>\n +get(key)* 获取缓存\n +set(key, value, expire)* 设置缓存\n +keys(pattern)* 获取所有键\n }\n\n class ExpiringLocalCache {\n -_cache: Dict\n -_expire_times: Dict\n +get(key)\n +set(key, value, expire_time)\n +keys(pattern)\n -_is_expired(key)\n }\n\n class RedisCache {\n -_client: Redis\n +get(key)\n +set(key, value, expire_time)\n +keys(pattern)\n }\n\n class CacheFactory {\n +create_cache(type) AbstractCache\n }\n\n AbstractCache <|-- ExpiringLocalCache\n AbstractCache <|-- RedisCache\n CacheFactory --> AbstractCache\n```\n\n---\n\n## 7. 数据模型\n\n### 7.1 ORM模型关系\n\n```mermaid\nerDiagram\n DouyinAweme {\n int id PK\n string aweme_id UK\n string aweme_type\n string title\n string desc\n int create_time\n int liked_count\n int collected_count\n int comment_count\n int share_count\n string user_id FK\n datetime add_ts\n datetime last_modify_ts\n }\n\n DouyinAwemeComment {\n int id PK\n string comment_id UK\n string aweme_id FK\n string content\n int create_time\n int sub_comment_count\n string user_id\n datetime add_ts\n datetime last_modify_ts\n }\n\n DyCreator {\n int id PK\n string user_id UK\n string nickname\n string avatar\n string desc\n int follower_count\n int total_favorited\n datetime add_ts\n datetime last_modify_ts\n }\n\n DouyinAweme ||--o{ DouyinAwemeComment : \"has\"\n DyCreator ||--o{ DouyinAweme : \"creates\"\n```\n\n### 7.2 各平台数据表\n\n| 平台 | 内容表 | 评论表 | 创作者表 |\n|------|--------|--------|---------|\n| 抖音 | DouyinAweme | DouyinAwemeComment | DyCreator |\n| 小红书 | XHSNote | XHSNoteComment | XHSCreator |\n| 快手 | KuaishouVideo | KuaishouVideoComment | KsCreator |\n| B站 | BilibiliVideo | BilibiliVideoComment | BilibiliUpInfo |\n| 微博 | WeiboNote | WeiboNoteComment | WeiboCreator |\n| 贴吧 | TiebaNote | TiebaNoteComment | - |\n| 知乎 | ZhihuContent | ZhihuContentComment | ZhihuCreator |\n\n---\n\n## 8. 配置系统\n\n### 8.1 核心配置项\n\n```python\n# config/base_config.py\n\n# 平台选择\nPLATFORM = \"xhs\" # xhs, dy, ks, bili, wb, tieba, zhihu\n\n# 登录配置\nLOGIN_TYPE = \"qrcode\" # qrcode, phone, cookie\nSAVE_LOGIN_STATE = True\n\n# 爬虫配置\nCRAWLER_TYPE = \"search\" # search, detail, creator\nKEYWORDS = \"编程副业,编程兼职\"\nCRAWLER_MAX_NOTES_COUNT = 15\nMAX_CONCURRENCY_NUM = 1\n\n# 评论配置\nENABLE_GET_COMMENTS = True\nENABLE_GET_SUB_COMMENTS = False\nCRAWLER_MAX_COMMENTS_COUNT_SINGLENOTES = 10\n\n# 浏览器配置\nHEADLESS = False\nENABLE_CDP_MODE = True\nCDP_DEBUG_PORT = 9222\n\n# 代理配置\nENABLE_IP_PROXY = False\nIP_PROXY_PROVIDER = \"kuaidaili\"\nIP_PROXY_POOL_COUNT = 2\n\n# 存储配置\nSAVE_DATA_OPTION = \"jsonl\" # csv, db, json, jsonl, sqlite, mongodb, excel, postgres\n```\n\n### 8.2 数据库配置\n\n```python\n# config/db_config.py\n\n# MySQL\nMYSQL_DB_HOST = \"localhost\"\nMYSQL_DB_PORT = 3306\nMYSQL_DB_NAME = \"media_crawler\"\n\n# Redis\nREDIS_DB_HOST = \"127.0.0.1\"\nREDIS_DB_PORT = 6379\n\n# MongoDB\nMONGODB_HOST = \"localhost\"\nMONGODB_PORT = 27017\n\n# SQLite\nSQLITE_DB_PATH = \"database/sqlite_tables.db\"\n```\n\n---\n\n## 9. 工具模块\n\n### 9.1 工具函数概览\n\n| 模块 | 文件 | 主要功能 |\n|------|------|---------|\n| 应用运行器 | `app_runner.py` | 信号处理、优雅退出、清理管理 |\n| 浏览器启动 | `browser_launcher.py` | 检测浏览器路径、启动浏览器进程 |\n| CDP管理 | `cdp_browser.py` | CDP连接、浏览器上下文管理 |\n| 爬虫工具 | `crawler_util.py` | 二维码识别、验证码处理、User-Agent |\n| 文件写入 | `async_file_writer.py` | 异步CSV/JSON写入、词云生成 |\n| 滑块验证 | `slider_util.py` | 滑动验证码破解 |\n| 时间工具 | `time_util.py` | 时间戳转换、日期处理 |\n\n### 9.2 应用运行管理\n\n```mermaid\nflowchart TB\n Start([程序启动]) --> Run[\"run(app_main, app_cleanup)\"]\n Run --> Main[\"执行 app_main()\"]\n Main --> Running{运行中}\n\n Running -->|正常完成| Cleanup1[\"执行 app_cleanup()\"]\n Running -->|SIGINT/SIGTERM| Signal[\"捕获信号\"]\n\n Signal --> First{第一次信号?}\n First -->|是| Cleanup2[\"启动清理流程\"]\n First -->|否| Force[\"强制退出\"]\n\n Cleanup1 & Cleanup2 --> Cancel[\"取消其他任务\"]\n Cancel --> Wait[\"等待任务完成 tag or is directly JSON)\n try:\n # Try to extract JSON from page\n json_text = await self.playwright_page.evaluate(\"() => document.body.innerText\")\n result = json.loads(json_text)\n utils.logger.info(f\"[BaiduTieBaClient.get_notes_by_creator] Successfully retrieved creator post data\")\n return result\n except json.JSONDecodeError as e:\n utils.logger.error(f\"[BaiduTieBaClient.get_notes_by_creator] JSON parsing failed: {e}\")\n utils.logger.error(f\"[BaiduTieBaClient.get_notes_by_creator] Page content: {page_content[:500]}\")\n raise Exception(f\"Failed to parse JSON from creator notes page: {e}\")\n\n except Exception as e:\n utils.logger.error(f\"[BaiduTieBaClient.get_notes_by_creator] Failed to get creator post list: {e}\")\n raise\n\n async def get_all_notes_by_creator_user_name(\n self,\n user_name: str,\n crawl_interval: float = 1.0,\n callback: Optional[Callable] = None,\n max_note_count: int = 0,\n creator_page_html_content: str = None,\n ) -> List[TiebaNote]:\n \"\"\"\n Get all creator posts by creator username\n Args:\n user_name: Creator username\n crawl_interval: Crawl delay interval in seconds\n callback: Callback function after one post crawl completes, an awaitable function\n max_note_count: Maximum number of posts to retrieve, if 0 then get all\n creator_page_html_content: Creator homepage HTML content\n\n Returns:\n\n \"\"\"\n # Baidu Tieba is special, the first 10 posts are directly displayed on the homepage and need special handling, cannot be obtained through API\n result: List[TiebaNote] = []\n if creator_page_html_content:\n thread_id_list = (self._page_extractor.extract_tieba_thread_id_list_from_creator_page(creator_page_html_content))\n