Tiktok-Scraper – TikTok Scraper. Download Video Posts, Collect User/Trend/Hashtag/Music Feed Metadata, Sign URL And Etc

docker build . -t tiktok-scraper

docker run -v $(pwd):/usr/app/files tiktok-scraper user tiktok -d -n 5 -s

docker run -v /User/blah/downloads:/usr/app/files tiktok-scraper user tiktok -d -n 5 -s

.user(id, options) //Scrape posts from a specific user (Promise)
.hashtag(id, options) //Scrape posts from hashtag section (Promise)
.trend('', options) // Scrape posts from a trends section (Promise)
.music(id, options) // Scrape posts by music id (Promise)

.userEvent(id, options) //Scrape posts from a specific user (Event)
.hashtagEvent(id, options) //Scrape posts from hashtag section (Event)
.trendEvent('', options) // Scrape posts from a trends section (Event)
.musicEvent(id, options) // Scrape posts by music id (Event)

.getUserProfileInfo('USERNAME', options) // Get user profile information
.getHashtagInfo('HASHTAG', options) // Get hashtag information
.signUrl('URL', options) // Get signature for the request
.getVideoMeta('WEB_VIDEO_URL', options) // Get video meta info, including video url without the    watermark
.getMusicInfo('https://www.tiktok.com/music/original-sound-6801885499343571718', options) // Get music metadata

video metadata then in return you will receive {headers} object // that was used to extract the information and in order to access and download video through received {videoUrl} value you need to use same headers headers: { ‘user-agent’: “BLAH”, referer: ‘https://www.tiktok.com/’, cookie: `tt_webid_v2=68dssds`, }, // Download video without the watermark: {boolean default: false} // Set to true to download without the watermark // This option will affect the execution speed noWaterMark: false, // Create link to HD video: {boolean default: false} // This option will only work if {noWaterMark} is set to {true} hdVideo: false, // verifyFp is used to verify the request and avoid captcha // When you are using proxy then there are high chances that the request will be // blocked with captcha // You can set your own verifyFp value or default(hardcoded) will be used verifyFp: ”, // Switch main host to Tiktok test enpoint. // When your requests are blocked by captcha you can try to use Tiktok test endpoints. useTestEndpoints: false };”>

const options = {
    // Number of posts to scrape: {int default: 20}
    number: 50,

    // Scrape posts published since this date: { int default: 0}
    since: 0,

    // Set session: {string[] default: ['']}
    // Authenticated session cookie value is required to scrape user/trending/music/hashtag feed
    // You can put here any number of sessions, each request will select random session from the list
    sessionList: ['sid_tt=21312213'],

    // Set proxy {string[] | string default: ''}
    // http proxy: 127.0.0.1:8080
    // socks proxy: socks5://127.0.0.1:8080
    // You can pass proxies as an array and scraper will randomly select a proxy from the array to execute the requests
    proxy: '',

    // Set to {true} to search by user id: {boolean default: false}
    by_user_id: false,

    // How many post should be downloaded asynchronously. Only if {download:true}: {int def   ault: 5}
    asyncDownload: 5,

    // How many post should be scraped asynchronously: {int default: 3}
    // Current option will be applied only with current types: music and hashtag
    // With other types it is always 1 because every request response to the TikTok API is providing the "maxCursor" value
    // that is required to send the next request
    asyncScraping: 3,

    // File path where all files will be saved: {string default: 'CURRENT_DIR'}
    filepath: `CURRENT_DIR`,

    // Custom file name for the output files: {string default: ''}
    fileName: `CURRENT_DIR`,

    // Output with information can be saved to a CSV or JSON files: {string default: 'na'}
    // 'csv' to save in csv
    // 'json' to save in json
    // 'all' to save in json and csv
    // 'na' to skip this step
    filetype: `na`,

    // Set custom headers: user-agent, cookie and etc
    // NOTE: When you parse    video feed or single video metadata then in return you will receive {headers} object
    // that was used to extract the information and in order to access and download video through received {videoUrl} value you need to use same headers
    headers: {
        'user-agent': "BLAH",
        referer: 'https://www.tiktok.com/',
        cookie: `tt_webid_v2=68dssds`,
    },

    // Download video without the watermark: {boolean default: false}
    // Set to true to download without the watermark
    // This option will affect the execution speed
    noWaterMark: false,

    // Create link to HD video: {boolean default: false}
    // This option will only work if {noWaterMark} is set to {true}
    hdVideo: false,

