diff --git a/PyPi/LICENSE b/PyPi/LICENSE new file mode 100644 index 0000000..fd91e63 --- /dev/null +++ b/PyPi/LICENSE @@ -0,0 +1,21 @@ +MIT License + +Copyright (c) 2021 Evil0ctal + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. diff --git a/PyPi/README.md b/PyPi/README.md new file mode 100644 index 0000000..5a11101 --- /dev/null +++ b/PyPi/README.md @@ -0,0 +1,450 @@ +# 欢迎使用 `Douyin_TikTok_Download_API` (抖音/TikTok无水印解析API) +![](https://views.whatilearened.today/views/github/Evil0ctal/TikTokDownloader_PyWebIO.svg) +[![GitHub license](https://img.shields.io/github/license/Evil0ctal/TikTokDownloader_PyWebIO)](https://github.com/Evil0ctal/TikTokDownloader_PyWebIO/blob/main/LICENSE) +[![GitHub issues](https://img.shields.io/github/issues/Evil0ctal/TikTokDownloader_PyWebIO)](https://github.com/Evil0ctal/TikTokDownloader_PyWebIO/issues) +[![GitHub forks](https://img.shields.io/github/forks/Evil0ctal/TikTokDownloader_PyWebIO)](https://github.com/Evil0ctal/TikTokDownloader_PyWebIO/network) +[![GitHub stars](https://img.shields.io/github/stars/Evil0ctal/TikTokDownloader_PyWebIO)](https://github.com/Evil0ctal/TikTokDownloader_PyWebIO/stargazers) + +Language: [[English](https://github.com/Evil0ctal/Douyin_TikTok_Download_API/blob/main/README.en.md)] [[简体中文](https://github.com/Evil0ctal/Douyin_TikTok_Download_API/blob/main/README.md)] [[繁体中文](https://github.com/Evil0ctal/Douyin_TikTok_Download_API/blob/main/README.zh-TW.md)] + +> Note: This API is applicable to Douyin and TikTok. Douyin is TikTok in China. You can distribute or modify the code at +> will, but please mark the original author. + +## 👻介绍 + +> 出于稳定性的考虑，暂时关闭演示站的/video(返回mp4文件)和/music(返回mp3文件) +> 这两个功能，同时结果页面的批量下载功能也暂时不可用，如有需求请自行部署，其他功能在演示站上仍正常使用，API服务器保证99%的时间正常运行，但不保证解析100%成功，如果解析失败请等一两分钟后重试。 + +🚀演示地址：[https://douyin.wtf/](https://douyin.wtf/) + +🛰API演示：[https://api.douyin.wtf/](https://api.douyin.wtf/) + +💾iOS快捷指令(中文): [点击获取](https://www.icloud.com/shortcuts/331073aca78345cf9ab4f73b6a457f97) ( +更新于2022/07/18，快捷指令可自动检查更新，安装一次即可。) + +🌎iOS Shortcut(English): [Click to get](https://www.icloud.com/shortcuts/83548306bc0c4f8ea563108f79c73f8d) (Updated on +2022/07/18, this shortcut will automatically check for updates, only need to install it once.) + +🗂快捷指令历史版本: [Shortcuts release](https://github.com/Evil0ctal/Douyin_TikTok_Download_API/issues/53) + +📦️Tiktok/抖音下载器(桌面应用)：[TikDown](https://github.com/Tairraos/TikDown/) + +本项目使用 [PyWebIO](https://github.com/pywebio/PyWebIO)、[Flask](https://github.com/pallets/flask) +，利用Python实现在线批量解析抖音的无水印视频/图集。 + +可用于下载作者禁止下载的视频，或者进行数据爬取等等，同时可搭配[iOS自带的快捷指令APP](https://apps.apple.com/cn/app/%E5%BF%AB%E6%8D%B7%E6%8C%87%E4%BB%A4/id915249334) +配合本项目API实现应用内下载。 + +快捷指令需要在抖音或TikTok的APP内，选择你想要保存的视频，点击分享按钮，然后找到 "抖音TikTok无水印下载" +这个选项，如遇到通知询问是否允许快捷指令访问xxxx (域名或服务器)，需要点击允许才可以正常使用，下载成功的视频或图集会保存在一个专门的相册中以方便浏览。 + +## 💡项目文件结构 + +``` +# 请根据需要自行修改config.ini中的内容 +. +└── Douyin_TikTok_Download_API/ + ├── /static(静态前端资源) + ├── web_zh.py(网页入口) + ├── web_api.py(API) + ├── scraper.py(解析库) + ├── config.ini(所有项目的配置文件，包含端口及代理等，如需请自行修改该文件。) + ├── logs.txt(错误日志，自动生成。) + └── API_logs.txt(API调用日志，自动生成。) +``` + +## 💯已支持功能： + +- 支持抖音视频/图集解析 +- 支持海外TikTok视频解析 +- 支持批量解析(支持抖音/TikTok混合解析) +- 解析结果页批量下载无水印视频 +- 支持API调用 +- 支持使用代理解析 +- 支持[iOS快捷指令](https://apps.apple.com/cn/app/%E5%BF%AB%E6%8D%B7%E6%8C%87%E4%BB%A4/id915249334)实现应用内下载无水印视频/图集 + +--- + +## 🤦‍后续功能： + +- [ ] 支持输入(抖音/TikTok)作者主页链接实现批量解析 + +--- + +## 🧭运行说明(经过测试过的Python版本为3.8): +> 🚨如果你要部署本项目，请参考部署方式([Docker部署](https://github.com/Evil0ctal/Douyin_TikTok_Download_API/blob/main/README.md#%E9%83%A8%E7%BD%B2%E6%96%B9%E5%BC%8F%E4%BA%8C-docker "Docker部署"), [手动部署](https://github.com/Evil0ctal/Douyin_TikTok_Download_API/blob/main/README.md#%E9%83%A8%E7%BD%B2%E6%96%B9%E5%BC%8F%E4%B8%80-%E6%89%8B%E5%8A%A8%E9%83%A8%E7%BD%B2 "手动部署")) + +- 克隆本仓库： + +```console +git clone https://github.com/Evil0ctal/Douyin_TikTok_Download_API.git +``` + +- 移动至仓库目录： + +```console +cd Douyin_TikTok_Download_API +``` + +- 安装依赖库： + +```console +pip install -r requirements.txt +``` + +- 修改config.ini(可选)： + +```console +vim config.ini +``` + +- 网页解析 + +```console +# 运行web_zh.py +python3 web_zh.py +``` + +- API + +```console +# 运行web_api.py +python3 web_api.py +``` + +- 调用解析库 + +```python +# 将scraper.py拷贝至你的项目目录 +# 在该项目中导入scraper.py +from scraper import Scraper + +api = Scraper() +# 解析Douyin视频/图集 +douyin_data = api.douyin(input('在此输入抖音分享口令/链接：')) +# 返回字典 +print(douyin_data) +# 解析TikTok视频/图集 +tiktok_data = api.tiktok(input('在此输入TikTok分享口令/链接：')) +# 返回字典 +print(tiktok_data) +``` + +- 入口(端口可在config.ini文件中修改) + +```text +网页入口: +http://localhost(服务器IP):5000/ +API入口: +http://localhost(服务器IP):2333/ +``` + +## 🗺️支持的提交格式(包含但不仅限于以下例子)： + +- 抖音分享口令 (APP内复制) + +```text +例子：7.43 pda:/ 让你在几秒钟之内记住我 https://v.douyin.com/L5pbfdP/ 复制此链接，打开Dou音搜索，直接观看视频！ +``` + +- 抖音短网址 (APP内复制) + +```text +例子：https://v.douyin.com/L4FJNR3/ +``` + +- 抖音正常网址 (网页版复制) + +```text +例子： +https://www.douyin.com/video/6914948781100338440 +``` + +- 抖音发现页网址 (APP复制) + +```text +例子： +https://www.douyin.com/discover?modal_id=7069543727328398622 +``` + +- TikTok短网址 (APP内复制) + +```text +例子： +https://vm.tiktok.com/TTPdkQvKjP/ +``` + +- TikTok正常网址 (网页版复制) + +```text +例子： +https://www.tiktok.com/@tvamii/video/7045537727743380782 +``` + +- 抖音/TikTok批量网址(无需使用符合隔开) + +```text +例子： +2.84 nqe:/ 骑白马的也可以是公主%%百万转场变身 https://v.douyin.com/L4FJNR3/ 复制此链接，打开Dou音搜索，直接观看视频！ +8.94 mDu:/ 让你在几秒钟之内记住我 https://v.douyin.com/L4NpDJ6/ 复制此链接，打开Dou音搜索，直接观看视频！ +9.94 LWz:/ ok我坦白交代 %%knowknow https://v.douyin.com/L4NEvNn/ 复制此链接，打开Dou音搜索，直接观看视频！ +https://www.tiktok.com/@gamer/video/7054061777033628934 +https://www.tiktok.com/@off.anime_rei/video/7059609659690339586 +https://www.tiktok.com/@tvamii/video/7045537727743380782 +``` + +## 🛰️API使用 + +API可将请求参数转换为需要提取的无水印视频/图片直链，配合IOS捷径可实现应用内下载。 + +- 解析请求参数 + +```text +http://localhost(服务器IP):2333/api?url="复制的(抖音/TikTok)口令/链接" +``` + +- 返回参数 + +> 抖音视频 + +```json +{ + "analyze_time": "1.9043s", + "api_url": "https://www.iesdouyin.com/web/api/v2/aweme/iteminfo/?item_ids=6918273131559881997", + "nwm_video_url": "http://v3-dy-o.zjcdn.com/23f0dec312ede563bef881af9a88bdc7/624dd965/video/tos/cn/tos-cn-ve-15/eccedcf4386948f5b5a1f0bcfb3dcde9/?a=1128&br=2537&bt=2537&cd=0%7C0%7C0%7C0&ch=0&cr=0&cs=0&cv=1&dr=0&ds=3&er=&ft=sYGC~3E7nz7Th1PZSDXq&l=202204070118030102080650132A21E31F&lr=&mime_type=video_mp4&net=0&pl=0&qs=0&rc=M3hleDRsODlkMzMzaGkzM0ApODpmNWc4ODs5N2lmNzg5aWcpaGRqbGRoaGRmLi4ybnBrbjYuYC0tYy0wc3MtYmJjNTM2NjAtNDFjMzJgOmNwb2wrbStqdDo%3D&vl=&vr=", + "original_url": "https://v.douyin.com/L4FJNR3/", + "platform": "douyin", + "status": "success", + "url_type": "video", + "video_author": "Real机智张", + "video_author_id": "Rea1yaoyue", + "video_author_signature": "", + "video_author_uid": "59840491348", + "video_aweme_id": "6918273131559881997", + "video_comment_count": "89145", + "video_create_time": "1610786002", + "video_digg_count": "2968195", + "video_hashtags": [ + "百万转场变身" + ], + "video_music": "https://sf3-cdn-tos.douyinstatic.com/obj/ies-music/6910889805266504461.mp3", + "video_music_author": "梅尼耶", + "video_music_id": "6910889820861451000", + "video_music_mid": "6910889820861451021", + "video_music_title": "@梅尼耶创作的原声", + "video_play_count": "0", + "video_share_count": "74857", + "video_title": "骑白马的也可以是公主#百万转场变身", + "wm_video_url": "https://aweme.snssdk.com/aweme/v1/playwm/?video_id=v0300ffe0000c01a96q5nis1qu5b1u10&ratio=720p&line=0" +} +``` + +> 抖音图集 + +```json +{ + "album_author": "治愈图集", + "album_author_id": "ZYTJ2002", + "album_author_signature": "取无水印图", + "album_author_uid": "449018054867063", + "album_aweme_id": "7015137063141920030", + "album_comment_count": "5436", + "album_create_time": "1633338878", + "album_digg_count": "193734", + "album_hashtags": [ + "晚霞", + "治愈系", + "落日余晖", + "日落🌄" + ], + "album_list": [ + "https://p26-sign.douyinpic.com/tos-cn-i-0813/5223757a7bef4f8480cd25d0fa2d2d94~noop.webp?x-expires=1651856400&x-signature=K1VjJdWTHCAaYSz14y6NumjjtfI%3D&from=4257465056&s=PackSourceEnum_DOUYIN_REFLOW&se=false&biz_tag=aweme_images&l=202204070120460102101050412A210A47", + "https://p26-sign.douyinpic.com/tos-cn-i-0813/d99467672da840908acccf2d2b4b7ef7~noop.webp?x-expires=1651856400&x-signature=ncBb8Tt7z4PmpUyiCNr%2FJYnwRSA%3D&from=4257465056&s=PackSourceEnum_DOUYIN_REFLOW&se=false&biz_tag=aweme_images&l=202204070120460102101050412A210A47", + "https://p26-sign.douyinpic.com/tos-cn-i-0813/5c2562210b1a4d4c99d6d4dbd2f23f2b~noop.webp?x-expires=1651856400&x-signature=Rsmplb53IKfvKd3mmIb4iQNhlIE%3D&from=4257465056&s=PackSourceEnum_DOUYIN_REFLOW&se=false&biz_tag=aweme_images&l=202204070120460102101050412A210A47", + "https://p26-sign.douyinpic.com/tos-cn-i-0813/9bb74c0c6aff4217bd1491a077b2c817~noop.webp?x-expires=1651856400&x-signature=BLRyHoKP0ybIci57yneOca62dxI%3D&from=4257465056&s=PackSourceEnum_DOUYIN_REFLOW&se=false&biz_tag=aweme_images&l=202204070120460102101050412A210A47" + ], + "album_music": "https://sf6-cdn-tos.douyinstatic.com/obj/ies-music/6978805801733442341.mp3", + "album_music_author": "魏同学", + "album_music_id": "6978805810365271000", + "album_music_mid": "6978805810365270791", + "album_music_title": "@魏同学创作的原声", + "album_play_count": "0", + "album_share_count": "30717", + "album_title": "“山海自有归期 风雨自有相逢 意难平终将和解 万事终将如意”#晚霞 #治愈系 #落日余晖 #日落🌄", + "analyze_time": "1.0726s", + "api_url": "https://www.iesdouyin.com/web/api/v2/aweme/iteminfo/?item_ids=7015137063141920030", + "original_url": "https://v.douyin.com/Nb8jysN/", + "platform": "douyin", + "status": "success", + "url_type": "album" +} +``` + +> TikTok视频 + +```JSON +{ + "analyze_time": "5.0863s", + "nwm_video_url": "https://v19.tiktokcdn-us.com/cfa357dadd8f913f013a6d0b0dca293f/624e20fa/video/tos/useast5/tos-useast5-ve-0068c003-tx/3296231486014755a1b81aa70c349a53/?a=1233&br=6498&bt=3249&cd=0%7C0%7C0%7C3&ch=0&cr=3&cs=0&cv=1&dr=0&ds=6&er=&ft=bY1KJnB4TJBS6BMy-L1iVKP&l=20220406172333010113135214232FAB56&lr=all&mime_type=video_mp4&net=0&pl=0&qs=0&rc=MzpsaGY6Zjo7PDMzZzczNEApNjY6ZTtkOzxpN2Q3PDo5OmdgZ2BtcjQwai9gLS1kMS9zczJhLTEzYjEuMTJeXzQyLmM6Yw%3D%3D&vl=&vr=", + "original_url": "https://www.tiktok.com/@oregonzoo/video/7080938094823738666", + "platform": "tiktok", + "status": "success", + "url_type": "video", + "video_author": "oregonzoo", + "video_author_SecId": "MS4wLjABAAAArWNQ8-AZN6CxWOkqdeWsMBUuLDmJt8TWUAk0S4aWDW5V5EoqRbuczhaLnxJHCGob", + "video_author_diggCount": 94, + "video_author_followerCount": 1800000, + "video_author_followingCount": 39, + "video_author_heartCount": 29700000, + "video_author_id": "6699816060206171141", + "video_author_nickname": "Oregon Zoo", + "video_author_videoCount": 264, + "video_aweme_id": "7080938094823738666", + "video_comment_count": 61, + "video_create_time": "1648659375", + "video_digg_count": 11800, + "video_hashtags": [ + "redpanda", + "boop", + "sunshine" + ], + "video_music": "https://sf16.tiktokcdn-us.com/obj/ies-music-tx/7075363935741856558.mp3", + "video_music_author": "Gilderoy Dauterive", + "video_music_id": "7075363884613356330", + "video_music_title": "Be the Sunshine", + "video_music_url": "https://sf16.tiktokcdn-us.com/obj/ies-music-tx/7075363935741856558.mp3", + "video_play_count": 60100, + "video_ratio": "720p", + "video_share_count": 298, + "video_title": "Moshu ✨ #redpanda #boop #sunshine", + "wm_video_url": "https://v16m-webapp.tiktokcdn-us.com/0394b9183a5852d4392a7e804bf78c55/624e20f6/video/tos/useast5/tos-useast5-ve-0068c001-tx/fc63ae232e70466398b55ccf97eb3c67/?a=1988&br=6468&bt=3234&cd=0%7C0%7C1%7C0&ch=0&cr=0&cs=0&cv=1&dr=0&ds=3&er=&ft=XY53A3E7nz7Th-pZSDXq&l=202204061723290101131351171341B9BB&lr=tiktok_m&mime_type=video_mp4&net=0&pl=0&qs=0&rc=MzpsaGY6Zjo7PDMzZzczNEApOjo4aDMzZmRlN2loOWk6ZWdgZ2BtcjQwai9gLS1kMS9zczBhNGA0LTIwNjNiYDQ2YmE6Yw%3D%3D&vl=&vr=" +} +``` + +- 下载视频请求参数 + +```text +http://localhost(服务器IP):2333/video?url="复制的(抖音/TikTok)口令/链接" +# 返回无水印mp4文件 +``` + +- 下载音频请求参数 + +```text +http://localhost(服务器IP):2333/music?url="复制的(抖音/TikTok)口令/链接" +# 返回mp3文件 +``` + +--- + +## 💾部署(方式一 手动部署) + +> 注： +> 截图可能因更新问题与文字不符，一切请优先参照文字叙述。 + +> 最好将本项目部署至海外服务器(优先选择美国地区的服务器)，否则可能会出现奇怪的问题。 + +例子： +项目部署在国内服务器，而人在美国，点击结果页面链接报错403 ，目测与抖音CDN有关系。 +项目部署在韩国服务器，解析TikTok报错 ，目测TikTok对某些地区或IP进行了限制。 + +> 使用宝塔Linux面板进行部署( +> 中文宝塔要强制绑定手机号了，很流氓且无法绕过，建议使用宝塔国际版，谷歌搜索关键字aapanel自行安装，部署步骤相似。) + +- 首先要去安全组开放5000和2333端口（Web默认5000，API默认2333，可以在文件config.ini中修改。） +- 在宝塔应用商店内搜索python并安装项目管理器 (推荐使用1.9版本) + +![](https://raw.githubusercontent.com/Evil0ctal/TikTokDownloader_PyWebIO/main/Screenshots/BT_Linux_Panel_Deploy_1.png) + +--- + +- 创建一个项目名字随意 +- 路径选择你上传文件的路径 +- Python版本需要至少3以上(在左侧版本管理中自行安装) +- 框架修改为`Flask` +- 启动方式修改为`python` +- Web启动文件选择`web_zh.py` +- API启动文件选择`web_api.py` +- 勾选安装模块依赖 +- 开机启动随意 +- 如果宝塔运行了`Nginx`等其他服务时请自行判断端口是否被占用，运行端口可在文件config.ini中修改。 + +![](https://raw.githubusercontent.com/Evil0ctal/TikTokDownloader_PyWebIO/main/Screenshots/BT_Linux_Panel_Deploy_2.png) + +- 如果有大量请求请使用进程守护启动防止进程关闭 + +--- + +## 💾部署(方式二 Docker) + +- 安装docker + +```yaml +curl -fsSL get.docker.com -o get-docker.sh&&sh get-docker.sh &&systemctl enable docker&&systemctl start docker +``` + +- 留下config.int和docker-compose.yml文件即可 +- 运行命令,让容器在后台运行 + +```yaml +docker compose up -d +``` + +- 查看容器日志 + +```yaml +docker logs -f douyin_tiktok_download_api +``` + +- 删除容器 + +```yaml +docker rm -f douyin_tiktok_download_api +``` + +- 更新 + +```yaml +docker compose pull && docker compose down && docker compose up -d +``` + +## 🎉截图 + +> 注： +> 截图可能因更新问题与文字不符，一切请优先参照文字叙述。 + +- 主界面 + +![](https://github.com/Evil0ctal/TikTokDownloader_PyWebIO/blob/main/Screenshots/home.png) + +--- + +- 解析完成 + +> 单个 + +![](https://github.com/Evil0ctal/TikTokDownloader_PyWebIO/blob/main/Screenshots/single_result.png) + +--- + +> 批量 + +![](https://github.com/Evil0ctal/TikTokDownloader_PyWebIO/blob/main/Screenshots/multi_results.png) + +--- + +- API提交/返回 + +> 视频返回值 + +![](https://github.com/Evil0ctal/TikTokDownloader_PyWebIO/blob/main/Screenshots/api_video_result.png) + +> 图集返回值 + +![](https://github.com/Evil0ctal/TikTokDownloader_PyWebIO/blob/main/Screenshots/api_image_result.png) + +> TikTok返回值 + +![](https://raw.githubusercontent.com/Evil0ctal/TikTokDownloader_PyWebIO/main/Screenshots/tiktok_API.png) + +--- diff --git a/PyPi/dist/DT_Scraper-1.0.0.tar.gz b/PyPi/dist/DT_Scraper-1.0.0.tar.gz new file mode 100644 index 0000000..15e74b5 Binary files /dev/null and b/PyPi/dist/DT_Scraper-1.0.0.tar.gz differ diff --git a/PyPi/pyproject.toml