fix(scraper): 页面抓取器支持员工列表翻页(之前只抓第一页10个)

yunke-server/scripts/scrape_via_page.py

@@ -209,11 +209,42 @@ class PageScraper:
             return result;
         }""")
 
-        # Also paginate through staff list if needed
+        # Paginate through ALL staff list pages
-        # (for now, first page of 50 should cover most)
+        all_employees = list(employees)
+        page = 1
+        while await self.click_next_page():
+            page += 1
+            await self.page.wait_for_timeout(2000)
+            more = await self.page.evaluate("""() => {
+                const rows = document.querySelectorAll('.ant-table-row');
+                const result = [];
+                for (const tr of rows) {
+                    const friendLink = tr.querySelector('a[href*="wechatdetail/1/"]');
+                    const groupLink = tr.querySelector('a[href*="wechatdetail/2/"]');
+                    if (friendLink) {
+                        const href = friendLink.getAttribute('href');
+                        const wxId = href.match(/wechatdetail\\/1\\/([^?]+)/)?.[1];
+                        const friendCount = parseInt(friendLink.textContent) || 0;
+                        const groupHref = groupLink?.getAttribute('href');
+                        const groupCount = parseInt(groupLink?.textContent) || 0;
+                        result.push({ wxId, friendCount, groupCount, friendHref: href, groupHref });
+                    }
+                }
+                return result;
+            }""")
+            all_employees.extend(more)
+            logger.info(f"  staff page {page}: +{len(more)} employees (total: {len(all_employees)})")
 
-        logger.info(f"Found {len(employees)} employees with friend links")
+        # Dedup by wxId
-        return employees
+        seen = set()
+        deduped = []
+        for emp in all_employees:
+            if emp["wxId"] not in seen:
+                seen.add(emp["wxId"])
+                deduped.append(emp)
+
+        logger.info(f"Found {len(deduped)} unique employees with friend links ({page} pages)")
+        return deduped
 
 
 async def scrape_friends(cookie_str: str, max_employees: int = 100):