    // verifyFp is used to verify the request and avoid captcha
    // When you are using proxy then there are high chances that the request will be
    // blocked with captcha
    // You can set y   our own verifyFp value or default(hardcoded) will be used
    verifyFp: '',

    // Switch main host to Tiktok test enpoint.
    // When your requests are blocked by captcha you can try to use Tiktok test endpoints.
    useTestEndpoints: false
};

const TikTokScraper = require('tiktok-scraper');

// User feed by username
(async () => {
    try {
        const posts = await TikTokScraper.user('USERNAME', {
            number: 100,
            sessionList: ['sid_tt=58ba9e34431774703d3c34e60d584475;']
        });
        console.log(posts);
    } catch (error) {
        console.log(error);
    }
})();

// User feed by user id
// Some TikTok user id's are larger then MAX_SAFE_INTEGER, you need to pass user id as a string
(async () => {
    try {
        const posts = await TikTokScraper.user(`USER_ID`, {
            number: 100,
            by_user_id: true,
            sessionList: ['sid_tt=58ba9e34431774703d3c34e60d584475;']
        });
        console.log(posts);
    } catch (error) {
        console.log(error);
    }
})();

// Trending feed
(async () => {
    try {
           const posts = await TikTokScraper.trend('', {
            number: 100,
            sessionList: ['sid_tt=58ba9e34431774703d3c34e60d584475;']
        });
        console.log(posts);
    } catch (error) {
        console.log(error);
    }
})();

// Hashtag feed
(async () => {
    try {
        const posts = await TikTokScraper.hashtag('HASHTAG', {
            number: 100,
            sessionList: ['sid_tt=58ba9e34431774703d3c34e60d584475;']
        });
        console.log(posts);
    } catch (error) {
        console.log(error);
    }
})();

// Get single user profile information: Number of followers and etc
// input - USERNAME
// options - not required
(async () => {
    try {
        const user = await TikTokScraper.getUserProfileInfo('USERNAME', options);
        console.log(user);
    } catch (error) {
        console.log(error);
    }
})();<   br/>
// Get single hashtag information: Number of views and etc
// input - HASHTAG NAME
// options - not required
(async () => {
    try {
        const hashtag = await TikTokScraper.getHashtagInfo('HASHTAG', options);
        console.log(hashtag);
    } catch (error) {
        console.log(error);
    }
})();


// Get single video metadata
// input - WEB_VIDEO_URL
// For example: https://www.tiktok.com/@tiktok/video/6807491984882765062
// options - not required
(async () => {
    try {
        const videoMeta = await TikTokScraper.getVideoMeta('https://www.tiktok.com/@tiktok/video/6807491984882765062', options);
        console.log(videoMeta);
    } catch (error) {
        console.log(error);
    }
})();

const TikTokScraper = require('tiktok-scraper');

const users = TikTokScraper.userEvent("tiktok", { number: 30 });
users.on('data', json => {
    //data in JSON format
});
users.on('done', () => {
    //completed
});
users.on('error', error => {
    //error message
});
users.scrape();

const hashtag = TikTokScraper.hashtagEvent("summer", { number: 250, proxy: 'socks5://1.1.1.1:90' });
hashtag.on('data', json => {
    //data in JSON format
});
hashtag.on('done', () => {
    //completed
});
hashtag.on('error', error => {
    //error message
});
hashtag.scrape();

    headers: {
        "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.80 Safari/537.36",
        "referer": "https://www.tiktok.com/",
        "cookie": "tt_webid_v2=689854141086886123"
    },

const headers = {
    "user-agent": "BOB",
    "referer": "https://www.tiktok.com/",
    "cookie": "tt_webid_v2=BOB"
}
getVideoMeta('WEB_VIDEO_URL', {headers})
user('WEB_VIDEO_URL', {headers})
hashtag('WEB_VIDEO_URL', {headers})
trend('WEB_VIDEO_URL', {headers})
music('WEB_VIDEO_URL', {headers})
// And after you can access video through {videoUrl} value by using same custom headers