b/PyPi/pyproject.toml new file mode 100644 index 0000000..0ad39d0 --- /dev/null +++ b/PyPi/pyproject.toml @@ -0,0 +1,6 @@ +[build-system] +requires = [ + "setuptools>=42", + "wheel" +] +build-backend = "setuptools.build_meta" \ No newline at end of file diff --git a/PyPi/setup.py b/PyPi/setup.py new file mode 100644 index 0000000..9b95be6 --- /dev/null +++ b/PyPi/setup.py @@ -0,0 +1,53 @@ +#! /usr/bin/env python +# -*- coding: utf-8 -*- +# RUN Command Line: +# python3 setup.py sdist (Build-check dist folder) +# python3 -m twine upload --repository pypi dist/* (Upload to PyPi) + +try: + from setuptools import setup +except ImportError: + from distutils.core import setup +import setuptools + +setup( + name='DT_Scraper', # 包的名字 + author='Evil0ctal', # 作者 + version='1.0.0', # 版本号 + license='MIT', + + description='Douyin/TikTok crawler and no watermark video download.', # 描述 + long_description='''Douyin/TikTok crawler and no watermark video download.''', + author_email='evil0ctal1985@gmail.com', # 你的邮箱** + url='https://github.com/Evil0ctal/Douyin_TikTok_Download_API', # 可以写github上的地址，或者其他地址 + # 包内需要引用的文件夹 + # packages=setuptools.find_packages(exclude=['url2io',]), + packages=["DT_scraper"], + # keywords='NLP,tokenizing,Chinese word segementation', + # package_dir={'jieba':'jieba'}, + # package_data={'jieba':['*.*','finalseg/*','analyse/*','posseg/*']}, + + # 依赖包 + install_requires=[ + 'requests', + "tenacity", + ], + classifiers=[ + # 'Development Status :: 4 - Beta', + # 'Operating System :: Microsoft' # 你的操作系统 OS Independent Microsoft + 'Intended Audience :: Developers', + # 'License :: OSI Approved :: MIT License', + # 'License :: OSI Approved :: BSD License', # BSD认证 + 'Programming Language :: Python', # 支持的语言 + 'Programming Language :: Python :: 3', # python版本 。。。 + 'Programming Language :: Python :: 3.4', + 'Programming Language :: Python :: 3.5', + 'Programming Language :: Python :: 3.6', + 'Programming Language :: Python :: 3.7', + 'Programming Language :: Python :: 3.8', + 'Programming Language :: Python :: 3.9', + 'Programming Language :: Python :: 3.10', + 'Topic :: Software Development :: Libraries' + ], + zip_safe=True, +) \ No newline at end of file diff --git a/PyPi/src/DT_Scraper.egg-info/PKG-INFO b/PyPi/src/DT_Scraper.egg-info/PKG-INFO new file mode 100644 index 0000000..d29f4ce --- /dev/null +++ b/PyPi/src/DT_Scraper.egg-info/PKG-INFO @@ -0,0 +1,27 @@ +Metadata-Version: 2.1 +Name: DT-Scraper +Version: 1.0.0 +Summary: Douyin/TikTok crawler and no watermark video download. +Home-page: https://github.com/Evil0ctal/Douyin_TikTok_Download_API +Author: Evil0ctal +Author-email: evil0ctal1985@gmail.com +License: MIT +Project-URL: Bug Tracker, https://github.com/Evil0ctal/Douyin_TikTok_Download_API/issues +Platform: UNKNOWN +Classifier: Intended Audience :: Developers +Classifier: Programming Language :: Python +Classifier: Programming Language :: Python :: 3 +Classifier: Programming Language :: Python :: 3.4 +Classifier: Programming Language :: Python :: 3.5 +Classifier: Programming Language :: Python :: 3.6 +Classifier: Programming Language :: Python :: 3.7 +Classifier: Programming Language :: Python :: 3.8 +Classifier: Programming Language :: Python :: 3.9 +Classifier: Programming Language :: Python :: 3.10 +Classifier: Topic :: Software Development :: Libraries +Requires-Python: >=3.6 +Description-Content-Type: text/markdown +License-File: LICENSE + +Douyin/TikTok crawler and no watermark video download. + diff --git a/PyPi/src/DT_Scraper.egg-info/SOURCES.txt b/PyPi/src/DT_Scraper.egg-info/SOURCES.txt new file mode 100644 index 0000000..4d821d6 --- /dev/null +++ b/PyPi/src/DT_Scraper.egg-info/SOURCES.txt @@ -0,0 +1,13 @@ +LICENSE +README.md +pyproject.toml +setup.cfg +setup.py +src/DT_Scraper.egg-info/PKG-INFO +src/DT_Scraper.egg-info/SOURCES.txt +src/DT_Scraper.egg-info/dependency_links.txt +src/DT_Scraper.egg-info/requires.txt +src/DT_Scraper.egg-info/top_level.txt +src/DT_Scraper.egg-info/zip-safe +src/DT_scraper/__init__.py +src/DT_scraper/scraper.py \ No newline at end of file diff --git a/PyPi/src/DT_Scraper.egg-info/dependency_links.txt b/PyPi/src/DT_Scraper.egg-info/dependency_links.txt new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/PyPi/src/DT_Scraper.egg-info/dependency_links.txt @@ -0,0 +1 @@ + diff --git a/PyPi/src/DT_Scraper.egg-info/requires.txt b/PyPi/src/DT_Scraper.egg-info/requires.txt new file mode 100644 index 0000000..365ee77 --- /dev/null +++ b/PyPi/src/DT_Scraper.egg-info/requires.txt @@ -0,0 +1,2 @@ +requests +tenacity diff --git a/PyPi/src/DT_Scraper.egg-info/top_level.txt b/PyPi/src/DT_Scraper.egg-info/top_level.txt new file mode 100644 index 0000000..742d7f0 --- /dev/null +++ b/PyPi/src/DT_Scraper.egg-info/top_level.txt @@ -0,0 +1 @@ +DT_scraper diff --git a/PyPi/src/DT_Scraper.egg-info/zip-safe b/PyPi/src/DT_Scraper.egg-info/zip-safe new file mode 100644 index 0000000..d3f5a12 --- /dev/null +++ b/PyPi/src/DT_Scraper.egg-info/zip-safe @@ -0,0 +1 @@ + diff --git a/PyPi/src/DT_scraper/__init__.py b/PyPi/src/DT_scraper/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/PyPi/src/DT_scraper/requirements.txt b/PyPi/src/DT_scraper/requirements.txt new file mode 100644 index 0000000..60444cf --- /dev/null +++ b/PyPi/src/DT_scraper/requirements.txt @@ -0,0 +1,2 @@ +requests==2.28.0 +tenacity==8.0.1 \ No newline at end of file diff --git a/PyPi/src/DT_scraper/scraper.py b/PyPi/src/DT_scraper/scraper.py new file mode 100644 index 0000000..b496494 --- /dev/null +++ b/PyPi/src/DT_scraper/scraper.py @@ -0,0 +1,535 @@ +#!/usr/bin/env python +# -*- encoding: utf-8 -*- +# @Author: https://github.com/Evil0ctal/ +# @Time: 2021/11/06 +# @Update: 2022/09/01 +# @Function: +# 核心代码，估值1块(๑•̀ㅂ•́)و✧ +# 用于爬取Douyin/TikTok数据并以字典形式返回。 +# input link, output dictionary. + + +import re +import json +import requests +from tenacity import * + + +class Scraper: + """ + Scraper.douyin(link): + 输入参数为抖音视频/图集链接，完成解析后返回字典。 + + Scraper.tiktok(link): + 输入参数为TikTok视频/图集链接，完成解析后返回字典。 + """ + + def __init__(self): + self.headers = { + 'user-agent': 'Mozilla/5.0 (Linux; Android 8.0; Pixel 2 Build/OPD3.170816.012) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Mobile Safari/537.36 Edg/87.0.664.66' + } + self.tiktok_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=0.9", + "authority": "www.tiktok.com", + "Accept-Encoding": "gzip, deflate", + "Connection": "keep-alive", + "Host": "www.tiktok.com", + "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) coc_coc_browser/86.0.170 Chrome/80.0.3987.170 Safari/537.36", + } + + @retry(stop=stop_after_attempt(3), wait=wait_random(min=1, max=2)) + def douyin(self, original_url: str, proxies: dict = None): + """ + 利用官方接口解析抖音链接信息 + :param proxies: pip install DT-Scraper, Default not use proxy. + :param original_url: 抖音/TikTok链接(支持长/短链接) TikTok&Douyin URL + :return:包含信息的字典 Dictionary data + """ + headers = self.headers + try: + # 开始时间 + start = time.time() + # 判断是否为个人主页链接 + if 'user' in original_url: + return {'status': 'failed', 'reason': '暂不支持个人主页批量解析', 'function': 'Scraper.douyin()', + 'value': original_url} + else: + # 原视频链接 + r = requests.get(url=original_url, headers=headers, allow_redirects=False, proxies=proxies) + try: + # 2021/12/11 发现抖音做了限制，会自动重定向网址，但是可以从回执头中获取 + long_url = r.headers['Location'] + # 判断是否为个人主页链接 + if 'user' in long_url: + return {'status': 'failed', 'reason': '暂不支持个人主页批量解析', + 'function': 'Scraper.douyin()', + 'value': original_url} + except: + # 报错后判断为长链接，直接截取视频id + long_url = original_url + # 正则匹配出视频ID + try: + # 第一种链接类型 + # https://www.douyin.com/video/7086770907674348841 + key = re.findall('/video/(\d+)?', long_url)[0] + print('视频ID为: {}'.format(key)) + except Exception: + # 第二种链接类型 + # https://www.douyin.com/discover?modal_id=7086770907674348841 + key = re.findall('modal_id=(\d+)', long_url)[0] + print('视频ID为: {}'.format(key)) + # 构造抖音API链接 + api_url = f'https://www.iesdouyin.com/web/api/v2/aweme/iteminfo/?item_ids={key}' + print("正在请求抖音API链接: " + '\n' + api_url) + # 将回执以JSON格式处理 + js = json.loads(requests.get(url=api_url, headers=headers, proxies=proxies).text) + # 判断是否为图集 + if js['item_list'][0]['images'] is not None: + print("类型 = 图集") + # 类型为图集 + url_type = 'album' + # 图集标题 + album_title = str(js['item_list'][0]['desc']) + # 图集作者昵称 + album_author = str(js['item_list'][0]['author']['nickname']) + # 图集作者签名 + album_author_signature = str(js['item_list'][0]['author']['signature']) + # 图集作者UID + album_author_uid = str(js['item_list'][0]['author']['uid']) + # 图集作者抖音号 + album_author_id = str(js['item_list'][0]['author']['unique_id']) + if album_author_id == "": + # 如果作者未修改过抖音号，应使用此值以避免无法获取其抖音ID + album_author_id = str(js['item_list'][0]['author']['short_id']) + # 尝试获取图集BGM信息 + for key in js['item_list'][0]: + if key == 'music': + # 图集BGM链接 + album_music = str(js['item_list'][0]['music']['play_url']['url_list'][0]) + # 图集BGM标题 + album_music_title = str(js['item_list'][0]['music']['title']) + # 图集BGM作者 + album_music_author = str(js['item_list'][0]['music']['author']) + # 图集BGM ID + album_music_id = str(js['item_list'][0]['music']['id']) + # 图集BGM MID + album_music_mid = str(js['item_list'][0]['music']['mid']) + else: + # 图集BGM链接 + album_music = album_music_title = album_music_author = album_music_id = album_music_mid = 'No BGM found ' + # 图集ID + album_aweme_id = str(js['item_list'][0]['statistics']['aweme_id']) + # 评论数量 + album_comment_count = str(js['item_list'][0]['statistics']['comment_count']) + # 获赞数量 + album_digg_count = str(js['item_list'][0]['statistics']['digg_count']) + # 播放次数 + album_play_count = str(js['item_list'][0]['statistics']['play_count']) + # 分享次数 + album_share_count = str(js['item_list'][0]['statistics']['share_count']) + # 上传时间戳 + album_create_time = str(js['item_list'][0]['create_time']) + # 将话题保存在列表中 + album_hashtags = [] + for tag in js['item_list'][0]['text_extra']: + album_hashtags.append(tag['hashtag_name']) + # 将无水印图片链接保存在列表中 + images_list = [] + for data in js['item_list'][0]['images']: + images_list.append(data['url_list'][0]) + # 结束时间 + end = time.time() + # 解析时间 + analyze_time = format((end - start), '.4f') + # 将信息储存在字典中 + album_data = {'status': 'success', + 'analyze_time': (analyze_time + 's'), + 'url_type': url_type, + 'platform': 'douyin', + 'original_url': original_url, + 'api_url': api_url, + 'album_aweme_id': album_aweme_id, + 'album_title': album_title, + 'album_author': album_author, + 'album_author_signature': album_author_signature, + 'album_author_uid': album_author_uid, + 'album_author_id': album_author_id, + 'album_music': album_music, + 'album_music_title': album_music_title, + 'album_music_author': album_music_author, + 'album_music_id': album_music_id, + 'album_music_mid': album_music_mid, + 'album_comment_count': album_comment_count, + 'album_digg_count': album_digg_count, + 'album_play_count': album_play_count, + 'album_share_count': album_share_count, + 'album_create_time': album_create_time, + 'album_list': images_list, + 'album_hashtags': album_hashtags} + return album_data + else: + print("类型 = 视频") + # 类型为视频 + url_type = 'video' + # 视频标题 + video_title = str(js['item_list'][0]['desc']) + # 视频作者昵称 + video_author = str(js['item_list'][0]['author']['nickname']) + # 视频作者抖音号 + video_author_id = str(js['item_list'][0]['author']['unique_id']) + if video_author_id == "": + # 如果作者未修改过抖音号，应使用此值以避免无法获取其抖音ID + video_author_id = str(js['item_list'][0]['author']['short_id']) + # vid + vid = str(js['item_list'][0]['video']['vid']) + # 无水印1080p视频链接 + try: + r = requests.get( + "https://aweme.snssdk.com/aweme/v1/play/?video_id={}&radio=1080p&line=0".format(vid), + headers=headers, allow_redirects=False, proxies=proxies) + nwm_video_url_1080p = r.headers['Location'] + except: + nwm_video_url_1080p = "None" + # 有水印视频链接 + wm_video_url = str(js['item_list'][0]['video']['play_addr']['url_list'][0]) + # 无水印视频链接 (在回执JSON中将关键字'playwm'替换为'play'即可获得无水印地址) + nwm_video_url = str(js['item_list'][0]['video']['play_addr']['url_list'][0]).replace('playwm', + 'play') + # 去水印后视频链接(2022年1月1日抖音APi获取到的URL会进行跳转，需要在Location中获取直链) + r = requests.get(url=nwm_video_url, headers=headers, allow_redirects=False, proxies=proxies) + video_url = r.headers['Location'] + # 视频作者签名 + video_author_signature = str(js['item_list'][0]['author']['signature']) + # 视频作者UID + video_author_uid = str(js['item_list'][0]['author']['uid']) + # 尝试获取视频背景音乐 + for key in js['item_list'][0]: + if key == 'music': + if len(js['item_list'][0]['music']['play_url']['url_list']) != 0: + # 视频BGM链接 + video_music = str(js['item_list'][0]['music']['play_url']['url_list'][0]) + else: + video_music = 'No BGM found' + # 视频BGM标题 + video_music_title = str(js['item_list'][0]['music']['title']) + # 视频BGM作者 + video_music_author = str(js['item_list'][0]['music']['author']) + # 视频BGM ID + video_music_id = str(js['item_list'][0]['music']['id']) + # 视频BGM MID + video_music_mid = str(js['item_list'][0]['music']['mid']) + else: + video_music = video_music_title = video_music_author = video_music_id = video_music_mid = 'No BGM found' + # 视频ID + video_aweme_id = str(js['item_list'][0]['statistics']['aweme_id']) + # 评论数量 + video_comment_count = str(js['item_list'][0]['statistics']['comment_count']) + # 获赞数量 + video_digg_count = str(js['item_list'][0]['statistics']['digg_count']) + # 播放次数 + video_play_count = str(js['item_list'][0]['statistics']['play_count']) + # 分享次数 + video_share_count = str(js['item_list'][0]['statistics']['share_count']) + # 上传时间戳 + video_create_time = str(js['item_list'][0]['create_time']) + # 视频封面 + video_cover = js['item_list'][0]['video']['cover']['url_list'][0] + # 视频动态封面 + video_dynamic_cover = js['item_list'][0]['video']['dynamic_cover']['url_list'][0] + # 视频原始封面 + video_origin_cover = js['item_list'][0]['video']['origin_cover']['url_list'][0] + # 将话题保存在列表中 + video_hashtags = [] + for tag in js['item_list'][0]['text_extra']: + video_hashtags.append(tag['hashtag_name']) + # 结束时间 + end = time.time() + # 解析时间 + analyze_time = format((end - start), '.4f') + # 返回包含数据的字典 + video_data = {'status': 'success', + 'analyze_time': (analyze_time + 's'), + 'url_type': url_type, + 'platform': 'douyin', + 'original_url': original_url, + 'api_url': api_url, + 'video_title': video_title, + 'nwm_video_url': video_url, + 'nwm_video_url_1080p': nwm_video_url_1080p, + 'wm_video_url': wm_video_url, + 'video_aweme_id': video_aweme_id, + 