hahaa

.gitignore

@@ -0,0 +1,5 @@
+.idea
+.git
+.log
+.venv
+__pycache__

main.py

@@ -0,0 +1,48 @@
+import requests
+
+
+cookies = {
+    'abRequestId': '343dbd09-707e-59a3-9315-3b6fa1c3ff34',
+    'webBuild': '5.7.0',
+    'xsecappid': 'xhs-pc-web',
+    'a1': '19bbae7730ahxzrs5lm6s46vde8fq350g5klg6uij50000427550',
+    'webId': '17c9fe1d1bc556b2837a35fb01b770b5',
+    'gid': 'yjDD0dWYyWk8yjDD0dWWq2K780xCuFM216KMT3V4KhfdY128iAq28k8884JW2288YJWqyYjD',
+    'web_session': '0400698f1bdf69567ccb126e523b4ba45d4326',
+    'id_token': 'VjEAANiXRALq8n+D/Uh5zBxUZgZQea2cBzD/+4ZtKQHrx2FPtJYJfV+n5N7LJDdNZmVmMugQNdlm0mg6Dy78u0wHOnF2RDB4ZB7i2whxyVT8v97Yrbwz4hbQM3EtVEyNMgzIvZnR',
+    'websectiga': '29098a4cf41f76ee3f8db19051aaa60c0fc7c5e305572fec762da32d457d76ae',
+    'sec_poison_id': '36102520-3a09-4447-a36f-a1c31b15b950',
+    'acw_tc': '0a00d49317683703864606878eb20c852cedbeb990c4ffae205ebc083fcc93',
+    'loadts': '1768370387610',
+}
+
+headers = {
+    'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
+    'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
+    'cache-control': 'no-cache',
+    'dnt': '1',
+    'pragma': 'no-cache',
+    'priority': 'u=0, i',
+    'sec-ch-ua': '"Microsoft Edge";v="143", "Chromium";v="143", "Not A(Brand";v="24"',
+    'sec-ch-ua-mobile': '?0',
+    'sec-ch-ua-platform': '"Windows"',
+    'sec-fetch-dest': 'document',
+    'sec-fetch-mode': 'navigate',
+    'sec-fetch-site': 'same-origin',
+    'sec-fetch-user': '?1',
+    'upgrade-insecure-requests': '1',
+    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/143.0.0.0 Safari/537.36 Edg/143.0.0.0',
+    # 'cookie': 'abRequestId=343dbd09-707e-59a3-9315-3b6fa1c3ff34; webBuild=5.7.0; xsecappid=xhs-pc-web; a1=19bbae7730ahxzrs5lm6s46vde8fq350g5klg6uij50000427550; webId=17c9fe1d1bc556b2837a35fb01b770b5; gid=yjDD0dWYyWk8yjDD0dWWq2K780xCuFM216KMT3V4KhfdY128iAq28k8884JW2288YJWqyYjD; web_session=0400698f1bdf69567ccb126e523b4ba45d4326; id_token=VjEAANiXRALq8n+D/Uh5zBxUZgZQea2cBzD/+4ZtKQHrx2FPtJYJfV+n5N7LJDdNZmVmMugQNdlm0mg6Dy78u0wHOnF2RDB4ZB7i2whxyVT8v97Yrbwz4hbQM3EtVEyNMgzIvZnR; websectiga=29098a4cf41f76ee3f8db19051aaa60c0fc7c5e305572fec762da32d457d76ae; sec_poison_id=36102520-3a09-4447-a36f-a1c31b15b950; acw_tc=0a00d49317683703864606878eb20c852cedbeb990c4ffae205ebc083fcc93; loadts=1768370387610',
+}
+
+response = requests.get(
+    'https://www.xiaohongshu.com/explore/68eab3870000000004004112?xsec_token=ABhDIDWci_QiY0PVUtlkViv01hH_8c3AiHfagOPVFNVms=&xsec_source=pc_search&source=unknown',
+    # cookies=cookies,
+    headers=headers,
+)
+
+# 保存HTML到文件
+with open('1.html', 'w', encoding='utf-8') as f:
+    f.write(response.text)
+
+print("HTML已保存到 1.html")

