advanced-keyword-scraper 0.1.0__tar.gz

advanced_keyword_scraper-0.1.0/PKG-INFO

@@ -0,0 +1,22 @@
+Metadata-Version: 2.4
+Name: advanced-keyword-scraper
+Version: 0.1.0
+Summary: A multithreaded Google autocomplete keyword scraper with intent classification and Excel export.
+Author-email: Your Name <your.email@example.com>
+License: MIT
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: requests>=2.28.0
+Requires-Dist: pandas>=2.0.0
+Requires-Dist: openpyxl>=3.1.0
+
+# Advanced Keyword Scraper
+
+A multithreaded Google autocomplete keyword scraper with intent classification and Excel export.
+
+## Installation
+```bash
+pip install advanced-keyword-scraper
+
+## Author
+Developed with 🔥 by **LORD SRIJWN**

advanced_keyword_scraper-0.1.0/README.md

@@ -0,0 +1,10 @@
+# Advanced Keyword Scraper
+
+A multithreaded Google autocomplete keyword scraper with intent classification and Excel export.
+
+## Installation
+```bash
+pip install advanced-keyword-scraper
+
+## Author
+Developed with 🔥 by **LORD SRIJWN**

advanced_keyword_scraper-0.1.0/pyproject.toml

@@ -0,0 +1,22 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "advanced-keyword-scraper"
+version = "0.1.0"
+description = "A multithreaded Google autocomplete keyword scraper with intent classification and Excel export."
+readme = "README.md"
+requires-python = ">=3.8"
+license = {text = "MIT"}
+authors = [
+    { name = "Your Name", email = "your.email@example.com" }
+]
+dependencies = [
+    "requests>=2.28.0",
+    "pandas>=2.0.0",
+    "openpyxl>=3.1.0"
+]
+
+[project.scripts]
+keyword-scraper = "keyword_scraper.cli:main"

advanced_keyword_scraper-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

advanced_keyword_scraper-0.1.0/src/advanced_keyword_scraper.egg-info/PKG-INFO

@@ -0,0 +1,22 @@
+Metadata-Version: 2.4
+Name: advanced-keyword-scraper
+Version: 0.1.0
+Summary: A multithreaded Google autocomplete keyword scraper with intent classification and Excel export.
+Author-email: Your Name <your.email@example.com>
+License: MIT
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: requests>=2.28.0
+Requires-Dist: pandas>=2.0.0
+Requires-Dist: openpyxl>=3.1.0
+
+# Advanced Keyword Scraper
+
+A multithreaded Google autocomplete keyword scraper with intent classification and Excel export.
+
+## Installation
+```bash
+pip install advanced-keyword-scraper
+
+## Author
+Developed with 🔥 by **LORD SRIJWN**

advanced_keyword_scraper-0.1.0/src/advanced_keyword_scraper.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+README.md
+pyproject.toml
+src/advanced_keyword_scraper.egg-info/PKG-INFO
+src/advanced_keyword_scraper.egg-info/SOURCES.txt
+src/advanced_keyword_scraper.egg-info/dependency_links.txt
+src/advanced_keyword_scraper.egg-info/entry_points.txt
+src/advanced_keyword_scraper.egg-info/requires.txt
+src/advanced_keyword_scraper.egg-info/top_level.txt
+src/keyword_scraper/cli.py
+src/keyword_scraper/init.py

advanced_keyword_scraper-0.1.0/src/advanced_keyword_scraper.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

advanced_keyword_scraper-0.1.0/src/advanced_keyword_scraper.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+keyword-scraper = keyword_scraper.cli:main

advanced_keyword_scraper-0.1.0/src/advanced_keyword_scraper.egg-info/requires.txt

@@ -0,0 +1,3 @@
+requests>=2.28.0
+pandas>=2.0.0
+openpyxl>=3.1.0

advanced_keyword_scraper-0.1.0/src/advanced_keyword_scraper.egg-info/top_level.txt