utils.logger.info(f\"[BaiduTieBaClient.get_all_notes_by_creator] got user_name:{user_name} thread_id_list len : {len(thread_id_list)}\")\n note_detail_task = [self.get_note_by_id(thread_id) for thread_id in thread_id_list]\n notes = await asyncio.gather(*note_detail_task)\n if callback:\n await callback(notes)\n result.extend(notes)\n\n notes_has_more = 1\n page_number = 1\n page_per_count = 20\n total_get_count = 0\n while notes_has_more == 1 and (max_note_count == 0 or total_get_count < max_note_count):\n notes_res = await self.get_notes_by_creator(user_name, page_number)\n if not notes_res or notes_res.get(\"no\") != 0:\n utils.logger.error(f\"[WeiboClient.get_notes_by_creator] got user_name:{user_name} notes failed, notes_res: {notes_res}\")\n break\n notes_data = notes_res.get(\"data\")\n notes_has_more = notes_data.get(\"has_more\")\n notes = notes_data[\"thread_list\"]\n utils.logger.info(f\"[WeiboClient.get_all_notes_by_creator] got user_name:{user_name} notes len : {len(notes)}\")\n\n note_detail_task = [self.get_note_by_id(note['thread_id']) for note in notes]\n notes = await asyncio.gather(*note_detail_task)\n if callback:\n await callback(notes)\n await asyncio.sleep(crawl_interval)\n result.extend(notes)\n page_number += 1\n total_get_count += page_per_count\n return result\n"
},
{
"path": "media_platform/tieba/core.py",
"content": "# -*- coding: utf-8 -*-\n# Copyright (c) 2025 relakkes@gmail.com\n#\n# This file is part of MediaCrawler project.\n# Repository: https://github.com/NanmiCoder/MediaCrawler/blob/main/media_platform/tieba/core.py\n# GitHub: https://github.com/NanmiCoder\n# Licensed under NON-COMMERCIAL LEARNING LICENSE 1.1\n#\n\n# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：\n# 1. 不得用于任何商业用途。\n# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。\n# 3. 不得进行大规模爬取或对平台造成运营干扰。\n# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。\n# 5. 不得用于任何非法或不当的用途。\n#\n# 详细许可条款请参阅项目根目录下的LICENSE文件。\n# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。\n\n\nimport asyncio\nimport os\nfrom asyncio import Task\nfrom typing import Dict, List, Optional, Tuple\n\nfrom playwright.async_api import (\n BrowserContext,\n BrowserType,\n Page,\n Playwright,\n async_playwright,\n)\n\nimport config\nfrom base.base_crawler import AbstractCrawler\nfrom model.m_baidu_tieba import TiebaCreator, TiebaNote\nfrom proxy.proxy_ip_pool import IpInfoModel, ProxyIpPool, create_ip_pool\nfrom store import tieba as tieba_store\nfrom tools import utils\nfrom tools.cdp_browser import CDPBrowserManager\nfrom var import crawler_type_var, source_keyword_var\n\nfrom .client import BaiduTieBaClient\nfrom .field import SearchNoteType, SearchSortType\nfrom .help import TieBaExtractor\nfrom .login import BaiduTieBaLogin\n\n\nclass TieBaCrawler(AbstractCrawler):\n context_page: Page\n tieba_client: BaiduTieBaClient\n browser_context: BrowserContext\n cdp_manager: Optional[CDPBrowserManager]\n\n def __init__(self) -> None:\n self.index_url = \"https://tieba.baidu.com\"\n self.user_agent = utils.get_user_agent()\n self._page_extractor = TieBaExtractor()\n self.cdp_manager = None\n\n async def start(self) -> None:\n \"\"\"\n Start the crawler\n Returns:\n\n \"\"\"\n playwright_proxy_format, httpx_proxy_format = None, None\n if config.ENABLE_IP_PROXY:\n utils.logger.info(\n \"[BaiduTieBaCrawler.start] Begin create ip proxy pool ...\"\n )\n ip_proxy_pool = await create_ip_pool(\n config.IP_PROXY_POOL_COUNT, enable_validate_ip=True\n )\n ip_proxy_info: IpInfoModel = await ip_proxy_pool.get_proxy()\n playwright_proxy_format, httpx_proxy_format = utils.format_proxy_info(ip_proxy_info)\n utils.logger.info(\n f\"[BaiduTieBaCrawler.start] Init default ip proxy, value: {httpx_proxy_format}\"\n )\n\n async with async_playwright() as playwright:\n # Choose startup mode based on configuration\n if config.ENABLE_CDP_MODE:\n utils.logger.info(\"[BaiduTieBaCrawler] Launching browser in CDP mode\")\n self.browser_context = await self.launch_browser_with_cdp(\n playwright,\n playwright_proxy_format,\n self.user_agent,\n headless=config.CDP_HEADLESS,\n )\n else:\n utils.logger.info(\"[BaiduTieBaCrawler] Launching browser in standard mode\")\n # Launch a browser context.\n chromium = playwright.chromium\n self.browser_context = await self.launch_browser(\n chromium,\n playwright_proxy_format,\n self.user_agent,\n headless=config.HEADLESS,\n )\n\n # Inject anti-detection scripts - for Baidu's special detection\n await self._inject_anti_detection_scripts()\n\n self.context_page = await self.browser_context.new_page()\n\n # First visit Baidu homepage, then click Tieba link to avoid triggering security verification\n await self._navigate_to_tieba_via_baidu()\n\n # Create a client to interact with the baidutieba website.\n self.tieba_client = await self.create_tieba_client(\n httpx_proxy_format,\n ip_proxy_pool if config.ENABLE_IP_PROXY else None\n )\n\n # Check login status and perform login if necessary\n if not await self.tieba_client.pong(browser_context=self.browser_context):\n login_obj = BaiduTieBaLogin(\n login_type=config.LOGIN_TYPE,\n login_phone=\"\", # your phone number\n browser_context=self.browser_context,\n context_page=self.context_page,\n cookie_str=config.COOKIES,\n )\n await login_obj.begin()\n await self.tieba_client.update_cookies(browser_context=self.browser_context)\n\n crawler_type_var.set(config.CRAWLER_TYPE)\n if config.CRAWLER_TYPE == \"search\":\n # Search for notes and retrieve their comment information.