Update app.py

app.py

@@ -2,12 +2,9 @@ import requests
 from bs4 import BeautifulSoup
 from urllib.parse import urlparse, urljoin
 import gradio as gr
+import plotly.graph_objects as go
 
 def seo_check(url):
-    report = []
-    suggestions = []
-
-    # Ensure HTTPS
     if not url.startswith("http"):
         url = "https://" + url
 
@@ -16,120 +13,165 @@ def seo_check(url):
         response.raise_for_status()
         html = response.text
     except Exception as e:
-        return f"❌ Error accessing URL: {e}", ""
+        return f"❌ Could not access URL: {e}", None, "", "", ""
 
     soup = BeautifulSoup(html, "html.parser")
+    parsed = urlparse(url)
+    base = f"{parsed.scheme}://{parsed.netloc}"
+
+    results = []
+    passed = 0
+    failed = 0
+    warnings = 0
+
+    def check(condition, title, fix, warning=False):
+        nonlocal passed, failed, warnings
+        if condition:
+            results.append(f"✅ {title}")
+            passed += 1
+        else:
+            if warning:
+                results.append(f"⚠️ {title}")
+                warnings += 1
+            else:
+                results.append(f"❌ {title}")
+                failed += 1
+            suggestions.append(f"{title}: {fix}")
+
+    suggestions = []
 
-    # Title Tag
-    title = soup.title.string.strip() if soup.title else ""
-    if not title:
-        report.append("❌ Missing <title> tag.")
-        suggestions.append("Add a <title> tag that describes your page in 50–60 characters.")
-    elif len(title) > 70:
-        report.append("⚠️ Title is too long.")
-        suggestions.append("Keep title under 70 characters.")
+    # 1. Title tag
+    check(soup.title and soup.title.string.strip(), "Title Tag Present", "Add a <title> tag to your HTML.")
 
-    # Meta Description
+    # 2. Meta Description
     desc_tag = soup.find("meta", attrs={"name": "description"})
-    desc = desc_tag["content"].strip() if desc_tag and desc_tag.get("content") else ""
-    if not desc:
-        report.append("❌ Missing meta description.")
-        suggestions.append("Add a <meta name='description'> summarizing the page.")
-    elif len(desc) > 160:
-        report.append("⚠️ Meta description is too long.")
-        suggestions.append("Keep meta descriptions under 160 characters.")
-
-    # Canonical Tag
+    check(desc_tag and desc_tag.get("content", "").strip(), "Meta Description Present", "Add a meta description.")
+
+    # 3. Canonical Link
     canonical = soup.find("link", rel="canonical")
-    if not canonical:
-        report.append("❌ Missing canonical link.")
-        suggestions.append("Add a <link rel='canonical'> to avoid duplicate content.")
+    check(bool(canonical), "Canonical Tag Present", "Add <link rel='canonical'> to avoid duplicate content.")
 
-    # H1 Tag
+    # 4. H1 Tag
     h1_tags = soup.find_all("h1")
-    if len(h1_tags) != 1:
-        report.append(f"⚠️ Found {len(h1_tags)} <h1> tags.")
-        suggestions.append("Use exactly one <h1> tag for SEO clarity.")
+    check(len(h1_tags) == 1, "Exactly One H1 Tag", "Use exactly one <h1> tag.")
 
-    # Mobile viewport
+    # 5. Mobile Meta Tag
     viewport = soup.find("meta", attrs={"name": "viewport"})
-    if not viewport:
-        report.append("⚠️ No viewport meta tag.")
-        suggestions.append("Add a viewport meta tag for mobile responsiveness.")
+    check(bool(viewport), "Mobile Viewport Meta Tag", "Add <meta name='viewport'> for mobile compatibility.")
 
-    # HTTPS check
-    if not url.startswith("https://"):
-        report.append("⚠️ URL is not secure (no HTTPS).")
-        suggestions.append("Install SSL and redirect HTTP to HTTPS.")
+    # 6. HTTPS
+    check(url.startswith("https://"), "Uses HTTPS", "Secure your website with SSL.")
 
