xhs-note-extractor 0.1.dev8__tar.gz → 0.1.dev10__tar.gz

{xhs_note_extractor-0.1.dev8 → xhs_note_extractor-0.1.dev10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: xhs-note-extractor
-Version: 0.1.dev8
+Version: 0.1.dev10
 Summary: A Python package for extracting Xiaohongshu (Little Red Book) note data from URLs
 Author-email: JoyCode Agent <agent@joycode.com>
 License: MIT

{xhs_note_extractor-0.1.dev8 → xhs_note_extractor-0.1.dev10}/examples/basic_usage.py

@@ -31,7 +31,7 @@ def main():
     
     # 示例1: 提取单个笔记
     print("\n=== 示例1: 提取单个笔记 ===")
-    note_url = "https://www.xiaohongshu.com/explore/6965d2be000000000d009811?xsec_token=ABSsTDqkPo7quKqkrecMaoJuId5a3mfvDLB3OpahVNmlU=&xsec_source=pc_search&source=unknown "  # 替换为实际的笔记URL
+    note_url = "https://www.xiaohongshu.com/explore/6960e673000000000a02857b?xsec_token=ABTv9s4ROv84q7M5ugj9bBctaS8LN3_BOhYsv1hlkAYoQ=&xsec_source=pc_search&source=unknown"  # 替换为实际的笔记URL
     
     try:
         note_data = extractor.extract_note_data(note_url)

{xhs_note_extractor-0.1.dev8 → xhs_note_extractor-0.1.dev10}/pyproject.toml

@@ -31,7 +31,7 @@ dependencies = [
     "uiautomator2>=2.16.17",
     "requests>=2.25.0",
 ]
-version = "0.1.dev8"
+version = "0.1.dev10"
 
 [project.optional-dependencies]
 dev = [

{xhs_note_extractor-0.1.dev8 → xhs_note_extractor-0.1.dev10}/uv.lock

@@ -816,7 +816,7 @@ wheels = [
 
 [[package]]
 name = "xhs-note-extractor"
-version = "0.1.dev8"
+version = "0.1.dev9"
 source = { editable = "." }
 dependencies = [
     { name = "requests" },

{xhs_note_extractor-0.1.dev8 → xhs_note_extractor-0.1.dev10}/xhs_note_extractor/extractor.py

@@ -464,11 +464,27 @@ class XHSNoteExtractor:
         if not detail_loaded:
             logger.warning("⚠ 警告:详情页特征未发现,提取可能不完整")
 
-        # 向下滚动一点,确保发布时间可见
+        # 向下滚动直到看到评论区标志
         try:
             logger.info("📜 向下滚动以显示发布时间...")
-            self.device.swipe(540, 1500, 540, 1000, 0.3)  # 从下往上滑动
-            time.sleep(0.5)  # 等待滚动完成
+            max_scrolls = 20  # 最多滚动5次
+            comment_section_found = False
+            
+            for scroll_attempt in range(max_scrolls):
+                # 检查是否已经看到评论区标志
+                xml_check = self.device.dump_hierarchy()
+                if re.search(r'共\s*\d+\s*条评论', xml_check) and re.search(r'说点什么', xml_check):
+                    logger.info(f"✓ 找到评论区标志,停止滚动 (滚动{scroll_attempt}次)")
+                    comment_section_found = True
+                    break
+                
+                # 继续滚动
+                self.device.swipe(540, 1500, 540, 1000, 0.3)
+                time.sleep(0.3)
+            
+            if not comment_section_found:
+                logger.warning(f"⚠ 滚动{max_scrolls}次后仍未找到评论区标志")
+                
         except Exception as e:
             logger.warning(f"滚动失败: {e}")
 

{xhs_note_extractor-0.1.dev8 → xhs_note_extractor-0.1.dev10}/xhs_note_extractor.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: xhs-note-extractor
-Version: 0.1.dev8
+Version: 0.1.dev10
 Summary: A Python package for extracting Xiaohongshu (Little Red Book) note data from URLs
 Author-email: JoyCode Agent <agent@joycode.com>
 License: MIT