\n await self.search()\n await self.get_specified_tieba_notes()\n elif config.CRAWLER_TYPE == \"detail\":\n # Get the information and comments of the specified post\n await self.get_specified_notes()\n elif config.CRAWLER_TYPE == \"creator\":\n # Get creator's information and their notes and comments\n await self.get_creators_and_notes()\n else:\n pass\n\n utils.logger.info(\"[BaiduTieBaCrawler.start] Tieba Crawler finished ...\")\n\n async def search(self) -> None:\n \"\"\"\n Search for notes and retrieve their comment information.\n Returns:\n\n \"\"\"\n utils.logger.info(\n \"[BaiduTieBaCrawler.search] Begin search baidu tieba keywords\"\n )\n tieba_limit_count = 10 # tieba limit page fixed value\n if config.CRAWLER_MAX_NOTES_COUNT < tieba_limit_count:\n config.CRAWLER_MAX_NOTES_COUNT = tieba_limit_count\n start_page = config.START_PAGE\n for keyword in config.KEYWORDS.split(\",\"):\n source_keyword_var.set(keyword)\n utils.logger.info(\n f\"[BaiduTieBaCrawler.search] Current search keyword: {keyword}\"\n )\n page = 1\n while (\n page - start_page + 1\n ) * tieba_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:\n if page < start_page:\n utils.logger.info(f\"[BaiduTieBaCrawler.search] Skip page {page}\")\n page += 1\n continue\n try:\n utils.logger.info(\n f\"[BaiduTieBaCrawler.search] search tieba keyword: {keyword}, page: {page}\"\n )\n notes_list: List[TiebaNote] = (\n await self.tieba_client.get_notes_by_keyword(\n keyword=keyword,\n page=page,\n page_size=tieba_limit_count,\n sort=SearchSortType.TIME_DESC,\n note_type=SearchNoteType.FIXED_THREAD,\n )\n )\n if not notes_list:\n utils.logger.info(\n f\"[BaiduTieBaCrawler.search] Search note list is empty\"\n )\n break\n utils.logger.info(\n f\"[BaiduTieBaCrawler.search] Note list len: {len(notes_list)}\"\n )\n await self.get_specified_notes(\n note_id_list=[note_detail.note_id for note_detail in notes_list]\n )\n\n # Sleep after page navigation\n await asyncio.sleep(config.CRAWLER_MAX_SLEEP_SEC)\n utils.logger.info(f\"[TieBaCrawler.search] Sleeping for {config.CRAWLER_MAX_SLEEP_SEC} seconds after page {page}\")\n\n page += 1\n except Exception as ex:\n utils.logger.error(\n f\"[BaiduTieBaCrawler.search] Search keywords error, current page: {page}, current keyword: {keyword}, err: {ex}\"\n )\n break\n\n async def get_specified_tieba_notes(self):\n \"\"\"\n Get the information and comments of the specified post by tieba name\n Returns:\n\n \"\"\"\n tieba_limit_count = 50\n if config.CRAWLER_MAX_NOTES_COUNT < tieba_limit_count:\n config.CRAWLER_MAX_NOTES_COUNT = tieba_limit_count\n for tieba_name in config.TIEBA_NAME_LIST:\n utils.logger.info(\n f\"[BaiduTieBaCrawler.get_specified_tieba_notes] Begin get tieba name: {tieba_name}\"\n )\n page_number = 0\n while page_number <= config.CRAWLER_MAX_NOTES_COUNT:\n note_list: List[TiebaNote] = (\n await self.tieba_client.get_notes_by_tieba_name(\n tieba_name=tieba_name, page_num=page_number\n )\n )\n if not note_list:\n utils.logger.info(\n f\"[BaiduTieBaCrawler.get_specified_tieba_notes] Get note list is empty\"\n )\n break\n\n utils.logger.info(\n f\"[BaiduTieBaCrawler.get_specified_tieba_notes] tieba name: {tieba_name} note list len: {len(note_list)}\"\n )\n await self.get_specified_notes([note.note_id for note in note_list])\n\n # Sleep after processing notes\n await asyncio.sleep(config.CRAWLER_MAX_SLEEP_SEC)\n utils.logger.info(f\"[TieBaCrawler.get_specified_tieba_notes] Sleeping for {config.CRAWLER_MAX_SLEEP_SEC} seconds after processing notes from page {page_number}\")\n\n page_number += tieba_limit_count\n\n async def get_specified_notes(\n self, note_id_list: List[str] = config.TIEBA_SPECIFIED_ID_LIST\n ):\n \"\"\"\n Get the information and comments of the specified post\n Args:\n note_id_list:\n\n Returns:\n\n \"\"\"\n semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)\n task_list = [\n self.get_note_detail_async_task(note_id=note_id, semaphore=semaphore)\n for note_id in note_id_list\n ]\n note_details = await asyncio.gather(*task_list)\n note_details_model: List[TiebaNote] = []\n for note_detail in note_details:\n if note_detail is not None:\n note_details_model.append(note_detail)\n await tieba_store.update_tieba_note(note_detail)\n await self.batch_get_note_comments(note_details_model)\n\n async def get_note_detail_async_task(\n self, note_id: str, semaphore: asyncio.Semaphore\n ) -> Optional[TiebaNote]:\n \"\"\"\n Get note detail\n Args:\n note_id: baidu tieba note id\n semaphore: asyncio semaphore\n\n Returns:\n\n \"\"\"\n async with semaphore:\n try:\n utils.logger.info(\n f\"[BaiduTieBaCrawler.get_note_detail] Begin get note detail, note_id: {note_id}\"\n )\n note_detail: TiebaNote = await self.tieba_client.get_note_by_id(note_id)\n\n # Sleep after fetching note details\n await asyncio.sleep(config.CRAWLER_MAX_SLEEP_SEC)\n utils.logger.info(f\"[TieBaCrawler.get_note_detail_async_task] Sleeping for {config.CRAWLER_MAX_SLEEP_SEC} seconds after fetching note details {note_id}\")\n\n if not note_detail:\n utils.logger.error(\n f\"[BaiduTieBaCrawler.get_note_detail] Get note detail error, note_id: {note_id}\"\n )\n return None\n return note_detail\n except Exception as ex:\n utils.logger.error(\n f\"[BaiduTieBaCrawler.get_note_detail] Get note detail error: {ex}\"\n )\n return None\n except KeyError as ex:\n utils.logger.error(\n f\"[BaiduTieBaCrawler.get_note_detail] have not fund note detail note_id:{note_id}, err: {ex}\"\n )\n return None\n\n async def