_results, start=1):
-            url = result.get("link", "")
-            domain = urlparse(url).netloc.replace("www.", "")
+        for idx, item in enumerate(organic_results, start=1):
+            url = item.get("link") or item.get("url") or ""
+            if not url:
+                continue
 
-            if TARGET_DOMAIN in domain:
-                return {
+            domain = normalize_domain(url)
+
+            if domain.endswith(TARGET_DOMAIN):
+                results.append({
                     "Keyword": keyword,
-                    "Domain": TARGET_DOMAIN,
+                    "Domain": f"https://www.{TARGET_DOMAIN}/",
                     "Page": page + 1,
                     "Position on Page": idx,
-                    "Absolute Rank": page * 10 + idx,
+                    "Absolute Rank": start + idx,
                     "URL": url,
-                    "Title": result.get("title")
-                }
+                    "Title": item.get("title")
+                })
+
+        if results:
+            break
 
-        time.sleep(1)  # rate-limit safety
+        time.sleep(SLEEP_TIME)
 
-    return {
+    if results:
+        return pd.DataFrame(results)
+
+    return pd.DataFrame([{
         "Keyword": keyword,
-        "Domain": TARGET_DOMAIN,
+        "Domain": f"https://www.{TARGET_DOMAIN}/",
         "Page": "Not Found",
         "Position on Page": "Not Found",
         "Absolute Rank": "Not Found",
         "URL": None,
-        "Title": "Not ranking in Top 100"
-    }
-
-# ---------------- BULK HANDLER ----------------
-def run_bulk_keywords(text):
-    if not text.strip():
+        "Title": "Not ranking in top 100"
+    }])
+
+# =====================================================
+# BULK EXCEL HANDLER
+# =====================================================
+def run_bulk_excel(file):
+    if file is None:
         return None, None
 
-    keywords = [k.strip() for k in text.splitlines() if k.strip()]
-    results = []
+    df = pd.read_excel(file)
 
-    for keyword in keywords:
-        results.append(check_domain_rank(keyword))
+    if "keyword" not in df.columns:
+        raise ValueError("Excel must contain a 'keyword' column")
 
-    df = pd.DataFrame(results)
+    all_results = []
 
-    output_file = "rishabhsoft_us_keyword_rankings.xlsx"
-    df.to_excel(output_file, index=False)
+    for kw in df["keyword"].dropna().unique():
+        all_results.append(check_domain_rank(str(kw)))
 
-    return df, output_file
+    final_df = pd.concat(all_results, ignore_index=True)
 
-# ---------------- UI ----------------
-with gr.Blocks(title="Domain Rank Checker — USA Google Results") as demo:
-    gr.Markdown("## 🔍 Domain Rank Checker — USA Google Results")
-    gr.Markdown(
-        "**Tracked domain:** https://www.rishabhsoft.com/\n\n"
-        "- 🇺🇸 USA Google results only\n"
-        "- 🔎 Checks Top 10 pages (Top 100)\n"
-        "- ⚡ Stops when domain is found (credit-optimized)\n"
-        "- 📋 One keyword per line\n"
-        "- 📥 Excel export supported"
-    )
+    output_file = "hasdata_keyword_ranking.xlsx"
+    final_df.to_excel(output_file, index=False)
+
+    return final_df, output_file
 
-    keyword_box = gr.Textbox(
-        label="Keywords (one per line)",
-        lines=10,
-        placeholder=".NET MAUI app development services\nenterprise software development"
+# =====================================================
+# GRADIO UI
+# =====================================================
+with gr.Blocks(title="Hasdata Google Rank Checker") as demo:
+    gr.Markdown("## 🔍 Google Keyword Rank Checker (Hasdata)")
+    gr.Markdown(f"**Target Domain:** https://www.{TARGET_DOMAIN}/")
+    gr.Markdown(f"**Country:** {COUNTRY.upper()} | **Device:** Desktop")
+
+    excel_input = gr.File(
+        label="Upload Excel (.xlsx) with 'keyword' column",
+        file_types=[".xlsx"]
     )
 
     run_btn = gr.Button("Check Rankings")
 
-    output_table = gr.Dataframe(wrap=True)
-    download_file = gr.File(label="Download Excel Report")
+    output_table = gr.Dataframe(
+        headers=[
+            "Keyword",
+            "Domain",
+            "Page",
+            "Position on Page",
+            "Absolute Rank",
+            "URL",
+            "Title"
+        ],
+        wrap=True
+    )
+
+    download_file = gr.File(label="Download Result Excel")
 
     run_btn.click(
-        fn=run_bulk_keywords,
-        inputs=keyword_box,
+        fn=run_bulk_excel,
+        inputs=excel_input,
         outputs=[output_table, download_file]
     )
 
+# 🔒 REQUIRED for Hugging Face + Python 3.12
+demo.queue()
 demo.launch()