@@ -0,0 +1 @@
+keyword_scraper

advanced_keyword_scraper-0.1.0/src/keyword_scraper/cli.py

@@ -0,0 +1,126 @@
+import argparse
+import concurrent.futures
+from datetime import datetime
+import json
+import os
+import random
+import string
+import time
+import pandas as pd
+import requests
+
+USER_AGENTS = [
+    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36",
+    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36",
+    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36",
+]
+
+def get_suggestions(keyword, country, lang):
+    url = f"http://suggestqueries.google.com/complete/search?client=chrome&gl={country}&hl={lang}&q={keyword}"
+    headers = {"User-Agent": random.choice(USER_AGENTS)}
+    try:
+        response = requests.get(url, headers=headers, timeout=5)
+        if response.status_code == 200:
+            data = json.loads(response.text)
+            return data[1] if len(data) > 1 else []
+    except Exception:
+        pass
+    return []
+
+def process_task(task, country, lang):
+    base_kw, pattern, query = task
+    suggestions = get_suggestions(query, country, lang)
+    time.sleep(random.uniform(0.05, 0.15))
+    return base_kw, pattern, suggestions
+
+def classify_intent(keyword):
+    kw = keyword.lower()
+    transactional = ["buy", "price", "cheap", "cost", "under", "online", "shop", "order", "deal", "discount", "store", "sale", "rate"]
+    commercial = ["best", "top", "review", "vs", "compare", "difference", "brand", "latest", "new"]
+    informational = ["how", "what", "where", "why", "which", "can", "guide", "tips", "ideas", "tutorial", "design", "style", "pattern"]
+
+    if any(w in kw for w in transactional):
+        return "Transactional (Buying)"
+    elif any(w in kw for w in commercial):
+        return "Commercial (Research)"
+    elif any(w in kw for w in informational):
+        return "Informational"
+    else:
+        return "General / Long-Tail"
+
+def run_scraper(keywords, country, lang, max_threads, output_folder):
+    if not os.path.exists(output_folder):
+        os.makedirs(output_folder)
+
+    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+    filename = os.path.join(output_folder, f"keyword_analysis_{timestamp}.xlsx")
+
+    questions = ["how", "what", "where", "why", "which", "can"]
+    prepositions = ["for", "with", "under", "near", "vs", "without"]
+    buying_intent = ["best", "buy", "price", "online", "top", "cheap", "shop"]
+
+    tasks = []
+    for base in keywords:
+        tasks.append((base, "Normal Search", base))
+        for letter in string.ascii_lowercase:
+            tasks.append((base, f"Alpha ({letter})", f"{base} {letter}"))
+        for num in string.digits:
+            tasks.append((base, f"Number ({num})", f"{base} {num}"))
+        for q in questions:
+            tasks.append((base, f"Question ({q})", f"{q} {base}"))
+            tasks.append((base, f"Question ({q})", f"{base} {q}"))
+        for prep in prepositions:
+            tasks.append((base, f"Preposition ({prep})", f"{base} {prep}"))
+        for intent in buying_intent:
+            tasks.append((base, f"Intent ({intent})", f"{intent} {base}"))
+
+    print(f"Total Queries Generated: {len(tasks)}")
+    print(f"Scraping started (Country: {country}, Threads: {max_threads})...\n")
+
+    all_keywords = set()
+    results = []
+    completed = 0
+
+    with concurrent.futures.ThreadPoolExecutor(max_workers=max_threads) as executor:
+        futures = [executor.submit(process_task, task, country, lang) for task in tasks]
+        for future in concurrent.futures.as_completed(futures):
+            base_kw, pattern, suggestions = future.result()
+            completed += 1
+
+            for s in suggestions:
+                if s not in all_keywords:
+                    all_keywords.add(s)
+                    intent = classify_intent(s)
+                    results.append([base_kw, pattern, s, intent])
+
+            if completed % 100 == 0 or completed == len(tasks):
+                print(f"Progress: {completed}/{len(tasks)} queries completed...")
+
+    df = pd.DataFrame(results, columns=["Base Keyword", "Search Pattern", "Long-Tail Keyword", "Search Intent"])
+
+    print("\nGenerating Excel report...")
+    with pd.ExcelWriter(filename, engine="openpyxl") as writer:
+        df.to_excel(writer, sheet_name="All Keywords", index=False)
+        for intent_name, group_df in df.groupby("Search Intent"):
+            sheet_title = intent_name.split()[0]
+            group_df.to_excel(writer, sheet_name=sheet_title, index=False)
+
+        summary_df = df.groupby(["Base Keyword", "Search Intent"]).size().unstack(fill_value=0)
+        summary_df.to_excel(writer, sheet_name="Intent Summary")
+
+    print(f"\nCompleted! Total {len(df)} unique keywords fetched.")
+    print(f"Saved File: {os.path.abspath(filename)}")
+
+def main():
+    parser = argparse.ArgumentParser(description="Advanced Google Autocomplete Keyword Scraper CLI Tool")
+    parser.add_argument("keywords", nargs="+", help="Base keywords to scrape (e.g. 'cotton kurti' 'western gown')")
+    parser.add_argument("--country", default="in", help="Target country code (e.g. 'in' for India, 'bd' for Bangladesh)")
+    parser.add_argument("--lang", default="en", help="Language code (e.g. 'en', 'bn')")
+    parser.add_argument("--threads", type=int, default=12, help="Number of concurrent threads")
+    parser.add_argument("--output", default="SEO_Keywords", help="Folder name to save results")
+
+    args = parser.parse_args()
+    run_scraper(args.keywords, args.country, args.lang, args.threads, args.output)
+
+if __name__ == "__main__":
+    main()

advanced_keyword_scraper-0.1.0/src/keyword_scraper/init.py

@@ -0,0 +1,2 @@
+__version__ = "0.1.0"
+__author__ = "LORD SRIJWN"