batch_get_note_comments(self, note_detail_list: List[TiebaNote]):\n \"\"\"\n Batch get note comments\n Args:\n note_detail_list:\n\n Returns:\n\n \"\"\"\n if not config.ENABLE_GET_COMMENTS:\n return\n\n semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)\n task_list: List[Task] = []\n for note_detail in note_detail_list:\n task = asyncio.create_task(\n self.get_comments_async_task(note_detail, semaphore),\n name=note_detail.note_id,\n )\n task_list.append(task)\n await asyncio.gather(*task_list)\n\n async def get_comments_async_task(\n self, note_detail: TiebaNote, semaphore: asyncio.Semaphore\n ):\n \"\"\"\n Get comments async task\n Args:\n note_detail:\n semaphore:\n\n Returns:\n\n \"\"\"\n async with semaphore:\n utils.logger.info(\n f\"[BaiduTieBaCrawler.get_comments] Begin get note id comments {note_detail.note_id}\"\n )\n\n # Sleep before fetching comments\n await asyncio.sleep(config.CRAWLER_MAX_SLEEP_SEC)\n utils.logger.info(f\"[TieBaCrawler.get_comments_async_task] Sleeping for {config.CRAWLER_MAX_SLEEP_SEC} seconds before fetching comments for note {note_detail.note_id}\")\n\n await self.tieba_client.get_note_all_comments(\n note_detail=note_detail,\n crawl_interval=config.CRAWLER_MAX_SLEEP_SEC,\n callback=tieba_store.batch_update_tieba_note_comments,\n max_count=config.CRAWLER_MAX_COMMENTS_COUNT_SINGLENOTES,\n )\n\n async def get_creators_and_notes(self) -> None:\n \"\"\"\n Get creator's information and their notes and comments\n Returns:\n\n \"\"\"\n utils.logger.info(\n \"[WeiboCrawler.get_creators_and_notes] Begin get weibo creators\"\n )\n for creator_url in config.TIEBA_CREATOR_URL_LIST:\n creator_page_html_content = await self.tieba_client.get_creator_info_by_url(\n creator_url=creator_url\n )\n creator_info: TiebaCreator = self._page_extractor.extract_creator_info(\n creator_page_html_content\n )\n if creator_info:\n utils.logger.info(\n f\"[WeiboCrawler.get_creators_and_notes] creator info: {creator_info}\"\n )\n if not creator_info:\n raise Exception(\"Get creator info error\")\n\n await tieba_store.save_creator(user_info=creator_info)\n\n # Get all note information of the creator\n all_notes_list = (\n await self.tieba_client.get_all_notes_by_creator_user_name(\n user_name=creator_info.user_name,\n crawl_interval=0,\n callback=tieba_store.batch_update_tieba_notes,\n max_note_count=config.CRAWLER_MAX_NOTES_COUNT,\n creator_page_html_content=creator_page_html_content,\n )\n )\n\n await self.batch_get_note_comments(all_notes_list)\n\n else:\n utils.logger.error(\n f\"[WeiboCrawler.get_creators_and_notes] get creator info error, creator_url:{creator_url}\"\n )\n\n async def _navigate_to_tieba_via_baidu(self):\n \"\"\"\n Simulate real user access path:\n 1. First visit Baidu homepage (https://www.baidu.com/)\n 2. Wait for page to load\n 3. Click \"Tieba\" link in top navigation bar\n 4. Jump to Tieba homepage\n\n This avoids triggering Baidu's security verification\n \"\"\"\n utils.logger.info(\"[TieBaCrawler] Simulating real user access path...\")\n\n try:\n # Step 1: Visit Baidu homepage\n utils.logger.info(\"[TieBaCrawler] Step 1: Visiting Baidu homepage https://www.baidu.com/\")\n await self.context_page.goto(\"https://www.baidu.com/\", wait_until=\"domcontentloaded\")\n\n # Step 2: Wait for page loading, using delay setting from config file\n utils.logger.info(f\"[TieBaCrawler] Step 2: Waiting {config.CRAWLER_MAX_SLEEP_SEC} seconds to simulate user browsing...\")\n await asyncio.sleep(config.CRAWLER_MAX_SLEEP_SEC)\n\n # Step 3: Find and click \"Tieba\" link\n utils.logger.info(\"[TieBaCrawler] Step 3: Finding and clicking 'Tieba' link...\")\n\n # Try multiple selectors to ensure finding the Tieba link\n tieba_selectors = [\n 'a[href=\"http://tieba.baidu.com/\"]',\n 'a[href=\"https://tieba.baidu.com/\"]',\n 'a.mnav:has-text(\"贴吧\")',\n 'text=贴吧',\n ]\n\n tieba_link = None\n for selector in tieba_selectors:\n try:\n tieba_link = await self.context_page.wait_for_selector(selector, timeout=5000)\n if tieba_link:\n utils.logger.info(f\"[TieBaCrawler] Found Tieba link (selector: {selector})\")\n break\n except Exception:\n continue\n\n if not tieba_link:\n utils.logger.warning(\"[TieBaCrawler] Tieba link not found, directly accessing Tieba homepage\")\n await self.context_page.goto(self.index_url, wait_until=\"domcontentloaded\")\n return\n\n # Step 4: Click Tieba link (check if it will open in a new tab)\n utils.logger.info(\"[TieBaCrawler] Step 4: Clicking Tieba link...\")\n\n # Check link's target attribute\n target_attr = await tieba_link.get_attribute(\"target\")\n utils.logger.info(f\"[TieBaCrawler] Link target attribute: {target_attr}\")\n\n if target_attr == \"_blank\":\n # If it's a new tab, need to wait for new page and switch\n utils.logger.info(\"[TieBaCrawler] Link will open in new tab, waiting for new page...\")\n\n async with self.browser_context.expect_page() as new_page_info:\n await tieba_link.click()\n\n # Get newly opened page\n new_page = await new_page_info.value\n await new_page.wait_for_load_state(\"domcontentloaded\")\n\n # Close old Baidu homepage\n await self.context_page.close()\n\n # Switch to new Tieba page\n self.context_page = new_page\n utils.logger.info(\"[TieBaCrawler] Successfully switched to new tab (Tieba page)\")\n else:\n # If it's same tab navigation, wait for navigation normally\n utils.logger.info(\"[TieBaCrawler] Link navigates in current tab...