diff --git a/README.en.md b/README.en.md index 081b3e29c..50f68721c 100644 --- a/README.en.md +++ b/README.en.md @@ -125,7 +125,7 @@ Part of TikHub's source code will be open sourced on Github, and it will sponsor - [iOS shortcut commands to quickly call API](https://apps.apple.com/cn/app/%E5%BF%AB%E6%8D%B7%E6%8C%87%E4%BB%A4/id915249334)Achieve in-app download of watermark-free videos/photo albums - Complete API documentation ([Demo/Demonstration](https://api.douyin.wtf/docs)) - Rich API interface: - - Douyin web version API + - Douyin web version API - [x] Video data analysis - [x] Get user homepage work data @@ -149,7 +149,7 @@ Part of TikHub's source code will be open sourced on Github, and it will sponsor - [x] Extract list work id - [x] Extract live broadcast room number from list - [x] Extract live broadcast room number from list - - TikTok web version API + - TikTok web version API - [x] Video data analysis - [x] Get user homepage work data @@ -171,7 +171,18 @@ Part of TikHub's source code will be open sourced on Github, and it will sponsor - [x] Extract list work id - [x] Get user unique_id - [x] Get list unique_id - + - Bilibili web version API + - [x] Get single video data + - [x] Get user homepage video data + - [x] Get user collection folders + - [x] Gets video data from a collection folder + - [x] Get information of specified user + - [x] Get comprehensive popular video information + - [x] Get comments on the specified video + - [x] Get reply to the specified comment + - [x] Get dynamic information of specified user + - [x] Get information of specified live room + - [x] Get a list of all live areas * * * ## 📦Call the parsing library (obsolete and needs to be updated): diff --git a/README.md b/README.md index 8837abbf3..b03e6a575 100644 --- a/README.md +++ b/README.md @@ -129,13 +129,15 @@ TikHub的部分源代码会开源在Github上，并且会赞助一些开源项 │ └─web │ └─views └─crawlers -├─douyin -│ └─web -├─hybrid -├─tiktok -│ ├─app -│ └─web -└─utils + ├─bilibili + │ └─web + ├─douyin + │ └─web + ├─hybrid + ├─tiktok + │ ├─app + │ └─web + └─utils ``` ## ✨支持功能： @@ -192,7 +194,18 @@ TikHub的部分源代码会开源在Github上，并且会赞助一些开源项 - [x] 提取列表作品id - [x] 获取用户unique_id - [x] 获取列表unique_id - + - 哔哩哔哩网页版API + - [x] 获取单个视频详情信息 + - [x] 获取用户发布视频作品数据 + - [x] 获取用户所有收藏夹信息 + - [x] 获取指定收藏夹内视频数据 + - [x] 获取指定用户的信息 + - [x] 获取综合热门视频信息 + - [x] 获取指定视频的评论 + - [x] 获取视频下指定评论的回复 + - [x] 获取指定用户动态 + - [x] 获取指定直播间信息 + - [x] 获取所有直播分区列表 --- ## 📦调用解析库（已废弃需要更新）: diff --git a/app/api/endpoints/bilibili_web.py b/app/api/endpoints/bilibili_web.py new file mode 100644 index 000000000..e0028522b --- /dev/null +++ b/app/api/endpoints/bilibili_web.py @@ -0,0 +1,498 @@ +from fastapi import APIRouter, Body, Query, Request, HTTPException # 导入FastAPI组件 +from app.api.models.APIResponseModel import ResponseModel, ErrorResponseModel # 导入响应模型 + +from crawlers.bilibili.web.web_crawler import BilibiliWebCrawler # 导入哔哩哔哩web爬虫 + + +router = APIRouter() +BilibiliWebCrawler = BilibiliWebCrawler() + + +# 获取单个视频详情信息 +@router.get("/fetch_one_video", response_model=ResponseModel, summary="获取单个视频详情信息/Get single video data") +async def fetch_one_video(request: Request, + bv_id: str = Query(example="BV1M1421t7hT", description="作品id/Video id")): + """ + # [中文] + ### 用途: + - 获取单个视频详情信息 + ### 参数: + - bv_id: 作品id + ### 返回: + - 视频详情信息 + + # [English] + ### Purpose: + - Get single video data + ### Parameters: + - bv_id: Video id + ### Return: + - Video data + + # [示例/Example] + bv_id = "BV1M1421t7hT" + """ + try: + data = await BilibiliWebCrawler.fetch_one_video(bv_id) + return ResponseModel(code=200, + router=request.url.path, + data=data) + except Exception as e: + status_code = 400 + detail = ErrorResponseModel(code=status_code, + router=request.url.path, + params=dict(request.query_params), + ) + raise HTTPException(status_code=status_code, detail=detail.dict()) + + +# 获取用户发布视频作品数据 +@router.get("/fetch_user_post_videos", response_model=ResponseModel, + summary="获取用户主页作品数据/Get user homepage video data") +async def fetch_user_post_videos(request: Request, + uid: str = Query(example="178360345", description="用户UID"), + pn: int = Query(default=1, description="页码/Page number"),): + """ + # [中文] + ### 用途: + - 获取用户发布的视频数据 + ### 参数: + - uid: 用户UID + - pn: 页码 + ### 返回: + - 用户发布的视频数据 + + # [English] + ### Purpose: + - Get user post video data + ### Parameters: + - uid: User UID + - pn: Page number + ### Return: + - User posted video data + + # [示例/Example] + uid = "178360345" + pn = 1 + """ + try: + data = await BilibiliWebCrawler.fetch_user_post_videos(uid, pn) + return ResponseModel(code=200, + router=request.url.path, + data=data) + except Exception as e: + status_code = 400 + detail = ErrorResponseModel(code=status_code, + router=request.url.path, + params=dict(request.query_params), + ) + raise HTTPException(status_code=status_code, detail=detail.dict()) + + +# 获取用户所有收藏夹信息 +@router.get("/fetch_collect_folders", response_model=ResponseModel, + summary="获取用户所有收藏夹信息/Get user collection folders") +async def fetch_collect_folders(request: Request, + uid: str = Query(example="178360345", description="用户UID")): + """ + # [中文] + ### 用途: + - 获取用户收藏作品数据 + ### 参数: + - uid: 用户UID + ### 返回: + - 用户收藏夹信息 + + # [English] + ### Purpose: + - Get user collection folders + ### Parameters: + - uid: User UID + ### Return: + - user collection folders + + # [示例/Example] + uid = "178360345" + """ + try: + data = await BilibiliWebCrawler.fetch_collect_folders(uid) + return ResponseModel(code=200, + router=request.url.path, + data=data) + except