feat(prospecting): add content scraping for POC builder (Workstream 3A)

- New scrape_content() method in enrichment_service: extracts meta
  description, H1/H2 headings, paragraphs, images (filtered for size),
  social links, service items, and detected languages using BeautifulSoup
- Scans 6 pages per prospect: /, /about, /a-propos, /services,
  /nos-services, /contact
- Results stored as JSON in prospect.scraped_content_json
- New endpoints: POST /content-scrape/{id} and /content-scrape/batch
- Added to full_enrichment pipeline (Step 5, before security audit)
- CONTENT_SCRAPE job type for scan-jobs tracking
- "Content Scrape" batch button on scan-jobs page
- Add beautifulsoup4 to requirements.txt

Tested on batirenovation-strasbourg.fr: extracted 30 headings,
21 paragraphs, 13 images.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

app/modules/prospecting/routes/api/admin_enrichment.py

@@ -139,6 +139,27 @@ def contact_scrape_batch(
     return ScanBatchResponse(processed=len(prospects), successful=count)
 
 
+@router.post("/content-scrape/batch", response_model=ScanBatchResponse)
+def content_scrape_batch(
+    limit: int = Query(50, ge=1, le=200),
+    db: Session = Depends(get_db),
+    current_admin: UserContext = Depends(get_current_admin_api),
+):
+    """Scrape page content for pending prospects."""
+    job = stats_service.create_job(db, JobType.CONTENT_SCRAPE)
+    prospects = prospect_service.get_pending_content_scrape(db, limit=limit)
+    count = 0
+    for i, prospect in enumerate(prospects):
+        result = enrichment_service.scrape_content(db, prospect)
+        if result:
+            count += 1
+        if i < len(prospects) - 1:
+            _batch_delay()
+    stats_service.complete_job(job, processed=len(prospects))
+    db.commit()
+    return ScanBatchResponse(processed=len(prospects), successful=count)
+
+
 @router.post("/security-audit/batch", response_model=ScanBatchResponse)
 def security_audit_batch(
     limit: int = Query(50, ge=1, le=200),
@@ -272,6 +293,19 @@ def security_audit_single(
     )
 
 
+@router.post("/content-scrape/{prospect_id}", response_model=ScanSingleResponse)
+def content_scrape_single(
+    prospect_id: int = Path(...),
+    db: Session = Depends(get_db),
+    current_admin: UserContext = Depends(get_current_admin_api),
+):
+    """Scrape page content for a single prospect."""
+    prospect = prospect_service.get_by_id(db, prospect_id)
+    result = enrichment_service.scrape_content(db, prospect)
+    db.commit()
+    return ScanSingleResponse(domain=prospect.domain_name, profile=result is not None)
+
+
 @router.post("/full/{prospect_id}", response_model=FullEnrichmentResponse)
 def full_enrichment(
     prospect_id: int = Path(...),
@@ -299,11 +333,15 @@ def full_enrichment(
     if prospect.has_website:
         contacts = enrichment_service.scrape_contacts(db, prospect)
 
-    # Step 5: Security audit (if has website)
+    # Step 5: Content scrape (if has website)
+    if prospect.has_website:
+        enrichment_service.scrape_content(db, prospect)
+
+    # Step 6: Security audit (if has website)
     if prospect.has_website:
         security_audit_service.run_audit(db, prospect)
 
-    # Step 6: Compute score
+    # Step 7: Compute score
     db.refresh(prospect)
     score = scoring_service.compute_score(db, prospect)
     db.commit()