import requests from bs4 import BeautifulSoup from urllib.parse import urljoin, urlparse import logging import re logger = logging.getLogger(__name__) class SEOAuditor: """Audit a website or individual pages for common SEO issues.""" def __init__(self, site_url): self.site_url = site_url.rstrip("/") self.domain = urlparse(self.site_url).netloc # ------------------------------------------------------------------ def audit_page(self, url): """Run a full SEO audit on a single page.""" try: resp = requests.get(url, timeout=15, headers={ "User-Agent": "Core365-SEO-Auditor/1.0" }) resp.raise_for_status() soup = BeautifulSoup(resp.text, "lxml") # Title title_tag = soup.find("title") title = title_tag.get_text(strip=True) if title_tag else "" title_length = len(title) # Meta description meta_desc_tag = soup.find("meta", attrs={"name": "description"}) meta_desc = meta_desc_tag.get("content", "") if meta_desc_tag else "" meta_desc_length = len(meta_desc) # Headings headings = {} for level in range(1, 7): tags = soup.find_all(f"h{level}") if tags: headings[f"h{level}"] = [t.get_text(strip=True) for t in tags] # Images images = soup.find_all("img") images_total = len(images) images_without_alt = len([ img for img in images if not img.get("alt") or img.get("alt", "").strip() == "" ]) # Links all_links = soup.find_all("a", href=True) internal_links = [] external_links = [] for link in all_links: href = link.get("href", "") full_url = urljoin(url, href) parsed = urlparse(full_url) if parsed.netloc == self.domain: internal_links.append(full_url) elif parsed.scheme in ("http", "https"): external_links.append(full_url) # Word count (body text) body = soup.find("body") text = body.get_text(separator=" ", strip=True) if body else "" word_count = len(text.split()) # Calculate SEO score score = 100 issues = [] # Title checks if not title: score -= 20 issues.append("Missing page title") elif title_length < 30: score -= 10 issues.append(f"Title too short ({title_length} chars, aim for 50-60)") elif title_length > 60: score -= 5 issues.append(f"Title too long ({title_length} chars, aim for 50-60)") # Meta description checks if not meta_desc: score -= 15 issues.append("Missing meta description") elif meta_desc_length < 120: score -= 5 issues.append(f"Meta description too short ({meta_desc_length} chars, aim for 150-155)") elif meta_desc_length > 160: score -= 5 issues.append(f"Meta description too long ({meta_desc_length} chars, aim for 150-155)") # Heading checks if "h1" not in headings: score -= 15 issues.append("Missing H1 heading") elif len(headings.get("h1", [])) > 1: score -= 10 issues.append(f"Multiple H1 headings ({len(headings['h1'])}). Use only one.") if "h2" not in headings: score -= 5 issues.append("No H2 subheadings found") # Image checks if images_without_alt > 0: penalty = min(images_without_alt * 3, 15) score -= penalty issues.append(f"{images_without_alt} of {images_total} images missing alt text") # Content length if word_count < 300: score -= 15 issues.append(f"Content too thin ({word_count} words, aim for 1000+)") elif word_count < 800: score -= 5 issues.append(f"Content could be longer ({word_count} words, aim for 1000+)") # Internal links if len(internal_links) < 2: score -= 5 issues.append("Few internal links. Add more for better SEO.") score = max(0, score) return { "url": url, "title": title, "title_length": title_length, "meta_description": meta_desc, "meta_description_length": meta_desc_length, "headings": headings, "images_total": images_total, "images_without_alt": images_without_alt, "internal_links": len(internal_links), "external_links": len(external_links), "word_count": word_count, "score": score, "issues": issues, } except Exception as e: logger.error(f"Failed to audit {url}: {e}") return {"url": url, "error": str(e), "score": 0, "issues": [str(e)]} # ------------------------------------------------------------------ def audit_site(self, sitemap_url=None): """Audit all pages found in the sitemap.""" urls = self._get_urls_from_sitemap(sitemap_url) if not urls: # Fall back to just the homepage urls = [self.site_url] results = [] for url in urls[:20]: # Limit to 20 pages to avoid timeouts results.append(self.audit_page(url)) return results # ------------------------------------------------------------------ def _get_urls_from_sitemap(self, sitemap_url=None): """Parse sitemap.xml to get page URLs.""" if not sitemap_url: sitemap_url = f"{self.site_url}/sitemap.xml" try: resp = requests.get(sitemap_url, timeout=15) resp.raise_for_status() soup = BeautifulSoup(resp.content, "lxml-xml") urls = [loc.text for loc in soup.find_all("loc")] return urls except Exception as e: logger.error(f"Failed to parse sitemap: {e}") return [] # ------------------------------------------------------------------ def check_robots_txt(self): """Check robots.txt.""" try: resp = requests.get(f"{self.site_url}/robots.txt", timeout=10) if resp.status_code == 200: return {"exists": True, "content": resp.text[:1000]} return {"exists": False, "content": ""} except Exception as e: return {"exists": False, "error": str(e)} # ------------------------------------------------------------------ def check_sitemap(self): """Check if sitemap.xml exists.""" try: resp = requests.get(f"{self.site_url}/sitemap.xml", timeout=10) if resp.status_code == 200: soup = BeautifulSoup(resp.content, "lxml-xml") urls = soup.find_all("loc") return {"exists": True, "url_count": len(urls)} return {"exists": False, "url_count": 0} except Exception as e: return {"exists": False, "error": str(e)}