internetarchive-ts - v0.1.0
    Preparing search index...

    Type Alias IaFileExtendedMetadataBeta

    IaFileExtendedMetadata: IaFileBaseMetadata & IaFileDefinedByIaMetadata & {
        adaptive_ocr?: true;
        addeddate?: string;
        "admin-collection"?: boolean;
        album?: string;
        artist?: string;
        aspect_ratio?: string;
        atime?: string;
        audio_codec?: string;
        audio_sample_rate?: string;
        autoplay?: string;
        betterpdf?: boolean;
        bitrate?: string;
        "bookreader-defaults"?: "mode/1up" | "mode/2up" | "mode/thumb";
        boxid?: string | string[];
        btih?: string;
        bwocr?: string;
        call_number?: string;
        camera?: string;
        ccnum?: string;
        closed_captioning?: "yes" | "no";
        collection?: string | string[];
        collection_catalog_number?: string;
        color?: string;
        comment?: string;
        condition?:
            | "Mint"
            | "Near Mint"
            | "Very Good"
            | "Good"
            | "Fair"
            | "Worn"
            | "Poor"
            | "Fragile"
            | "Incomplete";
        "condition-visual"?: string;
        contributor?: string;
        coverage?: string
        | string[];
        creator?: string | string[];
        "creator-alt-script"?: boolean;
        ctime?: string;
        curation?: string;
        date?: string;
        description?: string | string[];
        external_identifier?: string;
        external_identifier_match_date?: string | string[];
        "external-identifier"?: string | string[];
        filecount?: string;
        firstfiledate?: string;
        "fixed-ppi"?: boolean;
        foldoutcount?: string;
        "force-update"?: boolean;
        frames_per_second?: string;
        genre?: string;
        geo_restricted?: boolean;
        height?: number;
        hidden?: boolean;
        hocr_char_to_word_hocr_version?: string;
        hocr_char_to_word_module_version?: string;
        hocr_fts_text_hocr_version?: string;
        hocr_fts_text_module_version?: string;
        hocr_pageindex_hocr_version?: string;
        hocr_pageindex_module_version?: string;
        "identifier-ark"?: string;
        "identifier-bib"?: string | string[];
        imagecount?: string;
        isbn?: string | string[];
        issn?: string | string[];
        language?: string | string[];
        lastfiledate?: string;
        lccn?: string | string[];
        length?: number;
        licenseurl?: string;
        "marc-insert-only"?: boolean;
        matrix_number?: string;
        mediatype?: string;
        neverindex?: boolean;
        next_item?: string;
        no_ol_import?: boolean;
        noindex?: boolean;
        notes?: string | string[];
        "oclc-id"?: string | string[];
        ocr?: string;
        ocr_detected_lang?: string;
        ocr_detected_lang_conf?: string;
        ocr_detected_script?: string;
        ocr_detected_script_conf?: string;
        ocr_module_version?: string;
        ocr_parameters?: string;
        openlibrary_author?: string | string[];
        openlibrary_edition?: string;
        openlibrary_subject?: string | string[];
        openlibrary_work?: string;
        operatingsystem?: string;
        operator?: string;
        original?: string;
        original_name?: string;
        "page-progression"?: string;
        "possible-copyright-status"?: string;
        ppi?: string;
        previous_item?: string;
        private?: boolean;
        "public-format"?: string | string[];
        publisher?: string;
        related_collection?: boolean;
        "related-external-id"?: string | string[];
        repub_state?: string;
        republisher_date?: string;
        republisher_operator?: string;
        republisher_time?: string;
        rights?: string;
        rotation?: IaFileRotation;
        runtime?: string | string[];
        scandate?: string;
        scanfee?: string;
        scanner?: string;
        scanningcenter?: string;
        show_related_music_by_track?: boolean;
        sound?: string;
        source_pixel_height?: number;
        source_pixel_width?: number;
        sponsor?: string;
        sponsordate?: string;
        start_localtime?: string;
        start_time?: string;
        stop_time?: string;
        subject?: string | string[];
        summation?: string;
        title?: string;
        track?: string;
        tuner?: string;
        updated?: string | string[];
        updatedate?: string | string[];
        updater?: string | string[];
        utc_offset?: number;
        video_codec?: string;
        viruscheck?: "true";
        volume?: string;
        wb_filtered?: string;
        width?: number;
        [key: `word_conf_${number}_${number}`]: string;
    }

    Type Declaration

    • [key: `word_conf_${number}_${number}`]: string
    • Optionaladaptive_ocr?: true

      Adaptive OCR @ Allows deriver to skip a page that would otherwise disrupt OCR

      Defined by: uploader

      Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#adaptive_ocr

    • Optionaladdeddate?: string

      Date Added to Public Search

      2019-12 and later dates: represents time item was added to public search engine. Earlier dates: Date and time in UTC that the item was created on archive.org Beginning in December 2019: when item was first added to public search engine. It is added during the first task where the item does not have noindex present in meta.xml. The field is not changed or removed if the item is subsequently removed from public search. Prior to December 2019, Addeddate was automatically set when the item directory is been created in our file system. In many cases, the addeddate will be very similar to the publicdate. However, in some cases we create an item directory with metadata but no media files prior to the media being scanned. The addeddate reflects when the item was created, regardless of when the media was added to the item. When the media is added at a later date and a derive.php task is run, the publicdate will be added to the item.