note_data.json

@@ -0,0 +1,140 @@
+{
+  "title": "外版三星ZFold大折叠小红书优化排版/显示",
+  "desc": "不用再羡慕三星国行ZFold的小红书定制客户端，和多指捏放多列排版了！\n‼️一招解决：使用网页版快捷方式刷小红书，排版合理，功能简洁，客户端不再臃肿。\n\t\n使用方法（p7-p9）：\n1. Chrome浏览器打开网页版小红书，地址在p7。（其他浏览器也有类似功能）\n2. 浏览器右上角三个点 - “请求访问桌面版” - 然后再 “添加快捷方式到桌面” - 完成！\n\t\n#你会选择什么版本的三星手机？ [投票]#\n\t\n#折叠手机的各种形态[话题]# #折叠屏[话题]# #外版[话题]# #美版[话题]# #ZFold7[话题]# #三星zfold6[话题]# #W26[话题]# #心系天下[话题]# #一人一个安卓使用技巧[话题]# #一起聊数码[话题]#",
+  "images": [
+    {
+      "url": "http://sns-webpic-qc.xhscdn.com/202601141733/33e402eeb9c5ff920f17cb2629d8416f/1040g2sg31ngs7s0a5mdg4a37v9gupc36s0j93a8!nd_dft_wlteh_webp_3",
+      "urlPre": "http://sns-webpic-qc.xhscdn.com/202601141733/139f36d7c4dfd3e2976bb90261a63acd/1040g2sg31ngs7s0a5mdg4a37v9gupc36s0j93a8!nd_prv_wlteh_webp_3",
+      "width": 1200,
+      "height": 1600
+    },
+    {
+      "url": "http://sns-webpic-qc.xhscdn.com/202601141733/98a6c7d45537a5f2add622173cf24a84/1040g2sg31ngs7s0a5mbg4a37v9gupc36cg22vc0!nd_dft_wlteh_webp_3",
+      "urlPre": "http://sns-webpic-qc.xhscdn.com/202601141733/8f43add92ab25a5461b60780e796a674/1040g2sg31ngs7s0a5mbg4a37v9gupc36cg22vc0!nd_prv_wlteh_webp_3",
+      "width": 1968,
+      "height": 2184
+    },
+    {
+      "url": "http://sns-webpic-qc.xhscdn.com/202601141733/3d639a88face3b18148057ef197c47f8/1040g2sg31ngs7s0a5m7g4a37v9gupc36j1chdq0!nd_dft_wlteh_webp_3",
+      "urlPre": "http://sns-webpic-qc.xhscdn.com/202601141733/84d8fcdb12cf658b5d8dc9d50aec40ed/1040g2sg31ngs7s0a5m7g4a37v9gupc36j1chdq0!nd_prv_wlteh_webp_3",
+      "width": 1968,
+      "height": 2184
+    },
+    {
+      "url": "http://sns-webpic-qc.xhscdn.com/202601141733/12b653a8a4e91a7cf3277be9193a42bc/1040g2sg31ngs7s0a5md04a37v9gupc36f13sjlo!nd_dft_wlteh_webp_3",
+      "urlPre": "http://sns-webpic-qc.xhscdn.com/202601141733/80f540a14744b03dcf4fb840a628cc1a/1040g2sg31ngs7s0a5md04a37v9gupc36f13sjlo!nd_prv_wlteh_webp_3",
+      "width": 1968,
+      "height": 2184
+    },
+    {
+      "url": "http://sns-webpic-qc.xhscdn.com/202601141733/0ea1907a54e0ce8471aaaad44da0d4f2/1040g2sg31ngs7s0a5m9g4a37v9gupc36qqcttf8!nd_dft_wlteh_webp_3",
+      "urlPre": "http://sns-webpic-qc.xhscdn.com/202601141733/fb8e92fffb4724431c4e4a24c9933827/1040g2sg31ngs7s0a5m9g4a37v9gupc36qqcttf8!nd_prv_wlteh_webp_3",
+      "width": 1968,
+      "height": 2184
+    },
+    {
+      "url": "http://sns-webpic-qc.xhscdn.com/202601141733/302ab15194067c95bae700530d02fde1/1040g2sg31ngs7s0a5mb04a37v9gupc36rhqs4i0!nd_dft_wlteh_webp_3",
+      "urlPre": "http://sns-webpic-qc.xhscdn.com/202601141733/d250ded63f436abfd99719eae7237bd6/1040g2sg31ngs7s0a5mb04a37v9gupc36rhqs4i0!nd_prv_wlteh_webp_3",
