Add Flask SEO Meter app

Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+COPY requirements.txt requirements.txt
+RUN pip install --upgrade pip && pip install -r requirements.txt
+
+COPY . .
+
+ENV FLASK_APP=app.py
+
+CMD ["flask", "run", "--host=0.0.0.0", "--port=7860"]

app.py

@@ -0,0 +1,347 @@
+from flask import Flask, request, jsonify
+import re
+import json
+from typing import Dict, Union
+
+app = Flask(__name__)
+
+# ====================== COMMON UTILITY FUNCTIONS ======================
+def check_keyword_exist(text: str, keyword: str) -> bool:
+    """Cek apakah keyword ada dalam teks"""
+    if not text or not keyword:
+        return False
+    keywords = [kw.strip().lower() for kw in keyword.split(',') if kw.strip()]
+    text_lower = text.lower()
+    return any(kw in text_lower for kw in keywords)
+
+def format_score(score: Union[int, float]) -> Union[int, float]:
+    """Format skor untuk output"""
+    if isinstance(score, float):
+        return int(score) if score.is_integer() else round(score, 2)
+    return score
+
+def calculate_keyword_density(text: str, keyword: str) -> float:
+    """Menghitung kepadatan keyword dalam teks"""
+    if not text or not keyword:
+        return 0.0
+    total_words = len(text.split())
+    keyword_count = sum(text.lower().count(kw.lower()) for kw in keyword.split(','))
+    return (keyword_count / max(1, total_words)) * 100
+
+# ====================== TITLE ANALYSIS ======================
+def calculate_title_score(article_data: Dict[str, Union[str, Dict]]) -> Dict[str, float]:
+    """Menghitung skor SEO untuk bagian Title Page"""
+    title = article_data.get('title', '')
+    target_keyword = article_data.get('target-keyword', '')
+    
+    title_scores = {
+        'keyword_exist_score': 0,
+        'keyword_position_score': 0.0,
+        'title_length_score': 0.0,
+        'title_total_score': 0.0,
+        'statuses': {
+            'keyword_exist': '',
+            'keyword_position': '',
+            'title_length': '',
+            'overall': ''
+        }
+    }
+    
+    # 1. Target Keyword Exist (Bobot: 6%)
+    keyword_exist = check_keyword_exist(title, target_keyword)
+    title_scores['keyword_exist_score'] = 6 if keyword_exist else 0
+    title_scores['statuses']['keyword_exist'] = 'Good' if keyword_exist else 'Bad'
+    
+    # 2. Target Keyword Position (Bobot: 3%)
+    if keyword_exist:
+        position_score = check_keyword_position(title, target_keyword)
+        title_scores['keyword_position_score'] = position_score * 3
+        if position_score == 1.0:
+            title_scores['statuses']['keyword_position'] = 'Good'
+        elif position_score == 0.5:
+            title_scores['statuses']['keyword_position'] = 'Needs Improvement'
+        else:
+            title_scores['statuses']['keyword_position'] = 'Bad'
+    
+    # 3. Title Length (Bobot: 1%)
+    length_score = check_title_length(title)
+    title_scores['title_length_score'] = length_score * 1
+    if length_score == 1.0:
+        title_scores['statuses']['title_length'] = 'Good'
+    elif length_score == 0.5:
+        title_scores['statuses']['title_length'] = 'Needs Improvement'
+    else:
+        title_scores['statuses']['title_length'] = 'Bad'
+    
+    # Hitung total skor title
+    title_scores['title_total_score'] = (
+        float(title_scores['keyword_exist_score']) +
+        title_scores['keyword_position_score'] +
+        title_scores['title_length_score']
+    )
+    
+    # Determine overall status
+    total_percentage = (title_scores['title_total_score'] / 10) * 100
+    if total_percentage >= 80:
+        title_scores['statuses']['overall'] = 'Good'
+    elif total_percentage >= 50:
+        title_scores['statuses']['overall'] = 'Needs Improvement'
+    else:
+        title_scores['statuses']['overall'] = 'Bad'
+    
+    return title_scores
+
+def check_keyword_position(title: str, keyword: str) -> float:
+    """Cek posisi keyword dalam title"""
+    if not title or not keyword:
+        return 0.0
+    first_keyword = keyword.split(',')[0].strip().lower()
+    title_words = title.lower().split()
+    try:
+        keyword_index = title_words.index(first_keyword)
+    except ValueError:
+        return 0.0
+    words_before = keyword_index
+    if words_before <= 2: return 1.0
+    if words_before <= 4: return 0.5
+    return 0.0
+
+def check_title_length(title: str) -> float:
+    """Cek panjang title"""
+    length = len(title)
+    if 75 <= length <= 95: return 1.0
+    if (40 <= length <= 74) or (95 < length <= 120): return 0.5
+    return 0.0
+
+# ====================== META DESCRIPTION ANALYSIS ======================
+def calculate_meta_desc_score(article_data: Dict[str, Union[str, Dict]]) -> Dict[str, float]:
