ts

xhs_crawler_core.py

@@ -556,31 +556,15 @@ def resolve_profile_by_search(
                 xhs_no = ""
                 try:
                     full_text = (it.inner_text() or "").strip()
-                    _log(log, f"[调试] 原始文本: {full_text[:100]}")
-
-                    # 首先提取小红书号（尝试多种模式）
-                    patterns = [
-                        r'小红书号[：:]\s*([A-Za-z0-9]+)',
-                        r'小红书号[：:]\s*([A-Za-z0-9]+)',
-                        r'ID[：:]\s*([A-Za-z0-9]+)',
-                        r'账号[：:]\s*([A-Za-z0-9]+)',
-                    ]
-                    for pattern in patterns:
-                        m = re.search(pattern, full_text)
+                    # 提取小红书号
+                    m = re.search(r'小红书号[：:]\s*([A-Za-z0-9]+)', full_text)
                     if m:
                         xhs_no = m.group(1).strip()
-                            _log(log, f"[调试] 匹配到小红书号: {xhs_no} (pattern: {pattern})")
-                            break
-
-                    if not xhs_no:
-                        _log(log, f"[调试] 未能匹配小红书号")
 
                     # 提取昵称：从开头去除干扰信息
                     lines = full_text.split('\n')
                     if lines:
                         main_text = lines[0].strip()
-                        _log(log, f"[调试] 第一行文本: {main_text}")
-
                         # 移除小红书号及其后面的所有内容
                         main_text = re.sub(r'小红书号[：:].*$', '', main_text).strip()
                         # 移除时间信息
@@ -592,11 +576,9 @@ def resolve_profile_by_search(
                         # 移除分隔符
                         main_text = re.sub(r'\s*[・·]\s*', ' ', main_text).strip()
                         nickname = re.sub(r'\s+', ' ', main_text).strip()
-                        _log(log, f"[调试] 清理后昵称: {nickname}")
                     else:
                         nickname = full_text
-                except Exception as e:
-                    _log(log, f"[调试] 解析异常: {e}")
+                except Exception:
                     nickname = ""
                     xhs_no = ""
             else:
@@ -777,12 +759,12 @@ def crawl_detail(
     slow_mo: int = 80,
     batch_min: int = 3,
     batch_max: int = 7,
-    open_wait: Tuple[int, int] = (1800, 3200),
-    between_wait: Tuple[int, int] = (1500, 3200),
-    scroll_wait: Tuple[int, int] = (1600, 2800),
-    long_break: Tuple[int, int] = (6000, 12000),
+    open_wait: Tuple[int, int] = (1200, 2000),  # 风控安全：适度等待
+    between_wait: Tuple[int, int] = (1000, 1800),  # 风控安全：笔记间等待
+    scroll_wait: Tuple[int, int] = (1000, 1800),  # 风控安全：滚动等待
+    long_break: Tuple[int, int] = (5000, 9000),  # 风控安全：长休息时间
     scroll_target_new: int = 2,
-    scroll_max_attempts: int = 10,
+    scroll_max_attempts: int = 8,  # 风控安全：适度滚动次数
     out_file: str = "out/result_modal_details.json",
     stop_event=None,
     log: Optional[Callable[[str], None]] = None,
@@ -955,7 +937,7 @@ def crawl_detail(
                     """)
                 except Exception:
                     pass
-                page.wait_for_timeout(random.randint(2000, 3500))
+                page.wait_for_timeout(random.randint(1500, 2500))  # 风控安全：适度等待
                 after2 = count_visible_unprocessed(page, processed)
                 if after2 > before:
                     return True
@@ -994,8 +976,8 @@ def crawl_detail(
         page = context.new_page()
 
         page.goto(profile_url, wait_until="domcontentloaded", timeout=60000)
-        page.wait_for_selector(NOTE_CONTAINER_SELECTOR, timeout=30000)
-        _wait_ms(page, (1200, 2200))
+        page.wait_for_selector(NOTE_CONTAINER_SELECTOR, timeout=25000)  # 风控安全：适度等待
+        _wait_ms(page, (800, 1500))  # 风控安全：适度等待
 
         safety_round = 0
         while len(results) < limit and safety_round < 2000:
@@ -1020,7 +1002,7 @@ def crawl_detail(
                     item.scroll_into_view_if_needed()
                 except Exception:
                     pass
-                _wait_ms(page, (700, 1300))
+                _wait_ms(page, (500, 900))  # 风控安全：适度等待
 
                 try:
                     opener.click(timeout=6000)
@@ -1031,14 +1013,14 @@ def crawl_detail(
                         continue
 
                 try:
-                    # 关键：不要用 #noteContainer 这种“永远可见”的元素判断弹框是否打开
-                    page.wait_for_selector(DETAIL_TITLE_SELECTOR, state="visible", timeout=25000)
+                    # 关键：不要用 #noteContainer 这种"永远可见"的元素判断弹框是否打开
+                    page.wait_for_selector(DETAIL_TITLE_SELECTOR, state="visible", timeout=15000)  # 优化：从 25 秒降至 15 秒
                 except PWTimeoutError:
-                    # 先做一次“强制点击+更长等待”的快速重试，尽量别直接跳过
+                    # 先做一次"强制点击+更长等待"的快速重试，尽量别直接跳过
                     retry_ok = False
                     try:
                         opener.click(timeout=6000, force=True)
-                        page.wait_for_selector(DETAIL_TITLE_SELECTOR, state="visible", timeout=30000)
+                        page.wait_for_selector(DETAIL_TITLE_SELECTOR, state="visible", timeout=15000)  # 优化：从 30 秒降至 15 秒
                         retry_ok = True
                     except Exception:
                         retry_ok = False