\")\n async with self.context_page.expect_navigation(wait_until=\"domcontentloaded\"):\n await tieba_link.click()\n\n # Step 5: Wait for page to stabilize, using delay setting from config file\n utils.logger.info(f\"[TieBaCrawler] Step 5: Page loaded, waiting {config.CRAWLER_MAX_SLEEP_SEC} seconds...\")\n await asyncio.sleep(config.CRAWLER_MAX_SLEEP_SEC)\n\n current_url = self.context_page.url\n utils.logger.info(f\"[TieBaCrawler] Successfully entered Tieba via Baidu homepage! Current URL: {current_url}\")\n\n except Exception as e:\n utils.logger.error(f\"[TieBaCrawler] Failed to access Tieba via Baidu homepage: {e}\")\n utils.logger.info(\"[TieBaCrawler] Fallback: directly accessing Tieba homepage\")\n await self.context_page.goto(self.index_url, wait_until=\"domcontentloaded\")\n\n async def _inject_anti_detection_scripts(self):\n \"\"\"\n Inject anti-detection JavaScript scripts\n For Baidu Tieba's special detection mechanism\n \"\"\"\n utils.logger.info(\"[TieBaCrawler] Injecting anti-detection scripts...\")\n\n # Lightweight anti-detection script, only covering key detection points\n anti_detection_js = \"\"\"\n // Override navigator.webdriver\n Object.defineProperty(navigator, 'webdriver', {\n get: () => undefined,\n configurable: true\n });\n\n // Override window.navigator.chrome\n if (!window.navigator.chrome) {\n window.navigator.chrome = {\n runtime: {},\n loadTimes: function() {},\n csi: function() {},\n app: {}\n };\n }\n\n // Override Permissions API\n const originalQuery = window.navigator.permissions.query;\n window.navigator.permissions.query = (parameters) => (\n parameters.name === 'notifications' ?\n Promise.resolve({ state: Notification.permission }) :\n originalQuery(parameters)\n );\n\n // Override plugins length (make it look like there are plugins)\n Object.defineProperty(navigator, 'plugins', {\n get: () => [1, 2, 3, 4, 5],\n configurable: true\n });\n\n // Override languages\n Object.defineProperty(navigator, 'languages', {\n get: () => ['zh-CN', 'zh', 'en'],\n configurable: true\n });\n\n // Remove window.cdc_ and other ChromeDriver remnants\n delete window.cdc_adoQpoasnfa76pfcZLmcfl_Array;\n delete window.cdc_adoQpoasnfa76pfcZLmcfl_Promise;\n delete window.cdc_adoQpoasnfa76pfcZLmcfl_Symbol;\n\n console.log('[Anti-Detection] Scripts injected successfully');\n \"\"\"\n\n await self.browser_context.add_init_script(anti_detection_js)\n utils.logger.info(\"[TieBaCrawler] Anti-detection scripts injected\")\n\n async def create_tieba_client(\n self, httpx_proxy: Optional[str], ip_pool: Optional[ProxyIpPool] = None\n ) -> BaiduTieBaClient:\n \"\"\"\n Create tieba client with real browser User-Agent and complete headers\n Args:\n httpx_proxy: HTTP proxy\n ip_pool: IP proxy pool\n\n Returns:\n BaiduTieBaClient instance\n \"\"\"\n utils.logger.info(\"[TieBaCrawler.create_tieba_client] Begin create tieba API client...\")\n\n # Extract User-Agent from real browser to avoid detection\n user_agent = await self.context_page.evaluate(\"() => navigator.userAgent\")\n utils.logger.info(f\"[TieBaCrawler.create_tieba_client] Extracted User-Agent from browser: {user_agent}\")\n\n cookie_str, cookie_dict = utils.convert_cookies(await self.browser_context.cookies())\n\n # Build complete browser request headers, simulating real browser behavior\n tieba_client = BaiduTieBaClient(\n timeout=10,\n ip_pool=ip_pool,\n default_ip_proxy=httpx_proxy,\n headers={\n \"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\",\n \"Accept-Language\": \"zh-CN,zh;q=0.9\",\n \"Accept-Encoding\": \"gzip, deflate, br\",\n \"Connection\": \"keep-alive\",\n \"User-Agent\": user_agent, # Use real browser UA\n \"Cookie\": cookie_str,\n \"Host\": \"tieba.baidu.com\",\n \"Referer\": \"https://tieba.baidu.com/\",\n \"Sec-Fetch-Dest\": \"document\",\n \"Sec-Fetch-Mode\": \"navigate\",\n \"Sec-Fetch-Site\": \"same-origin\",\n \"Sec-Fetch-User\": \"?1\",\n \"Upgrade-Insecure-Requests\": \"1\",\n \"sec-ch-ua\": '\"Google Chrome\";v=\"141\", \"Not?A_Brand\";v=\"8\", \"Chromium\";v=\"141\"',\n \"sec-ch-ua-mobile\": \"?0\",\n \"sec-ch-ua-platform\": '\"macOS\"',\n },\n playwright_page=self.context_page, # Pass in playwright page object\n )\n return tieba_client\n\n async def launch_browser(\n self,\n chromium: BrowserType,\n playwright_proxy: Optional[Dict],\n user_agent: Optional[str],\n headless: bool = True,\n ) -> BrowserContext:\n \"\"\"\n Launch browser and create browser\n Args:\n chromium:\n playwright_proxy:\n user_agent:\n headless:\n\n Returns:\n\n \"\"\"\n utils.logger.info(\n \"[BaiduTieBaCrawler.launch_browser] Begin create browser context ...\"\n )\n if config.SAVE_LOGIN_STATE:\n # feat issue #14\n # we will save login state to avoid login every time\n user_data_dir = os.path.join(\n os.getcwd(), \"browser_data\", config.USER_DATA_DIR % config.PLATFORM\n ) # type: ignore\n browser_context = await chromium.launch_persistent_context(\n user_data_dir=user_data_dir,\n accept_downloads=True,\n headless=headless,\n proxy=playwright_proxy, # type: ignore\n viewport={\"width\": 1920, \"height\": 1080},\n user_agent=user_agent,\n channel=\"chrome\", # Use system's stable Chrome version\n )\n return browser_context\n else:\n browser = await chromium.launch(headless=headless, proxy=playwright_proxy, channel=\"chrome\") # type: ignore\n browser_context = await browser.new_context(\n viewport={\"width\": 1920, \"height\": 1080}, user_agent=user_agent\n )\n return browser_context\n\n async def launch_browser_with_cdp(\n self,\n playwright: Playwright,\n playwright_proxy: Optional[Dict],\n