+      "width": 1968,
+      "height": 2184
+    },
+    {
+      "url": "http://sns-webpic-qc.xhscdn.com/202601141733/599f42d37a2b4eb59c414f777a81f98c/1040g2sg31ngs7s0a5mc04a37v9gupc36ah2nce0!nd_dft_wlteh_webp_3",
+      "urlPre": "http://sns-webpic-qc.xhscdn.com/202601141733/b256afa10893b0a619199201263805d3/1040g2sg31ngs7s0a5mc04a37v9gupc36ah2nce0!nd_prv_wlteh_webp_3",
+      "width": 1968,
+      "height": 2184
+    },
+    {
+      "url": "http://sns-webpic-qc.xhscdn.com/202601141733/e91cc06969ab855a419970694c0133ab/1040g2sg31ngs7s0a5ma04a37v9gupc36snnfjj0!nd_dft_wlteh_webp_3",
+      "urlPre": "http://sns-webpic-qc.xhscdn.com/202601141733/d6c2010d73dac749f33a086aad6807f4/1040g2sg31ngs7s0a5ma04a37v9gupc36snnfjj0!nd_prv_wlteh_webp_3",
+      "width": 1968,
+      "height": 2184
+    },
+    {
+      "url": "http://sns-webpic-qc.xhscdn.com/202601141733/93d81ee1819745b2b50b7a65e33c461d/1040g2sg31ngs7s0a5mag4a37v9gupc36nbskn20!nd_dft_wlteh_webp_3",
+      "urlPre": "http://sns-webpic-qc.xhscdn.com/202601141733/e2333c5a4abbbedeabc615fdfd7a1f8d/1040g2sg31ngs7s0a5mag4a37v9gupc36nbskn20!nd_prv_wlteh_webp_3",
+      "width": 1968,
+      "height": 2184
+    }
+  ],
+  "videos": [],
+  "topics": [
+    {
+      "name": "折叠手机的各种形态",
+      "id": "64dd7b62000000000f00d00a"
+    },
+    {
+      "name": "折叠屏",
+      "id": "5cac7179000000000d014ce6"
+    },
+    {
+      "name": "外版",
+      "id": "613454d90000000001006368"
+    },
+    {
+      "name": "美版",
+      "id": "5fa0c960000000000100b74a"
+    },
+    {
+      "name": "ZFold7",
+      "id": "681b7312000000001703ad7e"
+    },
+    {
+      "name": "三星zfold6",
+      "id": "6649bb29000000001b03fc01"
+    },
+    {
+      "name": "W26",
+      "id": "6425446d000000000d03c650"
+    },
+    {
+      "name": "心系天下",
+      "id": "60842235000000000101e832"
+    },
+    {
+      "name": "一人一个安卓使用技巧",
+      "id": "5c72852c000000000f01a6c4"
+    },
+    {
+      "name": "一起聊数码",
+      "id": "62bd8992000000000101c0c6"
+    },
+    {
+      "name": "你会选择什么版本的三星手机？ ",
+      "id": "137617844749618429"
+    },
+    {
+      "name": "你会选择什么版本的三星手机？ [投票]"
+    },
+    {
+      "name": "折叠手机的各种形态[话题]"
+    },
+    {
+      "name": "折叠屏[话题]"
+    },
+    {
+      "name": "外版[话题]"
+    },
+    {
+      "name": "美版[话题]"
+    },
+    {
+      "name": "ZFold7[话题]"
+    },
+    {
+      "name": "三星zfold6[话题]"
+    },
+    {
+      "name": "W26[话题]"
+    },
+    {
+      "name": "心系天下[话题]"
+    },
+    {
+      "name": "一人一个安卓使用技巧[话题]"
+    },
+    {
+      "name": "一起聊数码[话题]"
+    }
+  ]
+}