+    """Menghitung skor SEO untuk bagian Meta Description"""
+    meta_desc = article_data.get('meta_desc', '')
+    target_keyword = article_data.get('target-keyword', '')
+    related_keyword = article_data.get('related-keyword', '')
+    
+    meta_scores = {
+        'keyword_exist_score': 0.0,
+        'related_keyword_score': 0.0,
+        'length_score': 0.0,
+        'meta_total_score': 0.0,
+        'statuses': {
+            'keyword_exist': '',
+            'related_keyword': '',
+            'length': '',
+            'overall': ''
+        }
+    }
+    
+    # 1. Target Keyword Exist (Bobot: 1%)
+    keyword_exist = check_keyword_exist(meta_desc, target_keyword)
+    meta_scores['keyword_exist_score'] = 1.0 if keyword_exist else 0.0
+    meta_scores['statuses']['keyword_exist'] = 'Good' if keyword_exist else 'Bad'
+    
+    # 2. Related Keyword Exist (Bobot: 3.5%)
+    related_exist = check_keyword_exist(meta_desc, related_keyword) if related_keyword else False
+    meta_scores['related_keyword_score'] = 3.5 if related_exist else 0.0
+    meta_scores['statuses']['related_keyword'] = 'Good' if related_exist else 'Bad'
+    
+    # 3. Meta Description Length (Bobot: 0.5%)
+    length_status = check_meta_desc_length(meta_desc)
+    if length_status == 1.0:
+        meta_scores['length_score'] = 0.5
+        meta_scores['statuses']['length'] = 'Good'
+    elif length_status == 0.5:
+        meta_scores['length_score'] = 0.25
+        meta_scores['statuses']['length'] = 'Needs Improvement'
+    else:
+        meta_scores['length_score'] = 0.0
+        meta_scores['statuses']['length'] = 'Bad'
+    
+    # Hitung total skor meta description
+    meta_scores['meta_total_score'] = (
+        meta_scores['keyword_exist_score'] +
+        meta_scores['related_keyword_score'] +
+        meta_scores['length_score']
+    )
+    
+    # Determine overall status
+    total_percentage = (meta_scores['meta_total_score'] / 5) * 100
+    if total_percentage >= 80:
+        meta_scores['statuses']['overall'] = 'Good'
+    elif total_percentage >= 50:
+        meta_scores['statuses']['overall'] = 'Needs Improvement'
+    else:
+        meta_scores['statuses']['overall'] = 'Bad'
+    
+    return meta_scores
+
+def check_meta_desc_length(meta_desc: str) -> float:
+    """Cek panjang meta description"""
+    length = len(meta_desc)
+    if 126 <= length <= 146: return 1.0
+    if (100 <= length <= 125) or (146 < length <= 160): return 0.5
+    return 0.0
+
+# ====================== CONTENT ANALYSIS ======================
+def calculate_content_score(article_data: Dict[str, Union[str, Dict]]) -> Dict[str, float]:
+    """Menghitung skor SEO untuk bagian Konten"""
+    content = article_data.get('content', '')
+    target_keyword = article_data.get('target-keyword', '')
+    related_keyword = article_data.get('related-keyword', '')
+    
+    content_scores = {
+        'word_count_score': 0.0,
+        'first_para_score': 0.0,
+        'last_para_score': 0.0,
+        'alt_image_score': 0.0,
+        'keyword_density_score': 0.0,
+        'related_keyword_density_score': 0.0,
+        'keyword_frequency_score': 0.0,
+        'content_total_score': 0.0,
+        'statuses': {
+            'word_count': '',
+            'first_paragraph': '',
+            'last_paragraph': '',
+            'alt_image': '',
+            'keyword_density': '',
+            'related_keyword_density': '',
+            'keyword_frequency': '',
+            'overall': ''
+        }
+    }
+    
+    # Clean HTML content
+    text_content = re.sub(r'<a href="#"[^>]*>.*?</a>', '', content)
+    text_content = re.sub('<[^<]+?>', '', text_content)
+    paragraphs = [p.strip() for p in text_content.split('\n') if p.strip()]
+    
+    # 1. Word Count (14.5%)
+    word_count = len(text_content.split())
+    if word_count > 400:
+        content_scores['word_count_score'] = 14.5
+        content_scores['statuses']['word_count'] = 'Good'
+    elif word_count > 200:
+        content_scores['word_count_score'] = 7.25
+        content_scores['statuses']['word_count'] = 'Needs Improvement'
+    else:
+        content_scores['statuses']['word_count'] = 'Bad'
+    
+    # 2. Target Keyword in First Paragraph (1.7%)
+    if paragraphs and check_keyword_exist(paragraphs[0], target_keyword):
+        content_scores['first_para_score'] = 1.7
+        content_scores['statuses']['first_paragraph'] = 'Good'
+    
+    # 3. Target Keyword in Last Paragraph (1.7%)
+    if paragraphs and check_keyword_exist(paragraphs[-1], target_keyword):
+        content_scores['last_para_score'] = 1.7
+        content_scores['statuses']['last_paragraph'] = 'Good'
+    
+    # 4. Target Keyword in Alt Image (0.9%)