Exception as e: + status_code = 400 + detail = ErrorResponseModel(code=status_code, + router=request.url.path, + params=dict(request.query_params), + ) + raise HTTPException(status_code=status_code, detail=detail.dict()) + + +# 获取指定收藏夹内视频数据 +@router.get("/fetch_user_collection_videos", response_model=ResponseModel, + summary="获取指定收藏夹内视频数据/Gets video data from a collection folder") +async def fetch_user_collection_videos(request: Request, + folder_id: str = Query(example="1756059545", + description="收藏夹id/collection folder id"), + pn: int = Query(default=1, description="页码/Page number") + ): + """ + # [中文] + ### 用途: + - 获取指定收藏夹内视频数据 + ### 参数: + - folder_id: 用户UID + - pn: 页码 + ### 返回: + - 指定收藏夹内视频数据 + + # [English] + ### Purpose: + - Gets video data from a collection folder + ### Parameters: + - folder_id: collection folder id + - pn: Page number + ### Return: + - video data from collection folder + + # [示例/Example] + folder_id = "1756059545" + pn = 1 + """ + try: + data = await BilibiliWebCrawler.fetch_folder_videos(folder_id, pn) + return ResponseModel(code=200, + router=request.url.path, + data=data) + except Exception as e: + status_code = 400 + detail = ErrorResponseModel(code=status_code, + router=request.url.path, + params=dict(request.query_params), + ) + raise HTTPException(status_code=status_code, detail=detail.dict()) + + +# 获取指定用户的信息 +@router.get("/fetch_user_profile", response_model=ResponseModel, + summary="获取指定用户的信息/Get information of specified user") +async def fetch_collect_folders(request: Request, + uid: str = Query(example="178360345", description="用户UID")): + """ + # [中文] + ### 用途: + - 获取指定用户的信息 + ### 参数: + - uid: 用户UID + ### 返回: + - 指定用户的个人信息 + + # [English] + ### Purpose: + - Get information of specified user + ### Parameters: + - uid: User UID + ### Return: + - information of specified user + + # [示例/Example] + uid = "178360345" + """ + try: + data = await BilibiliWebCrawler.fetch_user_profile(uid) + return ResponseModel(code=200, + router=request.url.path, + data=data) + except Exception as e: + status_code = 400 + detail = ErrorResponseModel(code=status_code, + router=request.url.path, + params=dict(request.query_params), + ) + raise HTTPException(status_code=status_code, detail=detail.dict()) + + +# 获取综合热门视频信息 +@router.get("/fetch_com_popular", response_model=ResponseModel, + summary="获取综合热门视频信息/Get comprehensive popular video information") +async def fetch_collect_folders(request: Request, + pn: int = Query(default=1, description="页码/Page number")): + """ + # [中文] + ### 用途: + - 获取综合热门视频信息 + ### 参数: + - pn: 页码 + ### 返回: + - 综合热门视频信息 + + # [English] + ### Purpose: + - Get comprehensive popular video information + ### Parameters: + - pn: Page number + ### Return: + - comprehensive popular video information + + # [示例/Example] + pn = 1 + """ + try: + data = await BilibiliWebCrawler.fetch_com_popular(pn) + return ResponseModel(code=200, + router=request.url.path, + data=data) + except Exception as e: + status_code = 400 + detail = ErrorResponseModel(code=status_code, + router=request.url.path, + params=dict(request.query_params), + ) + raise HTTPException(status_code=status_code, detail=detail.dict()) + + +# 获取指定视频的评论 +@router.get("/fetch_video_comments", response_model=ResponseModel, + summary="获取指定视频的评论/Get comments on the specified video") +async def fetch_collect_folders(request: Request, + bv_id: str = Query(example="BV1M1421t7hT", description="作品id/Video id"), + pn: int = Query(default=1, description="页码/Page number")): + """ + # [中文] + ### 用途: + - 获取指定视频的评论 + ### 参数: + - bv_id: 作品id + - pn: 页码 + ### 返回: + - 指定视频的评论数据 + + # [English] + ### Purpose: + - Get comments on the specified video + ### Parameters: + - bv_id: Video id + - pn: Page number + ### Return: + - comments of the specified video + + # [示例/Example] + bv_id = "BV1M1421t7hT" + pn = 1 + """ + try: + data = await BilibiliWebCrawler.fetch_video_comments(bv_id, pn) + return ResponseModel(code=200, + router=request.url.path, + data=data) + except Exception as e: + status_code = 400 + detail = ErrorResponseModel(code=status_code, + router=request.url.path, + params=dict(request.query_params), + ) + raise HTTPException(status_code=status_code, detail=detail.dict()) + + +# 获取视频下指定评论的回复 +@router.get("/fetch_comment_reply", response_model=ResponseModel, + summary="获取视频下指定评论的回复/Get reply to the specified comment") +async def fetch_collect_folders(request: Request, + bv_id: str = Query(example="BV1M1421t7hT", description="作品id/Video id"), + pn: int = Query(default=1, description="页码/Page number"), + rpid: str = Query(example="237109455120", description="回复id/Reply id")): + """ + # [中文] + ### 用途: + - 获取视频下指定评论的回复 + ### 参数: + - bv_id: 作品id + - pn: 页码 + - rpid: 回复id + ### 返回: + - 指定评论的回复数据 + + # [English] + ### Purpose: + - Get reply to the specified comment + ### Parameters: + - bv_id: Video id + - pn: Page number + - rpid: Reply id + ### Return: + - Reply of the specified comment + + # [示例/Example] + bv_id = "BV1M1421t7hT" + pn = 1 + rpid = "237109455120" + """ + try: + data = await BilibiliWebCrawler.fetch_comment_reply(bv_id, pn, rpid) + return ResponseModel(code=200, + router=request.url.path, + data=data) + except Exception as e: + status_code = 400 + detail = ErrorResponseModel(code=status_code, + router=request.url.path, + params=dict(request.query_params), + ) + raise HTTPException(status_code=status_code, detail=detail.dict()) + + +# 获取指定用户动态 +@router.get("/fetch_user_dynamic", response_model=ResponseModel, + summary="获取指定用户动态/Get dynamic information of specified user") +async def fetch_collect_folders(request: Request, + uid: str = Query(example="16015678", description="用户UID"), + offset: str = Query(default="", example="953154282154098691", + description="开始索引/offset")): + """ + # [中文] + ### 用途: + - 获取指定用户动态 + ### 参数: + - uid: 用户UID + - offset: 开始索引 + ### 返回: + - 指定用户动态数据 + + # [English] + ### Purpose: + - Get dynamic information of specified user + ### Parameters: + - uid: User UID + - offset: offset + ### Return: + - dynamic information of specified user + + # [示例/Example] + uid = "178360345" + offset = "953154282154098691" + """ + try: + data = await BilibiliWebCrawler.fetch_user_dynamic(uid, offset) + return ResponseModel(code=200, + router=request.url.path, + data=data) + except Exception as e: + status_code = 400 + detail = ErrorResponseModel(code=status_code, + router=request.url.path, + params=dict(request.query_params), + ) + raise HTTPException(status_code=status_code, detail=detail.dict()) + + +# 获取指定直播间信息 +@router.get("/fetch_live_room_detail", response_model=ResponseModel, + summary="获取指定直播间信息/Get information of specified live room") +async def fetch_collect_folders(request: Request, + room_id: str = Query(example="22816111", description="直播间ID/Live room ID")): + """ + # [中文] + ### 用途: + - 获取指定直播间信息 + ### 参数: + - room_id: 直播间ID + ### 返回: + - 指定直播间信息 + + # [English] + ### Purpose: + - Get information of specified live room + ### Parameters: + - room_id: Live room ID + ### Return: + - information of specified live room + + # [示例/Example] + room_id = "22816111" + """ + try: + data = await BilibiliWebCrawler.fetch_live_room_detail(room_id) + return ResponseModel(code=200, + router=request.url.path, + data=data) + except Exception as e: + status_code = 400 + detail = ErrorResponseModel(code=status_code, + router=request.url.path, + params=dict(request.query_params), + ) + raise HTTPException(status_code=status_code, detail=detail.dict()) + + +# # 获取指定直播间视频流 +# @router.get("/fetch_live_videos", response_model=ResponseModel, +# summary="获取直播间视频流/Get live video data of specified room") +# async def fetch_collect_folders(request: Request, +# room_id: str = Query(example="22816111", description="直播间ID/Live room ID")): +# """ +# # [中文] +# ### 用途: +# - 获取指定直播间视频流 +# ### 参数: +# - room_id: 直播间ID +# ### 返回: +# - 指定直播间视频流 +# +# # [English] +# ### Purpose: +# - Get live video data of specified room +# ### Parameters: +# - room_id: Live room ID +# ### Return: +# - live video data of specified room +# +# # [示例/Example] +# room_id = "22816111" +# """ +# try: +# data = await BilibiliWebCrawler.fetch_live_videos(room_id) +# return ResponseModel(code=200, +# router=request.url.path, +# data=data) +# except Exception as e: +# status_code = 400 +# detail = ErrorResponseModel(code=status_code, +# router=request.url.path, +# params=dict(request.query_params), +# ) +# raise HTTPException(status_code=status_code, detail=detail.dict()) + + +# 获取所有直播分区列表 +@router.get("/fetch_all_live_areas", response_model=ResponseModel, + summary="获取所有直播分区列表/Get a list of all live areas") +async def fetch_collect_folders(request: Request,): + """ + # [中文] + ### 用途: + - 获取所有直播分区列表 + ### 参数: + ### 返回: + - 所有直播分区列表 + + # [English] + ### Purpose: + - Get a list of all live areas + ### Parameters: + ### Return: + - list of all live areas + + # [示例/Example] + """ + try: + data = await BilibiliWebCrawler.fetch_all_live_areas() + return ResponseModel(code=200, + router=request.url.path, + data=data) + except Exception as e: + status_code = 400 + detail = ErrorResponseModel(code=status_code, + router=request.url.path, + params=dict(request.query_params), + ) + raise HTTPException(status_code=status_code, detail=detail.dict()) diff --git a/app/api/router.py b/app/api/router.py index 881513b2c..c510616fb 100644 --- a/app/api/router.py +++ b/app/api/router.py @@ -3,6 +3,7 @@ tiktok_web, tiktok_app, douyin_web, + bilibili_web, hybrid_parsing, ios_shortcut, download, ) @@ -15,6 +16,9 @@ # Douyin routers router.include_router(douyin_web.router, prefix="/douyin/web", tags=["Douyin-Web-API"]) +# Bilibili routers +router.include_router(bilibili_web.router, prefix="/bilibili/web", tags=["Bilibili-Web-API"]) + # Hybrid routers router.include_router(hybrid_parsing.router, prefix="/hybrid", tags=["Hybrid-API"]) diff --git a/app/main.py b/app/main.py index 38b64156d..075b00671 100644 --- a/app/main.py +++ b/app/main.py @@ -77,6 +77,10 @@ "name": "TikTok-App-API", "description": "**(TikTok-App-API数据接口/TikTok-App-API data endpoints)**", }, + { + "name": "Bilibili-Web-API", + "description": "**(Bilibili-Web-API数据接口/Bilibili-Web-API data endpoints)**", + }, { "name": "iOS-Shortcut", "description": "**(iOS快捷指令数据接口/iOS-Shortcut data endpoints)**", diff --git a/crawlers/bilibili/web/config.yaml b/crawlers/bilibili/web/config.yaml new file mode 100644 index 000000000..e33b0c44c --- /dev/null +++ b/crawlers/bilibili/web/config.yaml @@ -0,0 +1,13 @@ +TokenManager: + bilibili: + headers: + 'accept-language': zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6 + 'origin': https://www.bilibili.com + 'referer': https://space.bilibili.com/ + 'origin_2': https://space.bilibili.com + 