parse_html.py

@@ -0,0 +1,281 @@
+import re
+import json
+import sys
+import io
+from bs4 import BeautifulSoup
+
+# 设置标准输出编码为UTF-8，避免Windows控制台编码问题
+if sys.platform == 'win32':
+    sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8', errors='replace')
+
+
+def extract_video_from_meta(html_content):
+    """
+    从HTML的meta标签中提取视频信息
+    
+    Args:
+        html_content: HTML内容字符串
+        
+    Returns:
+        dict: 视频信息字典，如果没有找到则返回None
+    """
+    try:
+        soup = BeautifulSoup(html_content, 'html.parser')
+        video_info = {}
+
+        # 提取og:video标签
+        og_video = soup.find('meta', {'name': 'og:video'})
+        if og_video and og_video.get('content'):
+            video_info['url'] = og_video.get('content')
+
+        # 提取视频时长
+        og_videotime = soup.find('meta', {'name': 'og:videotime'})
+        if og_videotime and og_videotime.get('content'):
+            video_info['time'] = og_videotime.get('content')
+
+        # 提取视频质量
+        og_videoquality = soup.find('meta', {'name': 'og:videoquality'})
+        if og_videoquality and og_videoquality.get('content'):
+            video_info['quality'] = og_videoquality.get('content')
+
+        # 如果找到了视频URL，返回视频信息
+        if video_info.get('url'):
+            return video_info
+
+        return None
+    except Exception as e:
+        print(f"从meta标签提取视频信息时出错：{e}")
+        return None
+
+
+def parse_html_file(html_file='1.html'):
+    """
+    解析HTML文件，提取标题、描述、图片列表、视频列表和话题
+    
+    Args:
+        html_file: HTML文件路径
+        
+    Returns:
+        dict: 解析出的笔记数据
+    """
+    try:
+        # 读取HTML文件
+        with open(html_file, 'r', encoding='utf-8') as f:
+            html_content = f.read()
+
+        # 提取meta标签中的视频信息
+        video_info = extract_video_from_meta(html_content)
+
+        # 使用正则表达式提取window.__INITIAL_STATE__的内容
+        pattern = r'<script>window\.__INITIAL_STATE__\s*=\s*({.*?});?\s*</script>'
+        match = re.search(pattern, html_content, re.DOTALL)
+
+        if not match:
+            print("未找到 window.__INITIAL_STATE__ 数据")
+            # 如果只有视频信息，返回视频信息
+            if video_info:
+                return {'videos': [video_info]}
+            return None
+
+        # 提取JSON字符串
+        json_str = match.group(1)
+
+        # 处理JavaScript中的undefined值（Python JSON不支持undefined）
+        json_str = re.sub(r'\bundefined\b', 'null', json_str)
+
+        # 解析JSON
+        initial_state = json.loads(json_str)
+
+        # 提取笔记数据
+        note_data = extract_note_data(initial_state)
+
+        # 如果提取到视频信息，添加到笔记数据中
+        if video_info and note_data:
+            if 'videos' not in note_data or not note_data['videos']:
+                note_data['videos'] = []
+            note_data['videos'].append(video_info)
+
+        return note_data
+
+    except FileNotFoundError:
+        print(f"错误：找不到文件 {html_file}")
+        return None
+    except json.JSONDecodeError as e:
+        print(f"JSON解析错误：{e}")
+        return None
+    except Exception as e:
+        print(f"解析错误：{e}")
+        return None
+
+
+def extract_note_data(initial_state):
+    """
+    从初始状态中提取笔记数据（只提取标题、描述、图片列表、视频列表和话题）
+    
+    Args:
+        initial_state: window.__INITIAL_STATE__ 解析后的字典
+        
+    Returns:
+        dict: 提取的笔记数据
+    """
+    try:
+        # 获取笔记详情
+        note_store = initial_state.get('note', {})
+        note_detail_map = note_store.get('noteDetailMap', {})
+
+        # 获取第一个笔记ID
+        first_note_id = note_store.get('firstNoteId')
+        if not first_note_id:
+            # 如果没有firstNoteId，尝试获取noteDetailMap中的第一个key
+            if note_detail_map:
+                first_note_id = list(note_detail_map.keys())[0]
+            else:
+                print("未找到笔记ID")
+                return None
+
+        # 获取笔记详情
+        note_detail = note_detail_map.get(first_note_id, {})
+        note_info = note_detail.get('note', {})
+
+        if not note_info:
+            print("未找到笔记信息")
+            return None
+
+        # 只提取需要的字段
+        extracted_data = {
+            'title': note_info.get('title'),
+            'desc': note_info.get('desc'),
+            'images': [],
+            'videos': [],
+            'topics': []
+        }
+
+        # 提取图片信息
+        image_list = note_info.get('imageList', [])
+        for img in image_list:
+            image_data = {
+                'url': img.get('urlDefault') or img.get('url'),
+                'urlPre': img.get('urlPre'),
+                'width': img.get('width'),
+                'height': img.get('height'),