user_agent: Optional[str],\n headless: bool = True,\n ) -> BrowserContext:\n \"\"\"\n Launch browser using CDP mode\n \"\"\"\n try:\n self.cdp_manager = CDPBrowserManager()\n browser_context = await self.cdp_manager.launch_and_connect(\n playwright=playwright,\n playwright_proxy=playwright_proxy,\n user_agent=user_agent,\n headless=headless,\n )\n\n # Display browser information\n browser_info = await self.cdp_manager.get_browser_info()\n utils.logger.info(f\"[TieBaCrawler] CDP browser info: {browser_info}\")\n\n return browser_context\n\n except Exception as e:\n utils.logger.error(f\"[TieBaCrawler] CDP mode launch failed, falling back to standard mode: {e}\")\n # Fall back to standard mode\n chromium = playwright.chromium\n return await self.launch_browser(\n chromium, playwright_proxy, user_agent, headless\n )\n\n async def close(self):\n \"\"\"\n Close browser context\n Returns:\n\n \"\"\"\n # If using CDP mode, need special handling\n if self.cdp_manager:\n await self.cdp_manager.cleanup()\n self.cdp_manager = None\n else:\n await self.browser_context.close()\n utils.logger.info(\"[BaiduTieBaCrawler.close] Browser context closed ...\")\n"
},
{
"path": "media_platform/tieba/field.py",
"content": "# -*- coding: utf-8 -*-\n# Copyright (c) 2025 relakkes@gmail.com\n#\n# This file is part of MediaCrawler project.\n# Repository: https://github.com/NanmiCoder/MediaCrawler/blob/main/media_platform/tieba/field.py\n# GitHub: https://github.com/NanmiCoder\n# Licensed under NON-COMMERCIAL LEARNING LICENSE 1.1\n#\n\n# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：\n# 1. 不得用于任何商业用途。\n# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。\n# 3. 不得进行大规模爬取或对平台造成运营干扰。\n# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。\n# 5. 不得用于任何非法或不当的用途。\n#\n# 详细许可条款请参阅项目根目录下的LICENSE文件。\n# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。\n\n\nfrom enum import Enum\n\n\nclass SearchSortType(Enum):\n \"\"\"search sort type\"\"\"\n # Sort by time in descending order\n TIME_DESC = \"1\"\n # Sort by time in ascending order\n TIME_ASC = \"0\"\n # Sort by relevance\n RELEVANCE_ORDER = \"2\"\n\n\nclass SearchNoteType(Enum):\n # Only view main posts\n MAIN_THREAD = \"1\"\n # Mixed mode (posts + replies)\n FIXED_THREAD = \"0\"\n"
},
{
"path": "media_platform/tieba/help.py",
"content": "# -*- coding: utf-8 -*-\n# Copyright (c) 2025 relakkes@gmail.com\n#\n# This file is part of MediaCrawler project.\n# Repository: https://github.com/NanmiCoder/MediaCrawler/blob/main/media_platform/tieba/help.py\n# GitHub: https://github.com/NanmiCoder\n# Licensed under NON-COMMERCIAL LEARNING LICENSE 1.1\n#\n\n# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：\n# 1. 不得用于任何商业用途。\n# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。\n# 3. 不得进行大规模爬取或对平台造成运营干扰。\n# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。\n# 5. 不得用于任何非法或不当的用途。\n#\n# 详细许可条款请参阅项目根目录下的LICENSE文件。\n# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。\n\n\n# -*- coding: utf-8 -*-\nimport html\nimport json\nimport re\nfrom typing import Dict, List, Tuple\nfrom urllib.parse import parse_qs, unquote\n\nfrom parsel import Selector\n\nfrom constant import baidu_tieba as const\nfrom model.m_baidu_tieba import TiebaComment, TiebaCreator, TiebaNote\nfrom tools import utils\n\nGENDER_MALE = \"sex_male\"\nGENDER_FEMALE = \"sex_female\"\n\n\nclass TieBaExtractor:\n def __init__(self):\n pass\n\n @staticmethod\n def extract_search_note_list(page_content: str) -> List[TiebaNote]:\n \"\"\"\n Extract Tieba post list from keyword search result pages, still missing reply count and reply page data\n Args:\n page_content: HTML string of page content\n\n Returns:\n List of Tieba post objects\n \"\"\"\n xpath_selector = \"//div[@class='s_post']\"\n post_list = Selector(text=page_content).xpath(xpath_selector)\n result: List[TiebaNote] = []\n for post in post_list:\n tieba_note = TiebaNote(note_id=post.xpath(\".//span[@class='p_title']/a/@data-tid\").get(default='').strip(),\n title=post.xpath(\".//span[@class='p_title']/a/text()\").get(default='').strip(),\n desc=post.xpath(\".//div[@class='p_content']/text()\").get(default='').strip(),\n note_url=const.TIEBA_URL + post.xpath(\".//span[@class='p_title']/a/@href\").get(\n default=''),\n user_nickname=post.xpath(\".//a[starts-with(@href, '/home/main')]/font/text()\").get(\n default='').strip(), user_link=const.TIEBA_URL + post.xpath(\n \".//a[starts-with(@href, '/home/main')]/@href\").get(default=''),\n tieba_name=post.xpath(\".//a[@class='p_forum']/font/text()\").get(default='').strip(),\n tieba_link=const.TIEBA_URL + post.xpath(\".//a[@class='p_forum']/@href\").get(\n default=''),\n publish_time=post.xpath(\".//font[@class='p_green p_date']/text()\").get(\n default='').strip(), )\n result.append(tieba_note)\n return result\n\n def extract_tieba_note_list(self, page_content: str) -> List[TiebaNote]:\n \"\"\"\n Extract Tieba post list from Tieba page\n Args:\n page_content: HTML string of page content\n\n Returns:\n List of Tieba post objects\n \"\"\"\n page_content = page_content.replace('
签到排名：今日本吧第0 个签到，
本吧因你更精彩，明天继续来努力！
连续签到：
0 超级会员单次开通12个月以上，赠送连续签到卡3张
网球风云吧 关注： 48,523 贴子： 5,418,043
","isPlus":0,"builderId":1635505954,"post_no":1,"type":"0","comment_num":0,"is_fold":0,"props":null,"post_index":0,"pb_tpoint":null}}\" data-pid=\"150726491368\">
\n
中国队第22金！无悬念！
","isPlus":0,"builderId":1635505954,"post_no":3,"type":"0","comment_num":2,"is_fold":0,"props":null,"post_index":2,"pb_tpoint":null}}\" data-pid=\"150726497321\">