      Defined by: IA software

      Edit access: not editable

      See https://archive.org/developers/metadata-schema/index.html#addeddate

      "2017-03-28 22:05:46"
      
    • Optionaladmin-collection?: boolean

      Admin Collection

      Collection will generally be suppressed from public display, e.g. in facets, membership lists on Collection/Details pages, etc. Only used by internal IA admins Defined by: IA admin Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#admin-collection

      true
      
    • Optionalalbum?: string

      Album Name

    • Optionalartist?: string

      Similar to creator. This is a common tag used in audio files.

    • Optionalaspect_ratio?: string

      Aspect Ratio

      Ratio of the pixel width and height of a video stream Standard values for this field are 4:3 and 16:9, but other values are possible. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#aspect_ratio

      "4:3"
      
    • Optionalatime?: string
    • Optionalaudio_codec?: string

      Audio Codec

      Program used to decode audio stream Primarily used for TV Archive items. Defined by: IA software Edit access: IA admin

      See https://archive.org/developers/metadata-schema/index.html#audio_codec

      "ac3"
      
    • Optionalaudio_sample_rate?: string

      Audio Sample Rate

      Samples per second Primarily used for TV Archive items. Defined by: IA software Edit access: IA admin

      See https://archive.org/developers/metadata-schema/index.html#audio_sample_rate

      "48000"
      
    • Optionalautoplay?: string
    • Optionalbetterpdf?: boolean

      Better PDF

      Indicates that the derive module should create a higher quality PDF derivative (distinguishes text from background better). This field is either set to the value true, or is not included in meta.xml. If this field is included after the initial derive is run, user should also run a derive task to create the better quality PDF. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#betterpdf

      true
      
    • Optionalbitrate?: string

      Bit Rate

    • Optionalbookreader-defaults?: "mode/1up" | "mode/2up" | "mode/thumb"

      Bookreader defaults

      Indicates whether the bookreader should display one or two pages by default The bookreader defaults to showing books in 2up mode, so this field is generally only used to indicate that an item should be displayed in 1up mode (showing only one page at a time in the bookreader). Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#bookreader-defaults

      "mode/1up"
      
    • Optionalboxid?: string | string[]

      Box ID

      Location of physical item in the Physical Archive Boxids always start with the letters IA followed by numbers. The numbers represent the container, pallet and box that the physical item is stored in. When there are multiple boxid fields in meta.xml, the first boxid listed represents the physical item that was digitized. Subsequent boxid fields represent the location of duplicate physical items. Defined by: IA admin Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#boxid

      "IA158001"
      
    • Optionalbtih?: string

      BitTorrent Info Hash

    • Optionalbwocr?: string

      Black and White OCR

      Allows deriver to OCR specific pages as B&W if color is causing failure. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#bwocr

      "001"
      
    • Optionalcall_number?: string

      Call Number

      Contributing library's local call number Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#call_number

      "6675707"
      
      "NC 285.1 P9287m"
      
    • Optionalcamera?: string

      Camera

      Camera model used during digitization process Defined by: user admin Edit access: user admin

      See https://archive.org/developers/metadata-schema/index.html#camera

      "Canon 5D"
      
    • Optionalccnum?: string

      Closed Captioning Number

      Indicates which closed captioning file should be used for display and search Primarily used for TV Archive items. Closed captioning files are stored as [identifier].cc#.txt in the item. This tag indicates which cc# file to display in item and use for search indexing. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#ccnum

      "cc5"
      
    • Optionalclosed_captioning?: "yes" | "no"

      Closed Captioning

      Indicates whether item contains closed captioning files Field is generally only present when the video has closed captioning. When captioning is not present, the field may have "no" as the value, or just not be included in meta.xml Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#closed_captioning

      "yes"
      
      "no"
      
    • Optionalcollection?: string | string[]