-    # Robots.txt and sitemap.xml
-    parsed = urlparse(url)
-    base = f"{parsed.scheme}://{parsed.netloc}"
-    robots_url = urljoin(base, "/robots.txt")
-    sitemap_url = urljoin(base, "/sitemap.xml")
+    # 7. robots.txt
     try:
-        r1 = requests.get(robots_url)
-        if r1.status_code != 200:
-            report.append("❌ robots.txt not found.")
-            suggestions.append("Create a robots.txt to guide search bots.")
+        r1 = requests.get(urljoin(base, "/robots.txt"))
+        check(r1.status_code == 200, "robots.txt Found", "Create a robots.txt file.")
     except:
-        report.append("❌ Could not access robots.txt.")
+        check(False, "robots.txt Found", "Create a robots.txt file.")
 
+    # 8. sitemap.xml
     try:
-        r2 = requests.get(sitemap_url)
-        if r2.status_code != 200:
-            report.append("❌ sitemap.xml not found.")
-            suggestions.append("Add sitemap.xml for better crawling.")
+        r2 = requests.get(urljoin(base, "/sitemap.xml"))
+        check(r2.status_code == 200, "sitemap.xml Found", "Add a sitemap.xml file.")
     except:
-        report.append("❌ Could not access sitemap.xml.")
+        check(False, "sitemap.xml Found", "Add a sitemap.xml file.")
 
-    # Open Graph Tags
+    # 9. OG Title
     og_title = soup.find("meta", property="og:title")
-    if not og_title:
-        report.append("⚠️ Missing Open Graph (og:title).")
-        suggestions.append("Add OG tags to improve sharing on social media.")
+    check(bool(og_title), "Open Graph Title Present", "Add Open Graph meta tags.")
+
+    # 10. OG Description
+    og_desc = soup.find("meta", property="og:description")
+    check(bool(og_desc), "Open Graph Description Present", "Add Open Graph meta tags.")
 
-    # Image alt text
+    # 11. Image ALT Tags
     images = soup.find_all("img")
     alt_missing = [img for img in images if not img.get("alt")]
-    if alt_missing:
-        report.append(f"⚠️ {len(alt_missing)} images missing alt text.")
-        suggestions.append("Add descriptive alt attributes to all images.")
+    check(len(alt_missing) < len(images), "Image ALT Tags Used", "Add alt attributes to all images.")
 