\n \n \n
\n\n
\n \n\n \n \n\n 塔别啦 \n\n \n\n \n \n \n 全后卫冕，太好了
\n \n \n
\n\n
\n \n\n \n \n 月夜暗留香 \n\n \n \n
\n \n \n \n ","isPlus":0,"builderId":1635505954,"post_no":5,"type":"0","comment_num":1,"is_fold":0,"props":null,"post_index":4,"pb_tpoint":null}}\" data-pid=\"150726498817\">
\n \n \n
\n\n
\n \n\n \n \n\n 那就这样吧@ \n\n \n\n \n \n \n 皇后回宫
\n \n \n
\n\n
\n \n\n \n \n\n FO-af962G \n\n \n \n
\n \n \n \n \\u5c45\\u7136\\u4e0d\\u662f8\\u5206","isPlus":0,"builderId":1635505954,"post_no":7,"type":"0","comment_num":16,"is_fold":0,"props":null,"post_index":6,"pb_tpoint":null}}\" data-pid=\"150726500312\">
\n \n \n
\n\n
\n \n\n \n \n\n 美味蟹黄堡 \n\n \n\n \n \n \n 全最后水花那么大
居然不是8分
\n \n \n
\n\n
\n \n\n \n \n\n yangzi0823 \n\n \n\n \n \n \n \n \n \n
\n\n
\n \n\n \n \n\n 奥美丽扬奇科 \n\n \n\n \n \n \n ","isPlus":0,"builderId":1635505954,"post_no":10,"type":"0","comment_num":0,"is_fold":0,"props":null,"post_index":9,"pb_tpoint":null}}\" data-pid=\"150726502752\">
\n \n \n
\n\n
\n \n\n \n \n\n 哥欠独家记忆 \n\n \n\n \n \n \n \n \n \n
\n\n
\n \n\n \n \n\n 水蓝鲸鱼 \n\n \n \n
\n \n \n \n \n \n \n
\n\n
\n \n\n \n \n\n flybiubiu123 \n\n \n \n
\n \n \n \n ","isPlus":0,"builderId":1635505954,"post_no":13,"type":"0","comment_num":1,"is_fold":0,"props":null,"post_index":12,"pb_tpoint":null}}\" data-pid=\"150726503602\">
\n \n \n
\n\n
\n \n\n \n \n\n 好馨就有好蕴🤗 \n\n \n\n \n \n \n 恭喜全后卫冕 也恭喜汐贵妃银牌，汐贵妃挺遗憾的，不管怎么样还是恭喜两位
\n \n \n
\n\n
\n \n\n \n \n\n 芷合 \n\n \n\n \n \n \n \n \n \n
\n\n
\n \n\n \n \n\n Gary星 \n\n \n \n
\n \n \n \n ","isPlus":0,"builderId":1635505954,"post_no":16,"type":"0","comment_num":1,"is_fold":0,"props":null,"post_index":15,"pb_tpoint":null}}\" data-pid=\"150726505659\">
\n \n \n
\n\n
\n \n\n \n \n\n s伊什塔尔 \n\n \n\n \n \n \n \n \n \n
\n\n
\n \n\n \n \n\n AI未来 \n\n \n\n \n \n \n 全后真的是后。。。确实今天有点紧，正常应该在440-450左右。。。
IP属地:上海 17楼 2024-08-06 22:11 \n \n \n
\n\n
\n \n\n \n \n\n gholic \n\n \n\n \n \n \n IP属地:上海 18楼 2024-08-06 22:11 \n \n \n
\n\n
\n \n\n \n \n\n 芷合 \n\n \n\n \n \n \n \n \n \n
\n\n
\n \n\n \n \n\n 左边风依旧肆虐 \n\n \n\n \n \n \n
\n \n \n
\n\n
\n \n\n \n \n\n 方道正也 \n\n \n\n \n \n \n \\u597d\\u96be\\u8fc7\\u54e6","isPlus":0,"builderId":1635505954,"post_no":22,"type":"0","comment_num":12,"is_fold":0,"props":null,"post_index":21,"pb_tpoint":null}}\" data-pid=\"150726508793\">
\n \n \n
\n\n
\n \n\n \n \n\n 京酱肉丝-- \n\n \n\n \n \n \n 陈这个周期是不是压着全，吊打了，结果巴黎还是输了
好难过哦
\n \n \n
\n\n
\n \n\n \n \n\n free抽的就是你 \n\n \n\n \n \n \n \n \n \n
\n\n
\n \n\n \n \n\n 梦里回江 \n\n \n \n
\n \n \n \n \n \n \n
\n\n
\n \n\n \n \n\n AI未来 \n\n \n\n \n \n \n 汐贵妃有点惨。。相比预赛半决赛已经特别好了，今天机会很大的。。。
IP属地:上海 25楼 2024-08-06 22:12 ","isPlus":0,"builderId":1635505954,"post_no":26,"type":"0","comment_num":0,"is_fold":0,"props":null,"post_index":25,"pb_tpoint":null}}\" data-pid=\"150726510608\">
\n \n \n
\n\n
\n \n\n \n \n\n 洛神五五 \n\n \n\n \n \n \n
","isPlus":0,"builderId":1635505954,"post_no":27,"type":"0","comment_num":1,"is_fold":0,"props":null,"post_index":26,"pb_tpoint":null}}\" data-pid=\"150726510641\">
\n \n \n
\n\n
\n \n\n \n \n\n 红黑军团810 \n\n \n \n
\n \n \n \n 心疼陈宇汐一秒
IP属地:安徽 27楼 2024-08-06 22:12 \n \n \n
\n\n
\n \n\n \n \n\n 下次再见123 \n\n \n\n \n \n \n \n \n \n
\n\n
\n \n\n \n \n\n 托管教你做人 \n\n \n \n
\n \n \n \n ","isPlus":0,"builderId":1635505954,"post_no":30,"type":"0","comment_num":3,"is_fold":0,"props":null,"post_index":29,"pb_tpoint":null}}\" data-pid=\"150726510843\">
\n \n \n
\n\n
\n \n\n \n \n\n 巴黎奥运冠军郑钦文 \n\n \n\n \n \n \n 汐贵妃最后神情有点落寞
\n
\n
广告 \n
\n
\n
魔拜
魔蛋
![](\"http://tiebapic.baidu.com/forum/w%3D580/sign=fa4e9202f67eca80120539efa1239712/07d6f7de9c82d15884e06d90c60a19d8bd3e4294.jpg?tbpicau=2024-08-18-05_d05a4e18efd81f49f38ed55275a28c4e\")
![](\"http://tiebapic.baidu.com/forum/w%3D580/sign=81df64294ad79123e0e0947c9d345917/078788bf6c81800a5287bd2ff73533fa838b4794.jpg?tbpicau=2024-08-18-05_bad4bc8570a2a6ca4da65d61a4001daa\")
![\"WebUI](\"docs/static/images/img_8.png\")
\n\n![](\"docs/static/images/tikhub_banner_zh.png\")
\n![\"JetBrains\"](\"https://www.jetbrains.com/company/brand/img/jetbrains_logo.png\"){kind=logo}
\n\n"
},
{
"path": "README_es.md",
"content": "# 🔥 MediaCrawler - Rastreador de Plataformas de Redes Sociales 🕷️\n\n![\"微信赞赏二维码\"](\"./static/images/wechat_pay.jpeg\")
\n ![\"支付宝赞赏二维码\"](\"./static/images/zfb_pay.png\")
\n ![](\"\")
![](\"https://tiebapic.baidu.com/forum/w%3D150%3Bh%3D150%3Bq%3D80%3B/sign=7e925b16f67eca8012053de2a118ffe0/dcc451da81cb39db7a7e9a6396160924ab18304d.jpg?tbpicau=2024-08-18-05_9ba9ed31dffd04ea4c25f289238d4574\")
\n\n\n \n\t\t贴子管理\n\t ![](\\"http:\\/\\/tiebapic.baidu.com\\/forum\\/w%3D580\\/sign=fa4e9202f67eca80120539efa1239712\\/07d6f7de9c82d15884e06d90c60a19d8bd3e4294.jpg?tbpicau=2024-08-18-05_d05a4e18efd81f49f38ed55275a28c4e\\")
![](\\"http:\\/\\/tiebapic.baidu.com\\/forum\\/w%3D580\\/sign=81df64294ad79123e0e0947c9d345917\\/078788bf6c81800a5287bd2ff73533fa838b4794.jpg?tbpicau=2024-08-18-05_bad4bc8570a2a6ca4da65d61a4001daa\\")
","isPlus":0,"builderId":1635505954,"post_no":1,"type":"0","comment_num":0,"is_fold":0,"props":null,"post_index":0,"pb_tpoint":null}}\" data-pid=\"150726491368\"> ![](\"https://gss0.bdstatic.com/6LZ1dD3d1sgCo2Kml5_Y_D3/sys/portrait/item/tb.1.b08d8f12.IR-tbLlZ2GkD6ARA-mfGOA?t=1532192361\")
\n\n \n ![](\\"https:\\/\\/gsp0.baidu.com\\/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK\\/tb\\/editor\\/images\\/client\\/image_emoticon20.png\\")