'video_author': video_author, + 'video_author_signature': video_author_signature, + 'video_author_uid': video_author_uid, + 'video_author_id': video_author_id, + 'video_music': video_music, + 'video_music_title': video_music_title, + 'video_music_author': video_music_author, + 'video_music_id': video_music_id, + 'video_music_mid': video_music_mid, + 'video_comment_count': video_comment_count, + 'video_digg_count': video_digg_count, + 'video_play_count': video_play_count, + 'video_share_count': video_share_count, + 'video_create_time': video_create_time, + 'video_cover': video_cover, + 'video_dynamic_cover': video_dynamic_cover, + 'video_origin_cover': video_origin_cover, + 'video_hashtags': video_hashtags} + return video_data + except Exception as e: + # 返回异常 + return {'status': 'failed', 'reason': e, 'function': 'Scraper.douyin()', 'value': original_url} + + @retry(stop=stop_after_attempt(3), wait=wait_random(min=1, max=2)) + def tiktok(self, original_url: str, proxies: dict = None): + """ + 解析TikTok链接 + :param proxies: {'all': 127.0.0.1:2333}, Default not use proxy. + :param original_url:TikTok链接 + :return:包含信息的字典 + """ + headers = self.headers + # 开始时间 + start = time.time() + # 校验TikTok链接 + if '@' in original_url: + print("目标链接: ", original_url) + else: + # 从请求头中获取原始链接 + response = requests.get(url=original_url, headers=headers, allow_redirects=False, proxies=proxies) + true_link = response.headers['Location'].split("?")[0] + original_url = true_link + # TikTok请求头返回的第二种链接类型 + if '.html' in true_link: + response = requests.get(url=true_link, headers=headers, allow_redirects=False, proxies=proxies) + original_url = response.headers['Location'].split("?")[0] + print("目标链接: ", original_url) + try: + # 获取视频ID + video_id = re.findall('/video/(\d+)?', original_url)[0] + print('获取到的TikTok视频ID是{}'.format(video_id)) + # 尝试从TikTok网页获取部分视频数据 + try: + tiktok_headers = self.tiktok_headers + html = requests.get(url=original_url, headers=tiktok_headers, proxies=proxies, timeout=1) + # 正则检索网页中存在的JSON信息 + resp = re.search('"ItemModule":{(.*)},"UserModule":', html.text).group(1) + resp_info = ('{"ItemModule":{' + resp + '}}') + result = json.loads(resp_info) + # 从网页中获得的视频JSON数据 + video_info = result["ItemModule"][video_id] + except: + video_info = None + # 从TikTok官方API获取部分视频数据 + tiktok_api_link = 'https://api.tiktokv.com/aweme/v1/aweme/detail/?aweme_id={}'.format( + video_id) + print('正在请求API链接:{}'.format(tiktok_api_link)) + response = requests.get(url=tiktok_api_link, headers=headers, proxies=proxies).text + # 将API获取到的内容格式化为JSON + result = json.loads(response) + if 'image_post_info' in response: + # 判断链接是图集链接 + url_type = 'album' + print('类型为图集/type album') + # 视频标题 + album_title = result["aweme_detail"]["desc"] + # 视频作者昵称 + album_author_nickname = result["aweme_detail"]['author']["nickname"] + # 视频作者ID + album_author_id = result["aweme_detail"]['author']["unique_id"] + # 上传时间戳 + album_create_time = result["aweme_detail"]['create_time'] + # 视频ID + album_aweme_id = result["aweme_detail"]['statistics']['aweme_id'] + try: + # 视频BGM标题 + album_music_title = result["aweme_detail"]['music']['title'] + # 视频BGM作者 + album_music_author = result["aweme_detail"]['music']['author'] + # 视频BGM ID + album_music_id = result["aweme_detail"]['music']['id'] + # 视频BGM链接 + album_music_url = result["aweme_detail"]['music']['play_url']['url_list'][0] + except: + album_music_title, album_music_author, album_music_id, album_music_url = "None", "None", "None", "None" + # 评论数量 + album_comment_count = result["aweme_detail"]['statistics']['comment_count'] + # 获赞数量 + album_digg_count = result["aweme_detail"]['statistics']['digg_count'] + # 播放次数 + album_play_count = result["aweme_detail"]['statistics']['play_count'] + # 下载次数 + album_download_count = result["aweme_detail"]['statistics']['download_count'] + # 分享次数 + album_share_count = result["aweme_detail"]['statistics']['share_count'] + # 无水印图集 + album_list = [] + for i in result["aweme_detail"]['image_post_info']['images']: + album_list.append(i['display_image']['url_list'][0]) + # 结束时间 + end = time.time() + # 解析时间 + analyze_time = format((end - start), '.4f') + # 储存数据 + album_data = {'status': 'success', + 'analyze_time': (analyze_time + 's'), + 'url_type': url_type, + 'api_url': tiktok_api_link, + 'original_url': original_url, + 'platform': 'tiktok', + 'album_title': album_title, + 'album_list': album_list, + 'album_author_nickname': album_author_nickname, + 'album_author_id': album_author_id, + 'album_create_time': album_create_time, + 'album_aweme_id': album_aweme_id, + 'album_music_title': album_music_title, + 'album_music_author': album_music_author, + 'album_music_id': album_music_id, + 'album_music_url': album_music_url, + 'album_comment_count': album_comment_count, + 'album_digg_count': album_digg_count, + 