'cookie': buvid3=D6E58E7B-E3A9-7CD3-7BE5-B5F255788A3020034infoc; b_nut=1723702120; _uuid=6E10D69A10-A711-9DA8-6833-1010262296C24B21337infoc; buvid_fp=6cf2ea8e143bbc49f3b7c0dcb2465fc2; buvid4=748EC8F0-82E2-1672-A286-8445DDB2A80C06110-023112304-; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3MjM5NjEzMjIsImlhdCI6MTcyMzcwMjA2MiwicGx0IjotMX0.IWOEMLCDKqWAX24rePU-1Qgm9Isf5CU8Tz0O-j6GHfo; bili_ticket_expires=1723961262; CURRENT_FNVAL=4048; rpdid=|(JluY|JJ|RR0J'u~kJ~|kkuY; b_lsid=E10B83DC4_191552166D6; header_theme_version=CLOSE; enable_web_push=DISABLE; home_feed_column=5; browser_resolution=1488-714; sid=873ujj7i + 'user-agent': Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36 + + proxies: + http: + https: \ No newline at end of file diff --git a/crawlers/bilibili/web/endpoints.py b/crawlers/bilibili/web/endpoints.py new file mode 100644 index 000000000..da56f41f2 --- /dev/null +++ b/crawlers/bilibili/web/endpoints.py @@ -0,0 +1,50 @@ +class BilibiliAPIEndpoints: + + "-------------------------------------------------------域名-domain-------------------------------------------------------" + # 哔哩哔哩接口域名 + BILIAPI_DOMAIN = "https://api.bilibili.com" + + # 哔哩哔哩直播域名 + LIVE_DOMAIN = "https://api.live.bilibili.com" + + "-------------------------------------------------------接口-api-------------------------------------------------------" + # 作品信息 (Post Detail) + POST_DETAIL = f"{BILIAPI_DOMAIN}/x/web-interface/view" + + # 用户播放列表 (用于爬取用户所有视频数据) + USER_POST = f"{BILIAPI_DOMAIN}/x/v2/medialist/resource/list" + + # 收藏夹列表 + COLLECT_FOLDERS = f"{BILIAPI_DOMAIN}/x/v3/fav/folder/created/list-all" + + # 收藏夹视频 + COLLECT_VIDEOS = f"{BILIAPI_DOMAIN}/x/v3/fav/resource/list" + + # 用户个人信息 + USER_DETAIL = f"{BILIAPI_DOMAIN}/x/space/wbi/acc/info" + + # 综合热门 + COM_POPULAR = f"{BILIAPI_DOMAIN}/x/web-interface/popular" + + # 每周必看 + WEEKLY_POPULAR = f"{BILIAPI_DOMAIN}/x/web-interface/popular/series/one" + + # 入站必刷 + PRECIOUS_POPULAR = f"{BILIAPI_DOMAIN}/x/web-interface/popular/precious" + + # 视频评论 + VIDEO_COMMENTS = f"{BILIAPI_DOMAIN}/x/v2/reply" + + # 评论的回复 + COMMENT_REPLY = f"{BILIAPI_DOMAIN}/x/v2/reply/reply" + + # 直播间信息 + LIVEROOM_DETAIL = f"{LIVE_DOMAIN}/room/v1/Room/get_info" + + # 直播分区列表 + LIVE_AREAS = f"{LIVE_DOMAIN}/room/v1/Area/getList" + + # 直播间视频流 + LIVE_VIDEOS = f"{LIVE_DOMAIN}/room/v1/Room/playUrl" + + diff --git a/crawlers/bilibili/web/utils.py b/crawlers/bilibili/web/utils.py new file mode 100644 index 000000000..742b6a262 --- /dev/null +++ b/crawlers/bilibili/web/utils.py @@ -0,0 +1,201 @@ +import time +from urllib.parse import urlencode +import random +from crawlers.bilibili.web import wrid +from crawlers.utils.logger import logger + +# 装饰器 检查是否正确生成endpoint +def Check_gen(func): + def checker(*args, **kwargs): + try: + result = func(*args, **kwargs) + return result + except Exception as e: + raise RuntimeError("生成w_rid失败:{0}, 函数地址:{1}".format(e, func.__name__)) + + return checker + +class EndpointModels: + def __init__(self): + # 实例化WridManager + self.wridmanager = WridManager() + # 当前时间戳 + self.wts = round(time.time()) + # 固定inter也能获得结果。如果失效见--WridManager().get_inter + self.inter = '{"ds":[],"wh":[3557,5674,5],"of":[154,308,154]}' + + # 获取wrid示例 通过uid 生成包含w_rid和wts的字典 + @Check_gen + async def get_wrid_wts_by_uid(self, uid: str) -> dict: + params = { + 'dm_cover_img_str': 'QU5HTEUgKE5WSURJQSwgTlZJRElBIEdlRm9yY2UgUlRYIDMwNTAgTGFwdG9wIEdQVSAoMHgwMDAwMjVBMikgRGlyZWN0M0QxMSB2c181XzAgcHNfNV8wLCBEM0QxMSlHb29nbGUgSW5jLiAoTlZJRElBKQ', + 'dm_img_inter': self.inter, + 'dm_img_list': [], + 'dm_img_str': 'V2ViR0wgMS4wIChPcGVuR0wgRVMgMi4wIENocm9taXVtKQ', + 'mid': uid, + 'platform': 'web', + 'token': '', + 'web_location': '1550101', + 'wts': f'{self.wts}ea1db124af3c7062474693fa704f4ff8' + } + # 获取w_rid参数 + w_rid = await self.wridmanager.get_wrid(params=params) + reslut = { + "w_rid": w_rid, + "wts": self.wts + } + return reslut + + # 获取用户发布视频作品数据 生成enpoint + @Check_gen + async def user_post_videos_endpoint(self, uid: str, pn: int, ps: int = 30) -> str: + # 编码inter + new_inter = self.inter.replace(" ", "").replace('{', "%7B").replace("'", "%22").replace("}", "%7D") + # 构建请求参数 + params = { + "dm_cover_img_str": "QU5HTEUgKE5WSURJQSwgTlZJRElBIEdlRm9yY2UgUlRYIDMwNTAgTGFwdG9wIEdQVSAoMHgwMDAwMjVBMikgRGlyZWN0M0QxMSB2c181XzAgcHNfNV8wLCBEM0QxMSlHb29nbGUgSW5jLiAoTlZJRElBKQ", + "dm_img_inter": self.inter, + "dm_img_list": [], + "dm_img_str": "V2ViR0wgMS4wIChPcGVuR0wgRVMgMi4wIENocm9taXVtKQ", + "keyword": "", + "mid": uid, + "order": "pubdate", + "order_avoided": "true", + "platform": "web", + "pn": pn, + "ps": ps, + "tid": "0", + "web_location": "1550101", + "wts": f"{self.wts}ea1db124af3c7062474693fa704f4ff8", + } + # 获取wrid + w_rid = await self.wridmanager.get_wrid(params=params) + # 将上面结果拼接成最终结果并返回 + final_endpoint = f'https://api.bilibili.com/x/space/wbi/arc/search?mid={uid}&ps={ps}&tid=0&pn={pn}&keyword=&order=pubdate&platform=web&web_location=1550101&order_avoided=true&dm_img_list=[]&dm_img_str=V2ViR0wgMS4wIChPcGVuR0wgRVMgMi4wIENocm9taXVtKQ&dm_cover_img_str=QU5HTEUgKE5WSURJQSwgTlZJRElBIEdlRm9yY2UgUlRYIDMwNTAgTGFwdG9wIEdQVSAoMHgwMDAwMjVBMikgRGlyZWN0M0QxMSB2c181XzAgcHNfNV8wLCBEM0QxMSlHb29nbGUgSW5jLiAoTlZJRElBKQ&dm_img_inter={new_inter}&w_rid={w_rid}&wts={self.wts}' + return final_endpoint + + # 获取指定用户的信息 生成enpoint + @Check_gen + async def user_profile_endpoint(self, uid: str) -> str: + # 编码inter + new_inter = self.inter.replace(" ", "").replace('{', "%7B").replace("'", "%22").replace("}", "%7D") + # 构建请求参数 + params = { + 'dm_cover_img_str': 'QU5HTEUgKE5WSURJQSwgTlZJRElBIEdlRm9yY2UgUlRYIDMwNTAgTGFwdG9wIEdQVSAoMHgwMDAwMjVBMikgRGlyZWN0M0QxMSB2c181XzAgcHNfNV8wLCBEM0QxMSlHb29nbGUgSW5jLiAoTlZJRElBKQ', + 'dm_img_inter': self.inter, + 'dm_img_list': [], + 