      Collections

      Indicates to the website what collection(s) this item belongs to. Required for all items except "fav-username" collections. Always list the item's primary collection first in meta.xml; this is the collection the item "belongs" to. The primary collection often represents the entity that contributed or created the content. Uploaders can only choose from collections that they have privileges for. General uploaders with no special privs can only upload to selected "Community" collections or the test_collection. Items in the test_collection are removed from the site after 30 days. Parent collections If the parent collections of an item's collections are not already included in the item's own collection list, they will be automatically added (at the end of the next task on the item). Here, more specifically, is how that addition takes place: All of the item's currently listed collections are considered in turn. For each of them, we trace its ancestry all the way up to the top-level collection (usually a mediatype); in tracing ancestry, we consider only the primary (first-listed) parent collection at each step. If the original item is itself a collection, we include the top-level collection, otherwise we don't. Any collection we encounter during this traversal of the hierarchy that isn't already in the item's collection list gets added to the end of the list. For example, if the original item starts with collections A and B listed, we find A's primary parent (call it A-P), that collection's primary parent (A-P-P), etc., until we hit a mediatype; all of those that aren't already listed get added, including the mediatype if the item itself is a collection. Then we do the same for B and its primary parent B-P, B-P-P, etc. Defined by: user admin Edit access: user admin

      See https://archive.org/developers/metadata-schema/index.html#collection

      "prelinger"
      
    • Optionalcollection_catalog_number?: string
    • Optionalcolor?: string

      Color

      Indicates whether media is in color or black and white Most used values are: color, B&W (black and white) Mostly used for video items, indicates whether video is color or black and white. Can be used to indicate different kinds of color (e.g. Kodachrome). Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#color

      "color"
      
    • Optionalcomment?: string
    • Optionalcondition?:
          | "Mint"
          | "Near Mint"
          | "Very Good"
          | "Good"
          | "Fair"
          | "Worn"
          | "Poor"
          | "Fragile"
          | "Incomplete"

      Condition

      condition of media Defines the condition of the media in an item. In 78s and LPs this indicates the condition of the disc or media file. For sets with multiple discs, use the condition of the lowest grade disc in the set. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#condition

      "Good"
      
    • Optionalcondition-visual?: string

      Visual Condition

      Condition of the artwork or printed materials that accompany a media item Defines the condition of the artwork or printed materials that accompany the media in an item. In LPs this is used for album covers and sleeves. "Incomplete" should be used when we know that artwork/printed materials are missing. "None" should be used when the item has no artwork/printed materials and we know it is not supposed to have any. "Unknown" should be used when artwork/printed material MAY be missing, but we cannot verify. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#condition-visual

      "Good"
      
    • Optionalcontributor?: string

      Contributor

      The person or organization that provided the physical or digital media. For physical items that have been digitized, contributor represents the library or other organization that owns the physical item. For born-digital media, contributor often represents the organization responsible for the distribution of the content (e.g. a radio station or television station). Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#contributor

      "Robarts - University of Toronto"
      
    • Optionalcoverage?: string | string[]

      Coverage

      Geographic or subject area covered by item The preferred use of this field is to signify a geographical location that relates to the item. For example, in the TV and radio collections, we use the ISO 3166 location code for the country and state/territory of the station being recorded. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#coverage

      "GB-LND"
      
    • Optionalcreator?: string | string[]

      Creator

      The individual(s) or organization that created the media content. For items provided by libraries, the creator is often listed using the Library of Congress Name Authority Headings, http://authorities.loc.gov/ For items from other sources, the creator is often listed as first name and surname. When an item was created by an organization, such as a government agency or a production company, use the full name of the organization. This field represents the entity who created the media, not the person who uploaded the media to archive.org (though these may be the same person). All alphabets supported. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#creator

      "Austen, Jane, 1775-1817"
      
      "Ralph Burns"
      
    • Optionalcreator-alt-script?: boolean

      Creator Alternate Script

      Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#creator-alt-script

    • Optionalctime?: string
    • Optionalcuration?: string

      Curation

      Curation state and notes Curation is a compound field with "sub-fields": curator, date, state, and comment. - Curator is the email address of the person who added the curation tag. - Date is the UTC time and date the curation tag was added, in YYYYMMDDHHMMSS format. - State can be: dark, approved, freeze, un-dark or blank - Comment can be a code used by the scanning center team to indicate issues found during QA, or a text string with some other curation comment (e.g. information about why an item was frozen or made dark). Items uploaded into open collections are generally checked by malware detection software, and the curation field will contain the results of that check. Defined by: IA admin Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#curation

      "[curator]lenscriv@archive.org[/curator][date]20160504125613[/date][state]approved[/state][comment]199[/comment]"
      
      "[curator]malware@archive.org[/curator][date]20140321085621[/date][comment]checked for malware[/comment]"
      
