Update app.py

app.py

@@ -1,177 +1,84 @@
+import gradio as gr
 import requests
 from bs4 import BeautifulSoup
-from urllib.parse import urlparse, urljoin
-import gradio as gr
-import plotly.graph_objects as go
+from urllib.parse import urlparse
 
 def seo_check(url):
-    if not url.startswith("http"):
-        url = "https://" + url
-
     try:
         response = requests.get(url, timeout=10)
-        response.raise_for_status()
         html = response.text
+        soup = BeautifulSoup(html, 'html.parser')
     except Exception as e:
-        return f"❌ Could not access URL: {e}", None, "", "", ""
-
-    soup = BeautifulSoup(html, "html.parser")
+        return f"❌ Error fetching the URL: {e}", "", "", "", ""
+
+    checks = []
+
+    # SEO Test 1: Title tag
+    title_tag = soup.title.string.strip() if soup.title and soup.title.string else ''
+    if title_tag:
+        checks.append(("Title Tag Present", "Passed", "A <title> tag exists.", "No action needed."))
+    else:
+        checks.append(("Title Tag Missing", "Failed", "The page is missing a <title> tag.", "Add a <title> tag to improve SEO."))
+
+    # SEO Test 2: Meta description
+    meta_desc = soup.find("meta", attrs={"name": "description"})
+    if meta_desc and meta_desc.get("content", "").strip():
+        checks.append(("Meta Description Present", "Passed", "A meta description is provided.", "No action needed."))
+    else:
+        checks.append(("Meta Description Missing", "Warning", "No meta description found.", "Add a concise meta description (150-160 characters)."))
+
+    # SEO Test 3: H1 tag
+    h1 = soup.find("h1")
+    if h1 and h1.get_text(strip=True):
+        checks.append(("H1 Tag Present", "Passed", "A single <h1> tag is present.", "No action needed."))
+    else:
+        checks.append(("H1 Tag Missing", "Failed", "No <h1> tag found.", "Include one descriptive <h1> tag per page."))
+
+    # SEO Test 4: HTTPS usage
     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 = []
-
-    # 1. Title tag
-    check(soup.title and soup.title.string.strip(), "Title Tag Present", "Add a <title> tag to your HTML.")
-
-    # 2. Meta Description
-    desc_tag = soup.find("meta", attrs={"name": "description"})
-    check(desc_tag and desc_tag.get("content", "").strip(), "Meta Description Present", "Add a meta description.")
+    if parsed.scheme == "https":
+        checks.append(("HTTPS Protocol", "Passed", "Site uses secure HTTPS connection.", "No action needed."))
+    else:
+        checks.append(("Not Using HTTPS", "Failed", "The site is not served over HTTPS.", "Enable SSL/TLS to secure the site and improve rankings."))
 
-    # 3. Canonical Link
-    canonical = soup.find("link", rel="canonical")
-    check(bool(canonical), "Canonical Tag Present", "Add <link rel='canonical'> to avoid duplicate content.")
-
-    # 4. H1 Tag
-    h1_tags = soup.find_all("h1")
-    check(len(h1_tags) == 1, "Exactly One H1 Tag", "Use exactly one <h1> tag.")
-
-    # 5. Mobile Meta Tag
-    viewport = soup.find("meta", attrs={"name": "viewport"})
-    check(bool(viewport), "Mobile Viewport Meta Tag", "Add <meta name='viewport'> for mobile compatibility.")
-
-    # 6. HTTPS
-    check(url.startswith("https://"), "Uses HTTPS", "Secure your website with SSL.")
-
-    # 7. robots.txt
+    # SEO Test 5: Robots.txt availability
+    robots_url = f"{parsed.scheme}://{parsed.netloc}/robots.txt"
     try:
-        r1 = requests.get(urljoin(base, "/robots.txt"))
-        check(r1.status_code == 200, "robots.txt Found", "Create a robots.txt file.")
-    except:
-        check(False, "robots.txt Found", "Create a robots.txt file.")
-
-    # 8. sitemap.xml
-    try:
-        r2 = requests.get(urljoin(base, "/sitemap.xml"))
-        check(r2.status_code == 200, "sitemap.xml Found", "Add a sitemap.xml file.")
+        robots_response = requests.get(robots_url, timeout=5)
+        if robots_response.status_code == 200:
+            checks.append(("robots.txt Found", "Passed", "robots.txt file exists.", "No action needed."))
+        else:
+            checks.append(("robots.txt Missing", "Warning", "robots.txt file not found.", "Add a robots.txt to control crawler access."))
     except:
-        check(False, "sitemap.xml Found", "Add a sitemap.xml file.")
-
-    # 9. OG Title
-    og_title = soup.find("meta", property="og:title")
-    check(bool(og_title), "Open Graph Title Present", "Add Open Graph meta tags.")
+        checks.append(("robots.txt Fetch Failed", "Warning", "Could not access robots.txt.", "Ensure the file is publicly accessible."))
 
-    # 10. OG Description
-    og_desc = soup.find("meta", property="og:description")
-    check(bool(og_desc), "Open Graph Description Present", "Add Open Graph meta tags.")
+    # SEO Score calculation
+    total = len(checks)
+    passed = sum(1 for _, result, _, _ in checks if result == "Passed")
+    warnings = sum(1 for _, result, _, _ in checks if result == "Warning")
+    failed = sum(1 for _, result, _, _ in checks if result == "Failed")
+    score = int((passed / total) * 100)
 
-    # 11. Image ALT Tags
-    images = soup.find_all("img")
-    alt_missing = [img for img in images if not img.get("alt")]
-    check(len(alt_missing) < len(images), "Image ALT Tags Used", "Add alt attributes to all images.")
+    passed_section = "\n".join([f"✅ {name}\n✔️ {desc}" for name, result, desc, _ in checks if result == "Passed"])
+    warning_section = "\n".join([f"⚠️ {name}\n{desc}\n💡 Suggestion: {fix}" for name, result, desc, fix in checks if result == "Warning"])
+    failed_section = "\n".join([f"❌ {name}\n{desc}\n💡 Fix: {fix}" for name, result, desc, fix in checks if result == "Failed"])
 
-    # 12. Internal links
-    links = soup.find_all("a", href=True)
-    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.")
+    return f"🔎 SEO Score: {score}/100", f"✅ Passed: {passed}", f"⚠️ Warnings: {warnings}", f"❌ Failed: {failed}", f"{passed_section}\n\n{warning_section}\n\n{failed_section}"
 
-    # 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]
-    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 summary, chart, "\n".join(results), "\n".join(suggestions)
-
-# Gradio interface
-gr.Interface(
+# Gradio Interface
+seo_interface = gr.Interface(
     fn=seo_check,
     inputs=gr.Textbox(label="Enter Website URL"),
     outputs=[
-        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)
+        gr.Textbox(label="SEO Score"),
+        gr.Textbox(label="Passed Tests"),
+        gr.Textbox(label="Warnings"),
+        gr.Textbox(label="Failed Tests"),
+        gr.Textbox(label="Detailed Report", lines=20)
     ],
-    title="Advanced SEO Audit Tool",
-    description="Performs 25+ SEO checks like SEOSiteCheckup and gives clear solutions."
-).launch()
+    title="🔍 Website SEO Check App",
+    description="Enter any website URL to perform an SEO audit and get detailed, actionable feedback."
+)
+
+if __name__ == "__main__":
+    seo_interface.launch()