'dm_img_str': 'V2ViR0wgMS4wIChPcGVuR0wgRVMgMi4wIENocm9taXVtKQ', + 'mid': uid, + 'platform': 'web', + 'token': '', + 'web_location': '1550101', + 'wts': f'{self.wts}ea1db124af3c7062474693fa704f4ff8' + } + # 获取wrid + w_rid = await self.wridmanager.get_wrid(params=params) + # 将上面结果拼接成最终字符串并返回 + final_endpoint = f'https://api.bilibili.com/x/space/wbi/acc/info?mid={uid}&token=&platform=web&web_location=1550101&dm_img_list=[]&dm_img_str=V2ViR0wgMS4wIChPcGVuR0wgRVMgMi4wIENocm9taXVtKQ&dm_cover_img_str=QU5HTEUgKE5WSURJQSwgTlZJRElBIEdlRm9yY2UgUlRYIDMwNTAgTGFwdG9wIEdQVSAoMHgwMDAwMjVBMikgRGlyZWN0M0QxMSB2c181XzAgcHNfNV8wLCBEM0QxMSlHb29nbGUgSW5jLiAoTlZJRElBKQ&dm_img_inter={new_inter}&w_rid={w_rid}&wts={self.wts}' + return final_endpoint + + # 获取综合热门视频信息 生成enpoint + @Check_gen + async def com_popular_endpoint(self, pn: int) -> str: + # 构建请求参数 + params = { + "pn": pn, + "ps": "20", + "web_location": "333.934", + "wts": f"{self.wts}ea1db124af3c7062474693fa704f4ff8", + } + # 获取wrid + w_rid = await self.wridmanager.get_wrid(params=params) + # 将上面结果拼接成最终结果并返回 + final_endpoint = f"https://api.bilibili.com/x/web-interface/popular?ps=20&pn={pn}&web_location=333.934&w_rid={w_rid}&wts={self.wts}" + return final_endpoint + + # 获取指定用户动态 + @Check_gen + async def user_dynamic_endpoint(self, uid: str, offset: str): + # 编码inter + new_inter = self.inter.replace(" ", "").replace('{', "%7B").replace("'", "%22").replace("}", "%7D") + # 构建请求参数 + params = { + "dm_cover_img_str": "QU5HTEUgKE5WSURJQSwgTlZJRElBIEdlRm9yY2UgUlRYIDMwNTAgTGFwdG9wIEdQVSAoMHgwMDAwMjVBMikgRGlyZWN0M0QxMSB2c181XzAgcHNfNV8wLCBEM0QxMSlHb29nbGUgSW5jLiAoTlZJRElBKQ", + "dm_img_inter": self.inter, + "dm_img_list": [], + "dm_img_str": "V2ViR0wgMS4wIChPcGVuR0wgRVMgMi4wIENocm9taXVtKQ&features=itemOpusStyle%2ClistOnlyfans%2CopusBigCover%2ConlyfansVote%2CdecorationCard%2CforwardListHidden%2CugcDelete", + "host_mid": uid, + "offset": offset, + "platform": "web", + "timezone_offset": "-480", + "web_location": "333.999", + "wts": self.wts, + "x-bili-device-req-json": "%7B%22platform%22%3A%22web%22%2C%22device%22%3A%22pc%22%7D", + "x-bili-web-req-json": "%7B%22spm_id%22%3A%22333.999%22%7Dea1db124af3c7062474693fa704f4ff8" + } + # 获取wrid + w_rid = await self.wridmanager.get_wrid(params=params) + # 将上面结果拼接成最终结果并返回 + final_endpoint = f'https://api.bilibili.com/x/polymer/web-dynamic/v1/feed/space?offset={offset}&host_mid={uid}&timezone_offset=-480&platform=web&features=itemOpusStyle,listOnlyfans,opusBigCover,onlyfansVote,decorationCard,forwardListHidden,ugcDelete&web_location=333.999&dm_img_list=[]&dm_img_str=V2ViR0wgMS4wIChPcGVuR0wgRVMgMi4wIENocm9taXVtKQ&dm_cover_img_str=QU5HTEUgKE5WSURJQSwgTlZJRElBIEdlRm9yY2UgUlRYIDMwNTAgTGFwdG9wIEdQVSAoMHgwMDAwMjVBMikgRGlyZWN0M0QxMSB2c181XzAgcHNfNV8wLCBEM0QxMSlHb29nbGUgSW5jLiAoTlZJRElBKQ&dm_img_inter={new_inter}&x-bili-device-req-json=%7B%22platform%22:%22web%22,%22device%22:%22pc%22%7D&x-bili-web-req-json=%7B%22spm_id%22:%22333.999%22%7D&w_rid={w_rid}&wts={self.wts}' + return final_endpoint + + +class WridManager: + + def s(self) -> list: + x = random.randint(0, 113) + return [2 * 1488 + 2 * 311 + 3 * x, 4 * 1488 - 311 + x, x] + + def d(self) -> list: + x = random.randint(0, 513) + return [x, 2 * x, x] + + def get_inter(self) -> dict: + return {"ds": [], "wh": self.s(), "of": self.d()} + + async def get_encode_query(self, params: dict) -> str: + params = dict(sorted(params.items())) # 按照 key 重排参数 + # 过滤 value 中的 "!'()*" 字符 + params = { + k: ''.join(filter(lambda chr: chr not in "!'()*", str(v))) + for k, v + in params.items() + } + query = urlencode(params) # 序列化参数 + return query + + async def get_wrid(self, params: dict) -> str: + encode_query = await self.get_encode_query(params) + # 获取w_rid参数 + w_rid = wrid.get_wrid(e=encode_query) + return w_rid + +async def bv2av(bv_id:str) -> int: + table = "fZodR9XQDSUm21yCkr6zBqiveYah8bt4xsWpHnJE7jL5VG3guMTKNPAwcF" + s = [11, 10, 3, 8, 4, 6, 2, 9, 5, 7] + xor = 177451812 + add_105 = 8728348608 + add_all = 8728348608 - (2 ** 31 - 1) - 1 + tr = [0] * 128 + for i in range(58): + tr[ord(table[i])] = i + r = 0 + for i in range(6): + r += tr[ord(bv_id[s[i]])] * (58 ** i) + add = add_105 + if r < add: + add = add_all + aid = (r - add) ^ xor + return aid + + +# 响应分析 +class ResponseAnalyzer: + # 用户收藏夹信息 + @classmethod + async def collect_folders_analyze(cls, response: dict) -> dict: + if response['data']: + return response + else: + logger.warning("该用户收藏夹为空/用户设置为不可见") + return {"code": 1, "message": "该用户收藏夹为空/用户设置为不可见"} diff --git a/crawlers/bilibili/web/web_crawler.py b/crawlers/bilibili/web/web_crawler.py new file mode 100644 index 000000000..bfb8b6236 --- /dev/null +++ b/crawlers/bilibili/web/web_crawler.py @@ -0,0 +1,318 @@ +import asyncio # 异步I/O +import os # 系统操作 +import time # 时间操作 +import yaml # 配置文件 + +# 基础爬虫客户端和哔哩哔哩API端点 +from crawlers.base_crawler import BaseCrawler +from crawlers.bilibili.web.endpoints import BilibiliAPIEndpoints + +# 哔哩哔哩工具类 +from crawlers.bilibili.web.utils import EndpointModels, bv2av, ResponseAnalyzer + + +# 配置文件路径 +path = os.path.abspath(os.path.dirname(__file__)) + +# 读取配置文件 +with open(f"{path}/config.yaml", "r", encoding="utf-8") as f: + config = yaml.safe_load(f) + + +class BilibiliWebCrawler: + + # 从配置文件读取哔哩哔哩请求头 + async def get_bilibili_headers(self): + bili_config = config['TokenManager']['bilibili'] + kwargs = { + "headers": { + "accept-language": bili_config["headers"]["accept-language"], + "origin": bili_config["headers"]["origin"], + "referer": bili_config["headers"]["referer"], + "user-agent": bili_config["headers"]["user-agent"], + "cookie": bili_config["headers"]["cookie"], + }, + "proxies": {"http://": bili_config["proxies"]["http"], "https://": bili_config["proxies"]["https"]}, + } + return kwargs + + "-------------------------------------------------------handler接口列表-------------------------------------------------------" + # 获取单个视频详情信息 + async def fetch_one_video(self, bv_id: str) -> dict: + # 获取请求头信息 + kwargs = await self.get_bilibili_headers() + # 创建基础爬虫对象 + base_crawler = BaseCrawler(proxies=kwargs["proxies"], crawler_headers=kwargs["headers"]) + async with base_crawler as crawler: + # 创建请求endpoint + endpoint = f"{BilibiliAPIEndpoints.POST_DETAIL}?bvid={bv_id}" + # 发送请求，获取请求响应结果 + response = await crawler.fetch_get_json(endpoint) + return response + + # 获取用户发布视频作品数据 + async def fetch_user_post_videos(self, uid: str, pn: int) -> dict: + """ + :param uid: 用户uid + :param pn: 页码 + :return: + """ + # 获取请求头信息 + kwargs = await self.get_bilibili_headers() + # 创建基础爬虫对象 + base_crawler = BaseCrawler(proxies=kwargs["proxies"], crawler_headers=kwargs["headers"]) + async with base_crawler as crawler: + # 创建请求endpoint + endpoint = await EndpointModels().user_post_videos_endpoint(uid=uid, pn=pn) + # 发送请求，获取请求响应结果 + response = await crawler.fetch_get_json(endpoint) + return response + + # 获取用户所有收藏夹信息 + async def fetch_collect_folders(self, uid: str) -> dict: + # 获取请求头信息 + kwargs = await self.get_bilibili_headers() + # 创建基础爬虫对象 + base_crawler = BaseCrawler(proxies=kwargs["proxies"], crawler_headers=kwargs["headers"]) + async with base_crawler as crawler: + # 创建请求endpoint + endpoint = f"{BilibiliAPIEndpoints.COLLECT_FOLDERS}?up_mid={uid}" + # 发送请求，获取请求响应结果 + response = await crawler.fetch_get_json(endpoint) + # 分析响应结果 + result_dict = await ResponseAnalyzer.collect_folders_analyze(response=response) + return result_dict + + # 获取指定收藏夹内视频数据 + async def fetch_folder_videos(self, folder_id: str, pn: int) -> dict: + """ + :param folder_id: 收藏夹id-- 可从<获取用户所有收藏夹信息>获得 + :param pn: 页码 + :return: + """ + # 获取请求头信息 + kwargs = await self.get_bilibili_headers() + # 创建基础爬虫对象 + base_crawler = BaseCrawler(proxies=kwargs["proxies"], crawler_headers=kwargs["headers"]) + # 发送请求，获取请求响应结果 + async with base_crawler as crawler: + endpoint = f"{BilibiliAPIEndpoints.COLLECT_VIDEOS}?media_id={folder_id}&pn={pn}&ps=20&keyword=&order=mtime&type=0&tid=0&platform=web" + response = await crawler.fetch_get_json(endpoint) + return response + + # 获取指定用户的信息 + async def fetch_user_profile(self, uid: str) -> dict: + # 获取请求头信息 + kwargs = await self.get_bilibili_headers() + # 创建基础爬虫对象 + base_crawler = BaseCrawler(proxies=kwargs["proxies"], crawler_headers=kwargs["headers"]) + async with base_crawler as crawler: + # 创建请求endpoint + endpoint = await EndpointModels().user_profile_endpoint(uid=uid) + response = await crawler.fetch_get_json(endpoint=endpoint) + return response + + # 获取综合热门视频信息 + async def fetch_com_popular(self, pn: int) -> dict: + # 获取请求头信息 + kwargs = await self.get_bilibili_headers() + # 创建基础爬虫对象 + base_crawler = BaseCrawler(proxies=kwargs["proxies"], crawler_headers=kwargs["headers"]) + async with base_crawler as crawler: + # 创建请求endpoint + endpoint = await EndpointModels().com_popular_endpoint(pn=pn) + response = await crawler.fetch_get_json(endpoint=endpoint) + return response + + # 获取指定视频的评论 + async def fetch_video_comments(self, bv_id: str, pn: int) -> dict: + # 评论排序 -- 1:按点赞数排序. 0:按时间顺序排序 + sort = 1 + # 获取请求头信息 + kwargs = await self.get_bilibili_headers() + # 创建基础爬虫对象 + base_crawler = BaseCrawler(proxies=kwargs["proxies"], crawler_headers=kwargs["headers"]) + async with base_crawler as crawler: + # 创建请求endpoint + endpoint = f"{BilibiliAPIEndpoints.VIDEO_COMMENTS}?type=1&oid={bv_id}&sort={sort}&nohot=0&ps=20&pn={pn}" + # 发送请求，获取请求响应结果 + response = await crawler.fetch_get_json(endpoint) + return response + + # 获取视频下指定评论的回复 + async def fetch_comment_reply(self, bv_id: str, pn: int, rpid: str) -> dict: + """ + :param bv_id: 目标视频bv号 + :param pn: 页码 + :param rpid: 目标评论id，可通过fetch_video_comments获得 + :return: + """ + # 获取请求头信息 + kwargs = await self.get_bilibili_headers() + # 创建基础爬虫对象 + base_crawler = BaseCrawler(proxies=kwargs["proxies"], crawler_headers=kwargs["headers"]) + async with base_crawler as crawler: + # 创建请求endpoint + endpoint = f"{BilibiliAPIEndpoints.COMMENT_REPLY}?type=1&oid={bv_id}&root={rpid}&&ps=20&pn={pn}" + # 发送请求，获取请求响应结果 + response = await crawler.fetch_get_json(endpoint) + return response + + # 获取指定用户动态 + async def fetch_user_dynamic(self, uid: str, offset: str) -> dict: + # 获取请求头信息 + kwargs = await self.get_bilibili_headers() + # 创建基础爬虫对象 + base_crawler = BaseCrawler(proxies=kwargs["proxies"], crawler_headers=kwargs["headers"]) + async with base_crawler as crawler: + # 创建请求endpoint + endpoint = await EndpointModels().user_dynamic_endpoint(uid=uid, offset=offset) + # 发送请求，获取请求响应结果 + response = await crawler.fetch_get_json(endpoint) + return response + + # 获取指定直播间信息 + async def fetch_live_room_detail(self, room_id: str) -> dict: + # 获取请求头信息 + kwargs = await self.get_bilibili_headers() + # 创建基础爬虫对象 + base_crawler = BaseCrawler(proxies=kwargs["proxies"], crawler_headers=kwargs["headers"]) + async with base_crawler as crawler: + # 创建请求endpoint + endpoint = f"{BilibiliAPIEndpoints.LIVEROOM_DETAIL}?room_id={room_id}" + # 发送请求，获取请求响应结果 + response = await crawler.fetch_get_json(endpoint) + return response + + # 获取指定直播间视频流 + # async def