    • Optionaldate?: string

      Publication Date

      We encourage people to use YYYY, YYYY-MM, or YYYY-MM-DD for this field, but sometimes exact dates are not possible to determine. Other common usages: [YYYY] (brackets) when a date is not certain; c.a. YYYY (c.a.) when a date is approximate; and [n.d.] when a date is unknown (you may also leave the field blank in this case). If an item has a date range, such as YYYY-YYYY, we currently index only the first date in the range. Books, movies, and CDs often only have YYYY for a publication date. Magazines often have YYYY-MM for a publication date. Concerts and articles often have YYYY-MM-DD publication dates. Use the most specific verifiable date you have access to. When the item is a digitial representation of a physical piece of media (e.g. a book, a 78rpm disc, etc.) the publication date should represent the date that the specific physical item was published. A book may have been written in 1850, and then an edition was republished in 1885. If the digitized version is the edition republished in 1885, use 1885 as the publication date (not 1850).

      Defined by: uploader

      Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#date

      "1965"
      
      "2013-05-25"
      
      "[n.d.]"
      
    • Optionaldescription?: string | string[]

      Item Description

      Describes the media stored in the item. May be about the media content (e.g. a description of the book's plot), the physical item it represents (e.g. missing or damaged pages in the physical book that was digitized), the creator of the media (e.g. author biographical info that relates to the book), or any other information that may help a user understand the item or its context. All alphabets are supported. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#description

      "Cinemascope homage to the city of San Francisco made by amateur filmmaker and inventor Tullio Pellegrini. "
      
    • Optionalexternal_identifier?: string
    • Optionalexternal_identifier_match_date?: string | string[]
      "youtube:2018-07-19T04:36:11Z"
      
    • Optionalexternal-identifier?: string | string[]

      External Identifier

      URLs or identifiers to outside resources that represent the media External-identifier includes Uniform Resource Names (URNs) for external resources about the media in the item. The field is usually in the form of urn:namespace:identifier. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#external-identifier

      "urn:publisher_catalog_id:88697 03614 2"
      
      "urn:pubcat:victor:18890-B"
      
      "urn:spotify:album:3jmETApVCjXb3hWTR1IEdH"
      
      "urn:asin:0451531396"
      
      "acs:epub:urn:uuid:d935586b-72a7-4720-bbb9-72fe75eae0e1"
      
      "urn:acs6:blackreconstruc00dubo:epub:38413c16-074b-4fb6-a4dc-25e93e199d5f"
      
      "urn:mb_artist_id:6de0f914-3e60-4418-be3b-42e0feb6eb4d"
      
      "urn:X-pwacrawlid:AWP5"
      
    • Optionalfilecount?: string
    • Optionalfirstfiledate?: string

      First File Date

      Creation date of the earliest file contained in the item Primarily used for WARC items Defined by: IA software Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#firstfiledate

      "20211103001952"
      
    • Optionalfixed-ppi?: boolean

      Fixed PPI

      To change the ppi to a specific resolution. Usually lower especially when jp2.zip fails Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#fixed-ppi

    • Optionalfoldoutcount?: string

      Fold Out Count

      Number of fold outs captured by operator Fold outs are photographed on machinery other than the Scribe. This field indicates how many foldouts were captured. The value may be 0 or higher. Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#foldoutcount

      "1"
      
    • Optionalforce-update?: boolean

      Force Update

      For partner-funded scanned books (no boxid), this allows a MARC record in the item to overwrite metadata fields in meta.xml When this field is NOT present for partner scanned books (no boxid), metadata from a MARC record will only be used to automatically fill in EMPTY metadata fields in meta.xml, and fields that already have metadata in them will be left as-is. Adding force-update to the item causes MARC to overwrite all fields that can be extracted, regardless of whether they already contain information or not.

      Defined by: uploader

      Edit access: uploader

      INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#force-update

      true
      
    • Optionalframes_per_second?: string

      Frames Per Second

      Frequency at which consecutive images are displayed Primarily used for TV Archive items. Defined by: IA software Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#frames_per_second

      "29.97"
      
    • Optionalgenre?: string
    • Optionalgeo_restricted?: boolean

      Geo Restricted

      Limits access based on ISO-2 Country Code Defined by: IA admin Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#geo_restricted

    • Optionalheight?: number

      Image height (in pixels)

    • Optionalhidden?: boolean

      Hidden

      Hides collection from top level navigation This tag only functions on items of mediatype collection. Defined by: user admin Edit access: user admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#hidden

      true
      
    • Optionalhocr_char_to_word_hocr_version?: string
    • Optionalhocr_char_to_word_module_version?: string
    • Optionalhocr_fts_text_hocr_version?: string
    • Optionalhocr_fts_text_module_version?: string
    • Optionalhocr_pageindex_hocr_version?: string
    • Optionalhocr_pageindex_module_version?: string
    • Optionalidentifier-ark?: string