+    alt_images = re.findall(r'alt=["\'](.*?)["\']', content)
+    if any(check_keyword_exist(alt, target_keyword) for alt in alt_images):
+        content_scores['alt_image_score'] = 0.9
+        content_scores['statuses']['alt_image'] = 'Good'
+    
+    # 5. Keyword Density (14.9%)
+    keyword_density = calculate_keyword_density(text_content, target_keyword)
+    if 2.5 <= keyword_density <= 5:
+        content_scores['keyword_density_score'] = 14.9
+        content_scores['statuses']['keyword_density'] = 'Good'
+    elif keyword_density > 5:
+        content_scores['keyword_density_score'] = 7.45
+        content_scores['statuses']['keyword_density'] = 'Needs Improvement'
+    
+    # 6. Related Keyword Density (14.9%)
+    if related_keyword:
+        related_density = calculate_keyword_density(text_content, related_keyword)
+        if 1 <= related_density <= 2:
+            content_scores['related_keyword_density_score'] = 14.9
+            content_scores['statuses']['related_keyword_density'] = 'Good'
+        elif related_density < 1 or (2 < related_density < 5):
+            content_scores['related_keyword_density_score'] = 7.45
+            content_scores['statuses']['related_keyword_density'] = 'Needs Improvement'
+    
+    # 7. Keyword Frequency (25.5%)
+    keyword_count = sum(text_content.lower().count(kw.lower()) for kw in target_keyword.split(','))
+    if 3 <= keyword_count <= 6:
+        content_scores['keyword_frequency_score'] = 25.5
+        content_scores['statuses']['keyword_frequency'] = 'Good'
+    elif 1 <= keyword_count <= 2:
+        content_scores['keyword_frequency_score'] = 12.75
+        content_scores['statuses']['keyword_frequency'] = 'Needs Improvement'
+    
+    # Calculate total score (85% maksimal tanpa internal link)
+    content_scores['content_total_score'] = sum([
+        content_scores['word_count_score'],
+        content_scores['first_para_score'],
+        content_scores['last_para_score'],
+        content_scores['alt_image_score'],
+        content_scores['keyword_density_score'],
+        content_scores['related_keyword_density_score'],
+        content_scores['keyword_frequency_score']
+    ])
+    
+    # Determine overall status
+    total_percentage = (content_scores['content_total_score'] / 85) * 100
+    if total_percentage >= 80:
+        content_scores['statuses']['overall'] = 'Good'
+    elif total_percentage >= 50:
+        content_scores['statuses']['overall'] = 'Needs Improvement'
+    else:
+        content_scores['statuses']['overall'] = 'Bad'
+    
+    return content_scores
+
+# ====================== FLASK API ENDPOINTS ======================
+@app.route('/analyze', methods=['POST'])
+def analyze():
+    """Endpoint utama untuk analisis SEO"""
+    try:
+        article_data = request.get_json()
+        
+        if not article_data:
+            return jsonify({"error": "No JSON data provided"}), 400
+        
+        # Lakukan semua analisis
+        title_scores = calculate_title_score(article_data)
+        meta_scores = calculate_meta_desc_score(article_data)
+        content_scores = calculate_content_score(article_data)
+        
+        # Hitung skor total
+        overall_score = (
+            title_scores['title_total_score'] +
+            meta_scores['meta_total_score'] +
+            content_scores['content_total_score']
+        )
+        max_score = 10 + 5 + 85  # Total maksimal semua komponen
+        
+        # Siapkan response
+        response = {
+            "title_analysis": {
+                "scores": {k: format_score(v) for k, v in title_scores.items() if k.endswith('_score')},
+                "statuses": title_scores['statuses']
+            },
+            "meta_analysis": {
+                "scores": {k: format_score(v) for k, v in meta_scores.items() if k.endswith('_score')},
+                "statuses": meta_scores['statuses']
+            },
+            "content_analysis": {
+                "scores": {k: format_score(v) for k, v in content_scores.items() if k.endswith('_score')},
+                "statuses": content_scores['statuses']
+            },
+            "overall_score": {
+                "score": format_score(overall_score),
+                "max_score": max_score,
+                "percentage": round((overall_score / max_score) * 100, 2)
+            }
+        }
+        
+        return jsonify(response)
+    
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
+
+@app.route('/')
+def home():
+    return "SEO Analysis API - Send POST request to /analyze with article data"
+
+if __name__ == '__main__':
+    app.run(debug=True)

requirements.txt

@@ -0,0 +1,6 @@
+flask==2.3.2
+beautifulsoup4==4.12.2
+lxml==4.9.3
+requests==2.31.0
+python-dotenv==1.0.0
+gunicorn==20.1.0