-    # Internal and external links
+    # 12. Internal links
     links = soup.find_all("a", href=True)
-    internal = 0
-    external = 0
-    for link in links:
-        href = link['href']
-        if parsed.netloc in href:
-            internal += 1
-        elif href.startswith("http"):
-            external += 1
-    report.append(f"ℹ️ Internal Links: {internal} | External Links: {external}")
-    suggestions.append("Ensure most important links are internal. Check broken links.")
-
-    # Keyword density (basic)
-    body_text = soup.get_text().lower()
-    words = body_text.split()
-    word_count = len(words)
+    parsed_host = parsed.netloc
+    internal_links = [link for link in links if parsed_host in link['href']]
+    check(len(internal_links) >= 5, "Has Internal Links", "Add more internal links.")
+
+    # 13. External links
+    external_links = [link for link in links if link['href'].startswith("http") and parsed_host not in link['href']]
+    check(len(external_links) >= 1, "Has External Links", "Add authoritative external links.")
+
+    # 14. Favicon
+    favicon = soup.find("link", rel=lambda x: x and "icon" in x.lower())
+    check(bool(favicon), "Favicon Present", "Add a favicon link.")
+
+    # 15. Keyword in Title
     keyword = parsed.netloc.replace("www.", "").split(".")[0]
-    keyword_freq = words.count(keyword)
-    density = (keyword_freq / word_count) * 100 if word_count else 0
-    report.append(f"ℹ️ Keyword '{keyword}' appears {keyword_freq} times ({density:.2f}% density)")
-    if density < 0.5:
-        suggestions.append("Consider using your main keyword more often (target 1–2%).")
+    check(soup.title and keyword.lower() in soup.title.string.lower(), "Keyword in Title", f"Add keyword '{keyword}' in title.", warning=True)
+
+    # 16. Keyword in Description
+    check(desc_tag and keyword.lower() in desc_tag.get("content", "").lower(), "Keyword in Meta Description", f"Add keyword '{keyword}' in description.", warning=True)
+
+    # 17. Content Length
+    text = soup.get_text()
+    check(len(text.split()) >= 300, "Enough Text Content", "Add more meaningful content.")
+
+    # 18. No Inline CSS
+    inline_styles = soup.find_all(style=True)
+    check(len(inline_styles) < 5, "Minimal Inline CSS", "Avoid inline CSS styles.", warning=True)
+
+    # 19. No Broken Links (basic)
+    check(len([link for link in links if 'href' in link.attrs and link['href'].startswith("#")]) < len(links), "No Broken Anchor Links", "Avoid '#' as href in <a> tags.", warning=True)
+
+    # 20. No Flash
+    flash = soup.find_all("object")
+    check(len(flash) == 0, "No Flash Elements", "Avoid using Flash elements.")
+
+    # 21. Charset Set
+    charset = soup.find("meta", charset=True)
+    check(bool(charset), "Charset Declared", "Add <meta charset='UTF-8'>.")
+
+    # 22. HTML Language Set
+    check(soup.html and soup.html.get("lang"), "HTML lang Attribute", "Add lang attribute in <html> tag.")
+
+    # 23. Structured Data Present
+    ld_json = soup.find("script", type="application/ld+json")
+    check(bool(ld_json), "Structured Data Detected", "Add structured data using JSON-LD.")
+
+    # 24. H2 Tags
+    h2 = soup.find_all("h2")
+    check(len(h2) >= 1, "Has H2 Subheadings", "Use subheadings to organize content.")
+
+    # 25. Page Title Length OK
+    if soup.title:
+        check(len(soup.title.string) <= 70, "Title Length OK", "Keep title under 70 characters.", warning=True)
+
+    # Scoring
+    total_tests = 25
+    score = int((passed / total_tests) * 100)
+
+    # Chart
+    chart = go.Figure(go.Indicator(
+        mode="gauge+number",
+        value=score,
+        title={'text': "SEO Score"},
+        gauge={'axis': {'range': [0, 100]}, 'bar': {'color': "green"}}
+    ))
+    chart.update_layout(width=400, height=300)
+
+    # Result strings
+    summary = f"✅ Passed: {passed}/{total_tests}\n⚠️ Warnings: {warnings}/{total_tests}\n❌ Failed: {failed}/{total_tests}"
 
-    return "\n".join(report), "\n".join(suggestions)
+    return summary, chart, "\n".join(results), "\n".join(suggestions)
 
-# Gradio UI
+# Gradio interface
 gr.Interface(
     fn=seo_check,
     inputs=gr.Textbox(label="Enter Website URL"),
     outputs=[
-        gr.Textbox(label="SEO Report", lines=15),
-        gr.Textbox(label="Suggestions & Fixes", lines=15)
+        gr.Textbox(label="Summary"),
+        gr.Plot(label="SEO Score Gauge"),
+        gr.Textbox(label="Detailed Test Results", lines=25),
+        gr.Textbox(label="Fix Suggestions", lines=25)
     ],
-    title="SEO Website Checker",
-    description="Analyze your website's SEO like Sitechecker.pro & SEOSiteCheckup, with clear solutions!"
+    title="Advanced SEO Audit Tool",
+    description="Performs 25+ SEO checks like SEOSiteCheckup and gives clear solutions."
 ).launch()