      ARK

      Archival Resource Key identifier

      ARKs are URLs designed to support long-term access to information objects. We store the ark:/NAAN/Name portion of the URL in meta.xml. This can be tacked on to any ARK resolver's domain to resolve the ARK, i.e. http://n2t.net/. Read about ARKs: http://n2t.net/e/ark_ids.html ARK specification: http://n2t.net/e/arkspec.txt Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#identifier-ark

      "ark:/13960/t4rj5fk7h"
      
    • Optionalidentifier-bib?: string | string[]

      Local Identifier

      Additional local identifiers Fields for many identifiers exist in the schema, including isbn, issn, oclc, and call_number. The identifier-bib field is used for additional local identifiers that don't have a place elsewhere in metadata. These identifiers are unique to the institution providing the item. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#identifier-bib

      "GLAD-84064318"
      
    • Optionalimagecount?: string

      Image Count

      Imagecount gives an indication of the size of the content of an item (outside of file size, which is represented in the size field). Originally used only for books, the field has been repurposed over time to provide similar information for other mediatypes. Texts: represents number of page images in the item TV: represents number of seconds of video in the item Web: represents number of URIs captured in the WARCs in the item CD: number of images of physical item and accompanying materials Defined by: IA software Edit access: IA software INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#imagecount

      "230"
      
    • Optionalisbn?: string | string[]
      "3540212507"
      
      "031294716X"
      
    • Optionalissn?: string | string[]

      ISSN

      ISSN ISSNs are identifying numbers for serials. See https://www.issn.org/understanding-the-issn/what-is-an-issn/ for clarification. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#issn

      "2528-7788"
      
      "1943-345X"
      
    • Optionallanguage?: string | string[]

      Language

      The language the media is written or recorded in. For items provided by libraries, the language is often provided as a 3 letter MARC language code (e.g. eng), https://www.loc.gov/marc/languages/ For other items, the language is often written out as the full name (e.g. English). Not all items have a language associated with them (e.g. instrumental music), but when there is written or spoken language we are able to do some sorts of processing better when we know the language. To skip OCR on an item, set the value to None When an item contains no OCRable content, you will sometimes see the language set to zxx. Language is particularly important for text items so that we can do the best job with optical character recognition processing. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#language

      "eng"
      
      "Italian"
      
      "None"
      
    • Optionallastfiledate?: string

      Last File Date

      Date of creation of oldest file in the item Primarily used for WARC items Defined by: IA software Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#lastfiledate

      "20211103003910"
      
    • Optionallccn?: string | string[]

      LCCN

      Library of Congress Call Number https://www.loc.gov/marc/lccn_structure.html Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#lccn

      "2004045278"
      
    • Optionallength?: number

      Run length (in seconds).

    • Optionallicenseurl?: string

      License URL

      URL of the selected license This link should point to a recognized license, like Creative Commons or GNU. For other types of rights statements, use the rights field. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#licenseurl

      "http://creativecommons.org/licenses/by-nd/3.0/"
      
    • Optionalmarc-insert-only?: boolean

      Marc Insert Only

      restricting the incorporation of MARC-extracted metadata to fields that currently have no value ("insert only" behavior), there are certain classes of item for which we insert MARC-extracted metadata only where no value currently exists in the item metadata for that field, so that we won't overwrite any existing metadata. if their items are readily identifiable, the same restriction can be applied to those items. Defined by: IA admin Edit access: IA admin

      See https://archive.org/developers/metadata-schema/index.html#marc-insert-only

      true
      
    • Optionalmatrix_number?: string
    • Optionalmediatype?: string

      Type of Media

      Mediatype tells us about the main content of the item. It is used to determine how the item is displayed on the web site and may trigger special processing depending on the types of files contained in the item. texts: books, articles, newspapers, magazines, any documents with content that contains text etree: live music concerts, items should only be uploaded for artists with collections in the etree "Live Music Archive" community audio: any item where the main media content is audio files, like FLAC, mp3, WAV, etc. movies: any item where the main media content is video files, like mpeg, mov, avi, etc. software: any item where the main media content is software intended to be run on a computer or related device such as gaming devices, phones, etc. image: any item where the main media content is image files (but is not a book or other text item), like jpeg, gif, tiff, etc. data: any item where the main content is not media or web pages, such as data sets web: any item where the main content is copies of web pages, usually stored in WARC or ARC format collection: designates the item as a collection that can "contain" other items account: designates the item as being a user account page, can only be set by internal archive systems Defined by: uploader Edit access: IA admin