fetch_live_videos(self, room_id: str) -> dict: + # # 获取请求头信息 + # kwargs = await self.get_bilibili_headers() + # # 创建基础爬虫对象 + # base_crawler = BaseCrawler(proxies=kwargs["proxies"], crawler_headers=kwargs["headers"]) + # async with base_crawler as crawler: + # # 创建请求endpoint + # endpoint = f"{BilibiliAPIEndpoints.LIVE_VIDEOS}?cid={room_id}&quality=4" + # # 发送请求，获取请求响应结果 + # response = await crawler.fetch_get_json(endpoint) + # return response + + "-------------------------------------------------------utils接口列表-------------------------------------------------------" + # 通过bv号获得视频aid号 + async def get_aid(self, bv_id: str) -> int: + aid = await bv2av(bv_id=bv_id) + return aid + + # 获取所有直播分区列表 + async def fetch_all_live_areas(self) -> dict: + # 获取请求头信息 + kwargs = await self.get_bilibili_headers() + # 创建基础爬虫对象 + base_crawler = BaseCrawler(proxies=kwargs["proxies"], crawler_headers=kwargs["headers"]) + async with base_crawler as crawler: + # 创建请求endpoint + endpoint = BilibiliAPIEndpoints.LIVE_AREAS + # 发送请求，获取请求响应结果 + response = await crawler.fetch_get_json(endpoint) + return response + + # 根据uid生成wts及其对应w_rid参数(包含dm_img_inter参数) + # (仅示例 不同接口所需要传进去的参数不同)(待改进) + async def uid_to_wrid(self, uid: str) -> dict: + result = await EndpointModels().get_wrid_wts_by_uid(uid=uid) + return result + + "-------------------------------------------------------main-------------------------------------------------------" + async def main(self): + + "-------------------------------------------------------handler接口列表-------------------------------------------------------" + # 获取单个作品数据 + # bv_id = 'BV1M1421t7hT' + # result = await self.fetch_one_video(bv_id=bv_id) + # print(result) + + # 获取用户发布作品数据 + # uid = '178360345' + # pn = 1 + # result = await self.fetch_user_post_videos(uid=uid, pn=pn) + # print(result) + + # 获取用户所有收藏夹信息 + # uid = '178360345' + # reslut = await self.fetch_collect_folders(uid=uid) + # print(reslut) + + # 获取用户指定收藏夹内视频数据 + # folder_id = '1756059545' # 收藏夹id，可从<获取用户所有收藏夹信息>获得 + # pn = 1 + # result = await self.fetch_folder_videos(folder_id=folder_id, pn=pn) + # print(result) + + # 获取指定用户的信息 + # uid = '178360345' + # result = await self.fetch_user_profile(uid=uid) + # print(result) + + # 获取综合热门信息 + # pn = 1 # 页码 + # result = await self.fetch_com_popular(pn=pn) + # print(result) + + # 获取指定视频的评论(不登录只能获取一页的评论) + # bv_id = "BV1M1421t7hT" + # pn = 1 + # result = await self.fetch_video_comments(bv_id=bv_id, pn=pn) + # print(result) + + # 获取视频下指定评论的回复(不登录只能获取一页的评论) + # bv_id = "BV1M1421t7hT" + # rpid = "237109455120" + # pn = 1 + # result = await self.fetch_comment_reply(bv_id=bv_id, pn=pn, rpid=rpid) + # print(result) + + # 获取指定用户动态 + # uid = "16015678" + # offset = "953154282154098691" # 翻页索引，为空即从最新动态开始，可从获得到的动态数据里面获得 + # result = await self.fetch_user_dynamic(uid=uid, offset=offset) + # print(result) + + # 获取指定直播间信息 + # room_id = "22816111" + # result = await self.fetch_live_room_detail(room_id=room_id) + # print(result) + + # 获取直播间视频流 + # room_id = "22816111" + # result = await self.fetch_user_live_videos_by_room_id(room_id=room_id) + # print(result) + + "-------------------------------------------------------utils接口列表-------------------------------------------------------" + # 通过bv号获得视频aid号 + # bv_id = 'BV1M1421t7hT' + # aid = await self.get_aid(bv_id=bv_id) + # print(aid) + + # 获取所有直播分区列表 + # result = await self.fetch_all_live_areas() + # print(result) + + # 根据uid生成wts及其对应w_rid参数(包含dm_img_inter参数) + # (仅示例 不同接口所需要传进去的参数不同)(待改进) + # uid = '178360345' + # w_rid = await self.uid_to_wrid(uid=uid) + # print(w_rid) + + +if __name__ == '__main__': + # 初始化 + BilibiliWebCrawler = BilibiliWebCrawler() + + # 开始时间 + start = time.time() + + asyncio.run(BilibiliWebCrawler.main()) + + # 结束时间 + end = time.time() + print(f"耗时：{end - start}") diff --git a/crawlers/bilibili/web/wrid.py b/crawlers/bilibili/web/wrid.py new file mode 100644 index 000000000..97ed1ef95 --- /dev/null +++ b/crawlers/bilibili/web/wrid.py @@ -0,0 +1,204 @@ +import urllib.parse + +def srotl(t, e): + return (t << e) | (t >> (32 - e)) + +def tendian(t): + if isinstance(t, int): + return (16711935 & srotl(t, 8)) | (4278255360 & srotl(t, 24)) + for e in range(len(t)): + t[e] = tendian(t[e]) + return t + +# 没问题 +def tbytes_to_words(t): + e = [] + r = 0 + for n in range(len(t)): + if r >> 5 >= len(e): + e.append(0) + e[r >> 5] |= t[n] << (24 - r % 32) + r += 8 + return e + +def jbinstring_to_bytes(t): + e = [] + for n in range(len(t)): + e.append(ord(t[n]) & 255) + return e + +# 没问题 +def estring_to_bytes(t): + return jbinstring_to_bytes(urllib.parse.unquote(urllib.parse.quote(t))) + +def _ff(t, e, n, r, o, i, a): + # 计算中间值 c + c = t + ((e & n) | (~e & r)) + (o & 0xFFFFFFFF) + a + # 将 c 转换为 32 位无符号整数 + c = c & 0xFFFFFFFF + # 左移和右移操作 + c = (c << i | c >> (32 - i)) & 0xFFFFFFFF + # 返回结果 + return (c + e) & 0xFFFFFFFF + +def _gg(t, e, n, r, o, i, a): + # 计算中间值 c + c = t + ((e & r) | (n & ~r)) + (o & 0xFFFFFFFF) + a + # 将 c 转换为 32 位无符号整数 + c = c & 0xFFFFFFFF + # 左移和右移操作 + c = (c << i | c >> (32 - i)) & 0xFFFFFFFF + # 返回结果 + return (c + e) & 0xFFFFFFFF + +def _hh(t, e, n, r, o, i, a): + # 计算中间值 c + c = t + (e ^ n ^ r) + (o & 0xFFFFFFFF) + a + # 将 c 转换为 32 位无符号整数 + c = c & 0xFFFFFFFF + # 左移和右移操作 + c = (c << i | c >> (32 - i)) & 0xFFFFFFFF + # 返回结果 + return (c + e) & 0xFFFFFFFF + +def _ii(t, e, n, r, o, i, a): + # 计算中间值 c + c = t + (n ^ (e | ~r)) + (o & 0xFFFFFFFF) + a + # 将 c 转换为 32 位无符号整数 + c = c & 0xFFFFFFFF + # 左移和右移操作 + c = (c << i | c >> (32 - i)) & 