","isPlus":0,"builderId":1635505954,"post_no":5,"type":"0","comment_num":1,"is_fold":0,"props":null,"post_index":4,"pb_tpoint":null}}\" data-pid=\"150726498817\"> ![](\\"https:\\/\\/gsp0.baidu.com\\/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK\\/tb\\/editor\\/images\\/client\\/image_emoticon17.png\\")
\\u5c45\\u7136\\u4e0d\\u662f8\\u5206","isPlus":0,"builderId":1635505954,"post_no":7,"type":"0","comment_num":16,"is_fold":0,"props":null,"post_index":6,"pb_tpoint":null}}\" data-pid=\"150726500312\"> ![](\"https://gss0.bdstatic.com/6LZ1dD3d1sgCo2Kml5_Y_D3/sys/portrait/item/tb.1.703cbb02.2UdPazbJAeASDvPcBlpe-Q?t=1393996393\")
\n\n \n ![](\"//tb2.bdstatic.com/tb/static-pb/img/loading_69032b0.gif\")
","isPlus":0,"builderId":1635505954,"post_no":10,"type":"0","comment_num":0,"is_fold":0,"props":null,"post_index":9,"pb_tpoint":null}}\" data-pid=\"150726502752\"> ![](\"//tb2.bdstatic.com/tb/static-pb/img/head_80.jpg\")
\n\n \n ![\"\"](\"//tb1.bdstatic.com/tb/cms/PC%E7%AB%AF%E5%BA%95%E9%83%A8%E9%80%9A%E6%A0%8F%E5%BC%B9%E5%B1%821000x120.png\")
![\"\"](\"//tb2.bdstatic.com/tb/static-spage/widget/fixed_bar/images/icon_close_1683259.png\")
![](\"//tb2.bdstatic.com/tb/static-pb/img/jubao_button_4ee5c4f.png\"){kind=icon}
![](\"//tb1.bdstatic.com/tb/cms/nickemoji/3-3.png\")
啦🍓![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/editor/images/client/image_emoticon20.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/editor/images/client/image_emoticon10.png\")
遭不住！~~~！！！！![](\"https://ns-strategy.cdn.bcebos.com/ns-strategy/upload/fc_big_pic/part-00564-1575.jpg\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/editor/images/client/image_emoticon24.png\")
![](\"//tb1.bdstatic.com/tb/cms/nickemoji/1-21.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/editor/images/client/image_emoticon68.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/editor/images/client/image_emoticon66.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/editor/images/client/image_emoticon2.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/editor/images/client/image_emoticon69.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/editor/images/client/image_emoticon22.png\")
![](\"https://tb2.bdstatic.com/tb/editor/images/face/i_f22.png?t=20140803\")
![](\"//tb1.bdstatic.com/tb/cms/nickemoji/4-6.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/editor/images/client/image_emoticon17.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/editor/images/client/image_emoticon25.png\")
![](\"//tb1.bdstatic.com/tb/cms/nickemoji/1-23.png\")
![](\"//tb1.bdstatic.com/tb/cms/nickemoji/3-30.png\")
泽赫拉![](\"//tb1.bdstatic.com/tb/cms/nickemoji/4-21.png\")
![](\"//tb1.bdstatic.com/tb/cms/nickemoji/2-2.png\")
![\"\"](\"https://mediago-static.cdn.bcebos.com/assets/images/header/2.png\")
![\"\"](\"https://s3m.mediav.com/galileo/fd1ffe54d3571462904021756b704864_1920x1080_cover.jpg\")
![\"\"](\"https://mediago-static.cdn.bcebos.com/assets/images/mute.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/editor/images/client/image_emoticon16.png\")
![](\"//tb1.bdstatic.com/tb/cms/nickemoji/4-13.png\")
![\"\"](\"https://mediago-static.cdn.bcebos.com/assets/images/header/1.png\")
![\"\"](\"https://s3m.mediav.com/galileo/1f6eb1fcc2a4b2a882991d59305731d8.jpg\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/editor/images/client/image_emoticon8.png\")
好难过哦![](\"//tb1.bdstatic.com/tb/cms/nickemoji/1-10.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/editor/images/client/image_emoticon9.png\")
![](\"http://tb2.bdstatic.com/tb/static-user/widget/celebrity/img/single_member_100_8a10f9f.png\")
![](\"https://tb1.bdstatic.com/tb/cms/ngmis/adsense/file_1420437480279.jpg\")
\n ![](\"https://tieba-ares.cdn.bcebos.com/mis/2024-8/1722586936824/82195b2e9cf4.gif\")
\n ![](\"//tb2.bdstatic.com/tb/static-props/img/props/worship.png\")
![](\"//tb2.bdstatic.com/tb/static-props/img/props/egg.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/cms/commonsub/editor/images/qw_review/qw_cat_0001.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/cms/commonsub/editor/images/qw_review/qw_cat_0002.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/cms/commonsub/editor/images/qw_review/qw_cat_0003.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/cms/commonsub/editor/images/qw_review/qw_cat_0004.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/cms/commonsub/editor/images/qw_review/qw_cat_0005.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/cms/commonsub/editor/images/qw_review/qw_cat_0006.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/cms/commonsub/editor/images/qw_review/qw_cat_0007.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/cms/commonsub/editor/images/qw_review/qw_cat_0008.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/cms/commonsub/editor/images/qw_review/qw_cat_0009.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/cms/commonsub/editor/images/qw_review/qw_cat_0010.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/cms/commonsub/editor/images/qw_review/qw_cat_0011.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/cms/commonsub/editor/images/qw_review/qw_cat_0012.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/cms/commonsub/editor/images/qw_review/qw_cat_0013.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/cms/commonsub/editor/images/qw_review/qw_cat_0014.png\")
![](\"https://gsp0.baidu.com/5aAHeD3nKhI2p27j8IqW0jdnxx1xbK/tb/cms/commonsub/editor/images/qw_review/qw_cat_0015.png\")
![](\"http://tb2.bdstatic.com/tb/static-common/widget/aside_float_bar/images/loading2_a8a93d0.gif\")
正在加载，请稍后。。。