      See https://archive.org/developers/metadata-schema/index.html#mediatype

      "movies"
      
    • Optionalneverindex?: boolean

      Never Index

      Prevents RePublisher from removing noindex at the end of the texts digitization process. Only used on internally digitized texts items. Normally when a text finishes the RePublisher process, the noindex tag is removed and the book is added to the public search engine. The neverindex tag prevents the removal of noindex, so books with nevrindex set to true should not end up in the public search engine. Defined by: IA admin Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#neverindex

      true
      
    • Optionalnext_item?: string

      Next Item

      IA identifier of next item from a recorded feed Primarily used for TV Archive items. Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#next_item

      "BBCNEWS_20121204_090000_BBC_News"
      
    • Optionalno_ol_import?: boolean

      No OL Import

      Keeps books out of open library Defined by: IA admin Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#no_ol_import

    • Optionalnoindex?: boolean

      No Index

      Prevents item from being indexed in public archive.org search engine While the accepted practice is to have a value of "true" for this tag, the mere presence of the tag in meta.xml will actually cause the same effect regardless of the value used (including empty). In addition to not being included in the public archive.org search engine, the noindex tag will also cause the item to not be listed in the sitemap. Defined by: uploader Edit access: uploader INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#noindex

      true
      
    • Optionalnotes?: string | string[]

      Notes

      additional notes about the item Use the description field to describe the media stored in an item. The notes field is for additional information like condition of othe physical item, technical notes about digitization, or similar. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#notes

      []
      
    • Optionaloclc-id?: string | string[]

      OCLC ID

      Identifier of same edition in OCLC records Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#oclc-id

      "37432884"
      
    • Optionalocr?: string

      OCR Software

      Software package and version used for optical character recognition Set during derivation process. Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#ocr

      "ABBYY FineReader 8.0"
      
    • Optionalocr_detected_lang?: string
    • Optionalocr_detected_lang_conf?: string
    • Optionalocr_detected_script?: string
    • Optionalocr_detected_script_conf?: string
    • Optionalocr_module_version?: string
    • Optionalocr_parameters?: string
    • Optionalopenlibrary_author?: string | string[]

      Open Library author

      Open Library author Correlates to the edition page on openlibrary.org. The OL edition page URL is https://openlibrary.org/books/[openlibrary_edition] Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#openlibrary_author

      "OL52922A"
      
    • Optionalopenlibrary_edition?: string

      Open Library edition identifier

      Open Library edition identifier Correlates to the edition page on openlibrary.org. The OL edition page URL is https://openlibrary.org/books/[openlibrary_edition] Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#openlibrary_edition

      "OL2769393M"
      
    • Optionalopenlibrary_subject?: string | string[]

      Open Library subject

      Open Library subject This field is currently used to supply books for carousels on the openlibrary.org home page. At some point it will also be used to import subjects from the openlibrary_work associated with the item. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#openlibrary_subject

      "openlibrary_staff_picks"
      
    • Optionalopenlibrary_work?: string

      Open Library work identifier

      Open Library work identifier Correlates to the work page on openlibrary.org. The OL work page URL is https://openlibrary.org/works/[openlibrary_edition] Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#openlibrary_work

      "OL675783W"
      
    • Optionaloperatingsystem?: string
    • Optionaloperator?: string

      Operator

      Email of the person who scanned/captured the media in the item usually email address. In texts this represents the person who operated the Scribe or other scanning equipment. In web items this represents the engineer responsible for the crawl. Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#operator

      "associate-stephanie-kinsey@archive.org"
      
    • Optionaloriginal?: string

      For derivative files, this indicates the original file the derive was performed upon.

    • Optionaloriginal_name?: string
    • Optionalpage-progression?: string

      Page Progression

      Determines direction pages will be "turned" in a book lr = left to right rl = right to left Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#page-progression

      "rl"
      
      "lr"
      
    • Optionalpossible-copyright-status?: string

      Possible Copyright Status

      Information relevant to copyright status Do not use this field for CC license information (see licenseurl). Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#possible-copyright-status

      "The Centers for Medicare & Medicaid Services Library is unaware of any copyright restrictions for this item."
      
    • Optionalppi?: string

      PPI

      Pixels per inch Indicates pixels per inch for an image. The most common use case is Internet Archive digitization centers. This number is set during the book scanning process. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#ppi

      "300"
      
    • Optionalprevious_item?: string

      Previous Item

      IA identifier of previous item from a recorded feed Primarily used for TV Archive items. Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#previous_item

      "BBCNEWS_20121204_060000_Breakfast"
      
    • Optionalprivate?: boolean

      private

    • Optionalpublic-format?: string | string[]

      Public Formats

      Collection file formats that are available to users in an Access Restricted collection This tag only affects items of mediatype collection and must be used in conjunction with the access-restricted tag. This tag should only be assigned by internal IA admins. Defined by: IA admin Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#public-format

      "Metadata"
      
    • Optionalpublisher?: string

      Publisher

      Publisher of the media

      • Books use publisher - Movies often use production company - Music often uses record label

      Defined by: uploader

      Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#publisher

      "New York : R.R. Bowker Co."
      