0xFFFFFFFF + # 返回结果 + return (c + e) & 0xFFFFFFFF + +def o(i, a): + if isinstance(i, str): + i = estring_to_bytes(i) + elif isinstance(i, (list, tuple)): + i = list(i) + elif not isinstance(i, (list, bytearray)): + i = str(i) + c = tbytes_to_words(i) + u = 8 * len(i) + s, l, f, p = 1732584193, -271733879, -1732584194, 271733878 + + for d in range(len(c)): + c[d] = (16711935 & (c[d] << 8 | c[d] >> 24)) | (4278255360 & (c[d] << 24 | c[d] >> 8)) + + # 确保列表 c 的长度足够大 + while len(c) <= (14 + ((u + 64 >> 9) << 4)): + c.append(0) + + c[u >> 5] |= 128 << (u % 32) + c[14 + ((u + 64 >> 9) << 4)] = u + + h, v, y, m = _ff, _gg, _hh, _ii + for d in range(0, len(c), 16): + g, b, w, A = s, l, f, p + # 确保在访问索引之前扩展列表的长度 + while len(c) <= d + 15: + c.append(0) + s = h(s, l, f, p, c[d + 0], 7, -680876936) + p = h(p, s, l, f, c[d + 1], 12, -389564586) + f = h(f, p, s, l, c[d + 2], 17, 606105819) + l = h(l, f, p, s, c[d + 3], 22, -1044525330) + s = h(s, l, f, p, c[d + 4], 7, -176418897) + p = h(p, s, l, f, c[d + 5], 12, 1200080426) + f = h(f, p, s, l, c[d + 6], 17, -1473231341) + l = h(l, f, p, s, c[d + 7], 22, -45705983) + s = h(s, l, f, p, c[d + 8], 7, 1770035416) + p = h(p, s, l, f, c[d + 9], 12, -1958414417) + f = h(f, p, s, l, c[d + 10], 17, -42063) + l = h(l, f, p, s, c[d + 11], 22, -1990404162) + s = h(s, l, f, p, c[d + 12], 7, 1804603682) + p = h(p, s, l, f, c[d + 13], 12, -40341101) + f = h(f, p, s, l, c[d + 14], 17, -1502002290) + s = v(s, l := h(l, f, p, s, c[d + 15], 22, 1236535329), f, p, c[d + 1], 5, -165796510) + p = v(p, s, l, f, c[d + 6], 9, -1069501632) + f = v(f, p, s, l, c[d + 11], 14, 643717713) + l = v(l, f, p, s, c[d + 0], 20, -373897302) + s = v(s, l, f, p, c[d + 5], 5, -701558691) + p = v(p, s, l, f, c[d + 10], 9, 38016083) + f = v(f, p, s, l, c[d + 15], 14, -660478335) + l = v(l, f, p, s, c[d + 4], 20, -405537848) + s = v(s, l, f, p, c[d + 9], 5, 568446438) + p = v(p, s, l, f, c[d + 14], 9, -1019803690) + f = v(f, p, s, l, c[d + 3], 14, -187363961) + l = v(l, f, p, s, c[d + 8], 20, 1163531501) + s = v(s, l, f, p, c[d + 13], 5, -1444681467) + p = v(p, s, l, f, c[d + 2], 9, -51403784) + f = v(f, p, s, l, c[d + 7], 14, 1735328473) + s = y(s, l := v(l, f, p, s, c[d + 12], 20, -1926607734), f, p, c[d + 5], 4, -378558) + p = y(p, s, l, f, c[d + 8], 11, -2022574463) + f = y(f, p, s, l, c[d + 11], 16, 1839030562) + l = y(l, f, p, s, c[d + 14], 23, -35309556) + s = y(s, l, f, p, c[d + 1], 4, -1530992060) + p = y(p, s, l, f, c[d + 4], 11, 1272893353) + f = y(f, p, s, l, c[d + 7], 16, -155497632) + l = y(l, f, p, s, c[d + 10], 23, -1094730640) + s = y(s, l, f, p, c[d + 13], 4, 681279174) + p = y(p, s, l, f, c[d + 0], 11, -358537222) + f = y(f, p, s, l, c[d + 3], 16, -722521979) + l = y(l, f, p, s, c[d + 6], 23, 76029189) + s = y(s, l, f, p, c[d + 9], 4, -640364487) + p = y(p, s, l, f, c[d + 12], 11, -421815835) + f = y(f, p, s, l, c[d + 15], 16, 530742520) + s = m(s, l := y(l, f, p, s, c[d + 2], 23, -995338651), f, p, c[d + 0], 6, -198630844) + p = m(p, s, l, f, c[d + 7], 10, 1126891415) + f = m(f, p, s, l, c[d + 14], 15, -1416354905) + l = m(l, f, p, s, c[d + 5], 21, -57434055) + s = m(s, l, f, p, c[d + 12], 6, 1700485571) + p = m(p, s, l, f, c[d + 3], 10, -1894986606) + f = m(f, p, s, l, c[d + 10], 15, -1051523) + l = m(l, f, p, s, c[d + 1], 21, -2054922799) + s = m(s, l, f, p, c[d + 8], 6, 1873313359) + p = m(p, s, l, f, c[d + 15], 10, -30611744) + f = m(f, p, s, l, c[d + 6], 15, -1560198380) + l = m(l, f, p, s, c[d + 13], 21, 1309151649) + s = m(s, l, f, p, c[d + 4], 6, -145523070) + p = m(p, s, l, f, c[d + 11], 10, -1120210379) + f = m(f, p, s, l, c[d + 2], 15, 718787259) + l = m(l, f, p, s, c[d + 9], 21, -343485551) + + s = (s + g) >> 0 & 0xFFFFFFFF + l = (l + b) >> 0 & 0xFFFFFFFF + f = (f + w) >> 0 & 0xFFFFFFFF + p = (p + A) >> 0 & 0xFFFFFFFF + + return tendian([s, l, f, p]) + +def twords_to_bytes(t): + e = [] + for n in range(0, 32 * len(t), 8): + e.append((t[n >> 5] >> (24 - n % 32)) & 255) + return e + +def tbytes_to_hex(t): + e = [] + for n in range(len(t)): + e.append(hex(t[n] >> 4)[2:]) + e.append(hex(t[n] & 15)[2:]) + return ''.join(e) + +def get_wrid(e): + n = None + i = twords_to_bytes(o(e, n)) + return tbytes_to_hex(i) + +# def test(): +# e = "dm_cover_img_str=QU5HTEUgKE5WSURJQSwgTlZJRElBIEdlRm9yY2UgUlRYIDMwNTAgTGFwdG9wIEdQVSAoMHgwMDAwMjVBMikgRGlyZWN0M0QxMSB2c181XzAgcHNfNV8wLCBEM0QxMSlHb29nbGUgSW5jLiAoTlZJRElBKQ&dm_img_inter=%7B%22ds%22%3A%5B%5D%2C%22wh%22%3A%5B3697%2C5674%2C33%5D%2C%22of%22%3A%5B222%2C444%2C222%5D%7D&dm_img_list=%5B%5D&dm_img_str=V2ViR0wgMS4wIChPcGVuR0wgRVMgMi4wIENocm9taXVtKQ&mid=3546666038725258&platform=web&token=&web_location=1550101&wts=1723867512ea1db124af3c7062474693fa704f4ff8" +# n = None +# x = o(e, n) +# i = twords_to_bytes(x) +# return tbytes_to_hex(i) + +# if __name__ == '__main__': +# # test() +# encode_query = "dm_cover_img_str=QU5HTEUgKE5WSURJQSwgTlZJRElBIEdlRm9yY2UgUlRYIDMwNTAgTGFwdG9wIEdQVSAoMHgwMDAwMjVBMikgRGlyZWN0M0QxMSB2c181XzAgcHNfNV8wLCBEM0QxMSlHb29nbGUgSW5jLiAoTlZJRElBKQ&dm_img_inter=%7B%22ds%22%3A%5B%5D%2C%22wh%22%3A%5B3697%2C5674%2C33%5D%2C%22of%22%3A%5B222%2C444%2C222%5D%7D&dm_img_list=%5B%5D&dm_img_str=V2ViR0wgMS4wIChPcGVuR0wgRVMgMi4wIENocm9taXVtKQ&mid=3546666038725258&platform=web&token=&web_location=1550101&wts=1723867512ea1db124af3c7062474693fa704f4ff8" +# wrid1 = main(encode_query) +# print(wrid1) +# +# js1 = open('./wrid.js', 'r', encoding='utf-8').read() +# wrid2 = execjs.compile(js1).call('main', encode_query) +# print(wrid2) +