+            }
+            extracted_data['images'].append(image_data)
+
+        # 提取视频信息（如果存在）
+        video_info = note_info.get('video', {})
+        if video_info:
+            video_data = {}
+
+            # 尝试提取视频URL
+            media = video_info.get('media', {})
+            if media:
+                stream = media.get('stream', {})
+                if stream:
+                    hls = stream.get('hls', {})
+                    if hls:
+                        video_data['url'] = hls.get('masterUrl') or hls.get('url')
+                # 如果没有hls，尝试其他字段
+                if not video_data.get('url'):
+                    video_data['url'] = media.get('url') or media.get('videoUrl')
+
+            # 提取视频封面
+            if video_info.get('cover'):
+                video_data['cover'] = video_info.get('cover')
+
+            # 提取视频时长
+            if video_info.get('time'):
+                video_data['time'] = video_info.get('time')
+
+            if video_data.get('url'):
+                extracted_data['videos'].append(video_data)
+
+        # 提取话题信息
+        # 话题可能在多个位置，尝试不同的字段名
+        topic_list = note_info.get('topicList', []) or note_info.get('tagList', []) or note_info.get('hashtagList', [])
+        if topic_list:
+            for topic in topic_list:
+                topic_data = {
+                    'name': topic.get('name') or topic.get('title') or topic.get('tagName'),
+                    'id': topic.get('id') or topic.get('topicId') or topic.get('tagId'),
+                }
+                if topic_data.get('name'):
+                    extracted_data['topics'].append(topic_data)
+
+        # 如果描述中包含话题（#话题#格式），也提取出来
+        desc = note_info.get('desc', '')
+        if desc:
+            # 使用正则表达式提取 #话题# 格式
+            topic_pattern = r'#([^#]+)#'
+            matches = re.findall(topic_pattern, desc)
+            for match in matches:
+                # 避免重复添加
+                if not any(t.get('name') == match for t in extracted_data['topics']):
+                    extracted_data['topics'].append({'name': match})
+
+        return extracted_data
+
+    except Exception as e:
+        print(f"提取笔记数据时出错：{e}")
+        import traceback
+        traceback.print_exc()
+        return None
+
+
+def print_note_data(note_data):
+    """
+    格式化打印笔记数据
+    
+    Args:
+        note_data: 笔记数据字典
+    """
+    if not note_data:
+        print("没有可显示的数据")
+        return
+
+    print("=" * 60)
+    print("笔记信息")
+    print("=" * 60)
+    print(f"标题: {note_data.get('title')}")
+    print()
+
+    print("描述:")
+    desc = note_data.get('desc', '')
+    if desc:
+        print(desc)
+
+    print("图片列表:")
+    images = note_data.get('images', [])
+    print(f"  共 {len(images)} 张图片")
+    print(images)
+
+    print("视频列表:")
+    videos = note_data.get('videos', [])
+    print(f"  共 {len(videos)} 个视频")
+    print(videos)
+
+    print("话题列表:")
+    topics = note_data.get('topics', [])
+    print(f"  共 {len(topics)} 个话题")
+    print(topics)
+
+
+if __name__ == '__main__':
+    # 解析HTML文件
+    print("正在解析HTML文件...")
+    note_data = parse_html_file('1.html')
+
+    if note_data:
+        # 保存为JSON文件
+        with open('note_data.json', 'w', encoding='utf-8') as f:
+            json.dump(note_data, f, ensure_ascii=False, indent=2)
+        print("数据已保存到 note_data.json")
+        print()
+
+        # 打印数据（尝试处理编码问题）
+        try:
+            print_note_data(note_data)
+        except Exception as e:
+            print(f"打印数据时出错（但数据已保存到JSON文件）: {e}")
+            print("请查看 note_data.json 文件获取完整数据")
+    else:
+        print("解析失败，请检查HTML文件")

test.py

@@ -0,0 +1,14 @@
+from urllib.parse import urlparse
+import os
+
+url = "https://sns-video-hw.xhscdn.com/stream/110/258/01e6cd08be6e36ad010370019190eceaac_258.mp4"
+
+# 解析URL
+parsed_url = urlparse(url)
+# 获取路径部分
+path = parsed_url.path
+# 从路径中提取文件名
+filename = os.path.basename(path)
+
+print(f"完整路径: {path}")
+print(f"文件名: {filename}")

user/user_data/Default/BookmarkMergedSurfaceOrdering

@@ -0,0 +1,2 @@
+{
+}

user/user_data/Default/BrowsingTopicsState

@@ -0,0 +1,12 @@
+{
+   "epochs": [ {
+      "calculation_time": "13412845270589830",
+      "config_version": 0,
+      "model_version": "0",
+      "padded_top_topics_start_index": 0,
+      "taxonomy_version": 0,
+      "top_topics_and_observing_domains": [  ]
+   } ],
+   "hex_encoded_hmac_key": "434BF7DBD7DA573B45E0A11AD9045A61B6221D14AE2F9A341E2FEF659AF071F6",
+   "next_scheduled_calculation_time": "13413450070589860"
+}