    • Optionalrelated_collection?: boolean

      Related Collection

      Adds links to related collection on a collection's "About" page Defined by: user admin Edit access: user admin

      See https://archive.org/developers/metadata-schema/index.html#related_collection

    • Optionalrelated-external-id?: string | string[]

      Related External Identifier

      URLs or identifiers to resources related to the media, but not representing this exact form of the work Related-external-id includes URNs for media related to the media in the item, but which are not exactly the same. The primary use of this tag is to list ISBNs, LCCNs, and OCLC numbers for other editions of the same work. These IDs are used for deduplication purposes in the scanning proces. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#related-external-id

      "urn:isbn:0671038303"
      
    • Optionalrepub_state?: string

      Repub State

      Indicates the current state of a scanned book. Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#repub_state

      "19"
      
    • Optionalrepublisher_date?: string

      Republisher Date

      Date and time in UTC that the item was created archive.org. Set by Scribe3 software.

      Defined by: IA software

      Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#republisher_date

      "20170801165730"
      
    • Optionalrepublisher_operator?: string

      Republisher Operator

      Email of the person who completed republishing the item Set by Scribe3 software. Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#republisher_operator

      "associate-kiana-fekette@archive.org"
      
    • Optionalrepublisher_time?: string

      Republisher Time

      Number of seconds required to republish text Set by Scribe3 software. Defined by: IA software Edit access: IA software INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#republisher_time

      "504"
      
    • Optionalrights?: string

      Rights

      Rights statement Please see licenseurl for URL-based rights designations, like Creative Commons. For other rights information or statements, use the rights field. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#rights

      "Permission is granted under the Wikimedia Foundation's "
      
      "These National Treasury publications may not be reproduced wholly or in part without the express authorisation of the National Treasury in writing unless used for non-profit purposes."
      
    • Optionalrotation?: IaFileRotation

      Camera Rotation: represents the rotation (in degrees) of the camera. Typical values are: 0, 90, 180, 270

      "90"
      
    • Optionalruntime?: string | string[]

      Run Time

      Length of an audio or video item Uploader can set this field, but most often we have determined and set this value during the derive process. Defined by: IA software Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#runtime

      "00:15:00"
      
      "2:12"
      
      "0:23"
      
    • Optionalscandate?: string

      Scan Date

      The date and time in UTC that the media was captured. When an physical item is scanned/digitized, scandate represents the date/time that the digitization occurred. For web items, scandate represents the date/time the first WARC file in the item was created. For TV and radio items, scandate represents the begining time of the recording. Formats: YYYYMMDDHHMMSS YYYYMMDD YYYY YYYY-MM-DD HH:MM:SS Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#scandate

      "20170329201345"
      
    • Optionalscanfee?: string

      Scan Fee

      Scanning fee used during billing process Set by software based on parameters for each scanning partner Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#scanfee

      "100"
      
      "300;10;200"
      
      "0;1.45;0"
      
    • Optionalscanner?: string

      Scanner

      Machinery used to digitize or collect the media Primarily an internally used field. For digitized texts this represents the individual digitization station (e.g. Scribe 2 in the New Jersey center). For web items this represents the crawl machine used to gather the data. For films this represents the film scanner. For CDs this represents the version of the scanning software used for that CD. For end-user contriuted items, this represents the software used to upload the item. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#scanner

      "scribe2.nj.archive.org"
      
      "selenium-101.us.archive.org"
      
      "Lasergraphics Scanstation"
      
      "ArchiveCD Version 2.1.15"
      
      "Internet Archive HTML5 Uploader 1.6.3"
      
    • Optionalscanningcenter?: string

      Scanning Center

      The location where a digital copy of the media item was created Generally used in conjunction with our scanning services, this tag gives the location where an item was digitized, scanned or captured. Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#scanningcenter

      "boston"
      
    • Optionalshow_related_music_by_track?: boolean

      Related Music by Track

      Adds related tracks to details page Defined by: IA admin Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#show_related_music_by_track

    • Optionalsound?: string

      Sound

      Indicates whether media has sound or is silent Most used values are: sound, silent Mostly used for video items, this field indicates whether the media has related sound or is silent. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#sound

      "sound"
      
      "silent"
      
    • Optionalsource_pixel_height?: number

      Source Pixel Height

      Pixel height of original video stream Primarily used for TV Archive items. Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#source_pixel_height