'album_play_count': album_play_count, + 'album_share_count': album_share_count, + 'album_download_count': album_download_count + } + # 返回包含数据的字典 + return album_data + else: + # 类型为视频 + url_type = 'video' + print('类型为视频/type video') + # 无水印视频链接 + nwm_video_url = result["aweme_detail"]["video"]["play_addr"]["url_list"][0] + try: + # 有水印视频链接 + wm_video_url = result["aweme_detail"]["video"]['download_addr']['url_list'][0] + except Exception: + # 有水印视频链接 + wm_video_url = 'None' + # 视频标题 + video_title = result["aweme_detail"]["desc"] + # 视频作者昵称 + video_author_nickname = result["aweme_detail"]['author']["nickname"] + # 视频作者ID + video_author_id = result["aweme_detail"]['author']["unique_id"] + # 上传时间戳 + video_create_time = result["aweme_detail"]['create_time'] + # 视频ID + video_aweme_id = result["aweme_detail"]['statistics']['aweme_id'] + try: + # 视频BGM标题 + video_music_title = result["aweme_detail"]['music']['title'] + # 视频BGM作者 + video_music_author = result["aweme_detail"]['music']['author'] + # 视频BGM ID + video_music_id = result["aweme_detail"]['music']['id'] + # 视频BGM链接 + video_music_url = result["aweme_detail"]['music']['play_url']['url_list'][0] + except: + video_music_title, video_music_author, video_music_id, video_music_url = "None", "None", "None", "None" + # 评论数量 + video_comment_count = result["aweme_detail"]['statistics']['comment_count'] + # 获赞数量 + video_digg_count = result["aweme_detail"]['statistics']['digg_count'] + # 播放次数 + video_play_count = result["aweme_detail"]['statistics']['play_count'] + # 下载次数 + video_download_count = result["aweme_detail"]['statistics']['download_count'] + # 分享次数 + video_share_count = result["aweme_detail"]['statistics']['share_count'] + # 视频封面 + video_cover = result["aweme_detail"]['video']['cover']['url_list'][0] + # 视频动态封面 + video_dynamic_cover = result["aweme_detail"]['video']['dynamic_cover']['url_list'][0] + # 视频原始封面 + video_origin_cover = result["aweme_detail"]['video']['origin_cover']['url_list'][0] + # 将话题保存在列表中 + video_hashtags = [] + for tag in result["aweme_detail"]['text_extra']: + if 'hashtag_name' in tag: + video_hashtags.append(tag['hashtag_name']) + else: + continue + if video_info != None: + # 作者粉丝数量 + video_author_followerCount = video_info['authorStats']['followerCount'] + # 作者关注数量 + video_author_followingCount = video_info['authorStats']['followingCount'] + # 作者获赞数量 + video_author_heartCount = video_info['authorStats']['heartCount'] + # 作者视频数量 + video_author_videoCount = video_info['authorStats']['videoCount'] + # 作者已赞作品数量 + video_author_diggCount = video_info['authorStats']['diggCount'] + else: + # 作者粉丝数量 + video_author_followerCount = 'None' + # 作者关注数量 + video_author_followingCount = 'None' + # 作者获赞数量 + video_author_heartCount = 'None' + # 作者视频数量 + video_author_videoCount = 'None' + # 作者已赞作品数量 + video_author_diggCount = 'None' + # 结束时间 + end = time.time() + # 解析时间 + analyze_time = format((end - start), '.4f') + # 储存数据 + video_data = {'status': 'success', + 'analyze_time': (analyze_time + 's'), + 'url_type': url_type, + 'api_url': tiktok_api_link, + 'original_url': original_url, + 'platform': 'tiktok', + 'video_title': video_title, + 'nwm_video_url': nwm_video_url, + 'wm_video_url': wm_video_url, + 'video_author_nickname': video_author_nickname, + 'video_author_id': video_author_id, + 'video_create_time': video_create_time, + 'video_aweme_id': video_aweme_id, + 'video_music_title': video_music_title, + 'video_music_author': video_music_author, + 'video_music_id': video_music_id, + 'video_music_url': video_music_url, + 'video_comment_count': video_comment_count, + 'video_digg_count': video_digg_count, + 'video_play_count': video_play_count, + 'video_share_count': video_share_count, + 'video_download_count': video_download_count, + 'video_author_followerCount': video_author_followerCount, + 'video_author_followingCount': video_author_followingCount, + 'video_author_heartCount': video_author_heartCount, + 'video_author_videoCount': video_author_videoCount, + 'video_author_diggCount': video_author_diggCount, + 'video_cover': video_cover, + 'video_dynamic_cover': video_dynamic_cover, + 'video_origin_cover': video_origin_cover, + 'video_hashtags': video_hashtags + } + # 返回包含数据的字典 + return video_data + except Exception as e: + # 异常捕获 + return {'status': 'failed', 'reason': e, 'function': 'Scraper.tiktok()', 'value': original_url} + + +if __name__ == '__main__': + # 测试类 + scraper = Scraper() + while True: + url = re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', + input("Enter your Douyin/TikTok url here to test: "))[0] + try: + if 'douyin.com' in url: + douyin_date = scraper.douyin(url) + print(douyin_date) + else: + tiktok_date = scraper.tiktok(url) + print(tiktok_date) + except Exception as e: + print("Error: " + str(e))