{
    headers: {
        'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.80 Safari/537.36',
        referer: 'https://www.tiktok.com/',
        cookie: 'tt_webid_v2=689854141086886123'
    },
    collector:[{
        id: 'VIDEO_ID',
        text: 'CAPTION',
        createTime: '1583870600',
        authorMeta:{
            id: 'USER ID',
            name: 'USERNAME',
            following: 195,
            fans: 43500,
            heart: '1093998',
            video: 3,
            digg: 95,
            verified: false,
            private: false,
            signature: 'USER BIO',
            avatar:'AVATAR_URL'
        },
        musicMeta:{
            musicId: '6808098113188120838',
            musicName: 'blah blah',
            musicAuthor: 'blah',
            musicOriginal: true,
               playUrl: 'SOUND/MUSIC_URL',
        },
        covers:{
            default: 'COVER_URL',
            origin: 'COVER_URL',
            dynamic: 'COVER_URL'
        },
        imageUrl:'IMAGE_URL',
        videoUrl:'VIDEO_URL',
        videoUrlNoWaterMark:'VIDEO_URL_WITHOUT_THE_WATERMARK',
        videoMeta: { width: 480, height: 864, ratio: 14, duration: 14 },
        diggCount: 2104,
        shareCount: 1,
        playCount: 9007,
        commentCount: 50,
        mentions: ['@bob', '@sam', '@bob_again', '@and_sam_again'],
        hashtags:
        [{
            id: '69573911',
            name: 'PlayWithLife',
            title: 'HASHTAG_TITLE',
            cover: [Array]
        }...],
        downloaded: true
    }...],
    //If {filetype} and {download} options are enbabled then:
    zip: '/{CURRENT_PATH}/user_1552963581094.zip',
    json: '/{CURRENT_PATH}/user_   1552963581094.json',
    csv: '/{CURRENT_PATH}/user_1552963581094.csv'
}

{
    secUid: 'MS4wLjABAAAAv7iSuuXDJGDvJkmH_vz1qkDZYo1apxgzaxdBSeIuPiM',
    userId: '107955',
    isSecret: false,
    uniqueId: 'tiktok',
    nickName: 'TikTok',
    signature: 'Make Your Day',
    covers: ['COVER_URL'],
    coversMedium: ['COVER_URL'],
    following: 490,
    fans: 38040567,
    heart: '211522962',
    video: 93,
    verified: true,
    digg: 29,
}

{
    challengeId: '4231',
    challengeName: 'love',
    text: '',
    covers: [],
    coversMedium: [],
    posts: 66904972,
    views: '194557706433',
    isCommerce: false,
    splitTitle: ''
}

{
    headers: {
        'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.80 Safari/537.36',
        referer: 'https://www.tiktok.com/',
        cookie: 'tt_webid_v2=689854141086886123'
    },
    collector:[{
        id: '6807491984882765062',
        text: 'We’re kicking off the #happyathome live stream series today at 5pm PT!',
        createTime: '1584992742',
        authorMeta: { id: '6812221792183403526', name: 'blah' },
        musicMeta:{
            musicId: '6822233276137213677',
            musicName: 'blah',
            musicAuthor: 'blah'
        },
        imageUrl: 'IMAGE_URL',
        videoUrl: 'VIDEO_URL',
        videoUrlNoWaterMark: 'VIDEO_URL_WITHOUT_THE_WATERMARK',
        videoMeta: { width: 480, height: 864, ratio: 14, duration: 14 },
        covers:{
            default: 'COV   ER_URL',
            origin: 'COVER_URL'
        },
        diggCount: 49292,
        shareCount: 339,
        playCount: 614678,
        commentCount: 4023,
        downloaded: false,
        hashtags: [],
    }]
}

{
    music: {
        id: '6882925279036066566',
        title: 'doja x calabria',
        playUrl: 'dfdfdfdf',
        coverThumb:
            'dfdfdf',
        coverMedium:
            'dfdfdf',
        coverLarge:
            'fdfdf',
        authorName: 'bryce',
        original: true,
        playToken:
            'ffdfdf',
        keyToken: 'dfdfdfd',
        audioURLWithcookie: false,
        private: false,
        duration: 46,
        album: '',
    },
    author: {
        id: '6835300004094166021',
        uniqueId: 'mashupsbybryce',
        nickname: 'bryce',
        avatarThumb:
            'dfdfd',
        avatarMedium:
            'dfdfdf',
        avatarLarger:
            'dfdfdf',
        signature: 'hi ily :)n70k sounds cool tbhn👇follow my soundcloud & insta👇',
           verified: false,
        secUid: 'MS4wLjABAAAA1_5bjLAamayD4rv3q49qJGa_7dZ5jzExTO0ozOybqIwwhw5TAg_iM25lkO94DM3K',
        secret: false,
        ftc: false,
        relation: 0,
        openFavorite: false,
        commentSetting: 0,
        duetSetting: 0,
        stitchSetting: 0,
        privateAccount: false,
    },
    stats: { videoCount: 361700 },
    shareMeta: {
        title: 'bryceyouloser | ♬ doja x calabria | on TikTok',
        desc: '361.0k videos - Watch awesome short ' + 'videos created with ♬ doja x calabria',
    },
};