      480
      
    • Optionalsource_pixel_width?: number

      Source Pixel Width

      Pixel width of original video stream Primarily used for TV Archive items. Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#source_pixel_width

      704
      
    • Optionalsponsor?: string

      Sponsor

      The person or organization that funded the digitization or collection of this media. For physical items (books, film, 78rpm, etc.), this represents the entity that funded the digitization/scanning work. For born-digital items (TV, Radio, Web, etc.) this represents the entity that funded the collection of the items. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#sponsor

      "Kahle-Austin Foundation"
      
    • Optionalsponsordate?: string

      Sponsor Date

      Billing date for scanned materials Related to digitization work. Usually a date string "YYYYMMDD", but can contain notes, such as: "not to be invoiced-past billing period" "Grant ended, item not yet invoiced" "sent20111010" Defined by: IA admin Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#sponsordate

      "20100531"
      
    • Optionalstart_localtime?: string

      Local Start Time

      Start time of program in broadcast time zone Primarily used for TV Archive items. Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#start_localtime

      "2010-03-26 18:00:00"
      
    • Optionalstart_time?: string

      UTC Start Time

      Start time of program in UTC Primarily used for TV Archive items. Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#start_time

      "2010-03-26 15:00:00"
      
    • Optionalstop_time?: string

      UTC Stop Time

      Stop time of program in UTC Primarily used for TV Archive items. Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#stop_time

      "2010-03-26 16:00:00"
      
    • Optionalsubject?: string | string[]

      Subject/Keyword

      Subjects and/or topics covered by the media content Books and other media objects from libraries often use Library of Congress Subject Headings, http://id.loc.gov/authorities/subjects.html. Some collections may use their own controlled vocabulary for setting subjects. Many other items use the subject field as more casual "tags." All alphabets are supported. Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#subject

      "France"
      
    • Optionalsummation?: string
    • Optionaltitle?: string

      Title

      Title of media All alphabets are supported Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#title

      "San Francisco (1955 Cinemascope film)"
      
    • Optionaltrack?: string

      Track number of album. Usually an number, but occasionally has values like "2/14" (track 2 of 14)

    • Optionaltuner?: string

      Skip OCR

      Virtual Channel the video was recorded from Primarily used for TV Archive items. Maps the program number as used in H.222 Program Association Tables and Program Mapping Tables to a channel number that can be entered via digits on a receiver's remote control. Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#tuner

      "Virtual Ch. 24"
      
    • Optionalupdated?: string | string[]

      Updated

      Timestamp in the metadata table for the last time the item's row in that table was written Timestamp is typically when the last task ran on the item, but metadata updates can also be triggered manually. Defined by: IA software Edit access: not editable INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#updated

      "2014-12-05"
      
    • Optionalupdatedate?: string | string[]

      Update Date

      Date the item was updated by updater Any time an item is changed via the editxml page by the updater (see field), a corresponding field is added to the meta.xml. Updatedate fields are added to meta.xml in the order changes have been made, so the oldest dates are listed first. Defined by: IA software Edit access: not editable INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#updatedate

      "2009-03-02 21:48:28"
      
    • Optionalupdater?: string | string[]

      Updater

      Screen name of the account that updated the item After initial upload, when changes are made to the content of an item the account that made changes is included in the meta.xml in an field. Updater fields are added to meta.xml in the order changes have been made, so the first listed updater belongs to the oldest modification. Defined by: IA software Edit access: not editable INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#updater

      "tracey pooh"
      
    • Optionalutc_offset?: number

      UTC Offset

      Offset between local time and UTC Primarily used for TV Archive items. Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#utc_offset

      300
      
      -400
      
    • Optionalvideo_codec?: string

      Video Codec

      Program used to decode video stream Primarily used for TV Archive items. Defined by: IA software Edit access: IA admin INTERNAL USE ONLY

      See https://archive.org/developers/metadata-schema/index.html#video_codec

      "mpeg2video"
      
    • Optionalviruscheck?: "true"

      Virus Check This tag only functions on items of mediatype collection. The tag is either present with a value of true or it should not be present in the item metadata at all. Currently all items uploaded into the open community collections have the virus check task run on them, without needing this tag. Any other collection that needs virus checking should have this tag present in order to trigger the virus check task to run on items uploaded into the collection.

      defined by: IA software edit access: IA admin

    • Optionalvolume?: string

      Volume

      Volume number or name This field is not overwritten by MARC Defined by: uploader Edit access: uploader

      See https://archive.org/developers/metadata-schema/index.html#volume

      "15"
      
    • Optionalwb_filtered?: string
    • Optionalwidth?: number

      Image width (in pixels)