{
"@context": "https://w3id.org/ro/crate/1.1/context",
"@graph": [
{
"@id": "ro-crate-metadata.json",
"@type": "CreativeWork",
"about": {
"@id": "./"
},
"conformsTo": {
"@id": "https://w3id.org/ro/crate/1.1"
},
"license": {
"@id": "https://creativecommons.org/publicdomain/zero/1.0/"
}
},
{
"@id": "./",
"@type": "Dataset",
"datePublished": "2023-10-23T05:02:01+00:00",
"description": "This dataset of digitised newspaper articles from Trove was created using the Trove Newspaper Harvester. Details of the search query used to generate this dataset can be found in the harvester_config.json file.",
"hasPart": [
{
"@id": "harvester_config.json"
},
{
"@id": "text"
},
{
"@id": "results.csv"
}
],
"mainEntity": {
"@id": "#harvester_run"
},
"name": "Dataset of digitised newspaper articles harvested from Trove on 23 October 2023"
},
{
"@id": "harvester_config.json",
"@type": "File",
"encodingFormat": "application/json",
"name": "Trove Newspaper Harvester configuration file"
},
{
"@id": "text",
"@type": [
"File",
"Dataset"
],
"dateCreated": "2023-10-23T16:02:30.929438+11:00",
"description": "There is one text file per article. The file titles include basic article metadata \u2013 the date of the article, the id number of the newspaper, and the id number of the article.",
"license": {
"@id": "http://rightsstatements.org/vocab/CNE/1.0/"
},
"name": "Text files harvested from articles",
"size": 272
},
{
"@id": "results.csv",
"@type": [
"File",
"Dataset"
],
"contentSize": 80336,
"dateCreated": "2023-10-23T16:02:30.944094+11:00",
"encodingFormat": "text/csv",
"license": {
"@id": "http://rightsstatements.org/vocab/NKC/1.0/"
},
"name": "Metadata of harvested articles in CSV format",
"size": 272
},
{
"@id": "#harvester_run",
"@type": "CreateAction",
"actionStatus": {
"@id": "http://schema.org/CompletedActionStatus"
},
"endDate": "2023-10-23T16:02:30.929438+11:00",
"instrument": "https://github.com/wragge/trove-newspaper-harvester",
"name": "Run of harvester",
"object": "harvester_config.json",
"result": [
{
"@id": "text"
},
{
"@id": "results.csv"
}
],
"startDate": "2023-10-23T16:02:01.306088+11:00"
},
{
"@id": "https://github.com/wragge/trove-newspaper-harvester",
"@type": "SoftwareApplication",
"description": "The Trove Newspaper (& Gazette) Harvester makes it easy to download large quantities of digitised articles from Trove\u2019s newspapers and gazettes.",
"documentation": "https://wragge.github.io/trove-newspaper-harvester/",
"name": "Trove Newspaper and Gazette Harvester",
"softwareVersion": "0.7.2",
"url": "https://github.com/wragge/trove-newspaper-harvester"
},
{
"@id": "http://rightsstatements.org/vocab/NKC/1.0/",
"@type": "CreativeWork",
"description": "The organization that has made the Item available reasonably believes that the Item is not restricted by copyright or related rights, but a conclusive determination could not be made.",
"name": "No Known Copyright",
"url": "http://rightsstatements.org/vocab/NKC/1.0/"
},
{
"@id": "http://rightsstatements.org/vocab/CNE/1.0/",
"@type": "CreativeWork",
"description": "The copyright and related rights status of this Item has not been evaluated.",
"name": "Copyright Not Evaluated",
"url": "http://rightsstatements.org/vocab/CNE/1.0/"
},
{
"@id": "https://creativecommons.org/publicdomain/zero/1.0/",
"@type": "CreativeWork",
"name": "CC0 Public Domain Dedication",
"url": "https://creativecommons.org/publicdomain/zero/1.0/"
}
]
}
{
"@context": "https://w3id.org/ro/crate/1.1/context",
"@graph": [
{
"@id": "./",
"@type": "Dataset",
"author": [
{
"@id": "0000-0001-7956-4498"
}
],
"datePublished": "2023-10-25",
"description": "A GLAM Workbench repository",
"hasPart": [
{
"@id": "newspaper_harvester_app.ipynb"
},
{
"@id": "Using-TroveHarvester-to-get-newspaper-articles-in-bulk.ipynb"
},
{
"@id": "Explore-harvested-text-files.ipynb"
},
{
"@id": "display_harvest_results_using_datasette.ipynb"
},
{
"@id": "Exploring-your-TroveHarvester-data.ipynb"
},
{
"@id": "harvest-specific-days.ipynb"
}
],
"license": {
"@id": "https://spdx.org/licenses/MIT"
},
"name": "trove-newspaper-harvester",
"url": "https://github.com/GLAM-Workbench/trove-newspaper-harvester",
"version": "v2.0.1"
},
{
"@id": "ro-crate-metadata.json",
"@type": "CreativeWork",
"about": {
"@id": "./"
},
"conformsTo": {
"@id": "https://w3id.org/ro/crate/1.1"
},
"license": {
"@id": "https://creativecommons.org/publicdomain/zero/1.0/"
}
},
{
"@id": "newspaper_harvester_app.ipynb",
"@type": [
"File",
"SoftwareSourceCode"
],
"author": [
{
"@id": "https://orcid.org/0000-0001-7956-4498"
}
],
"codeRepository": "https://github.com/GLAM-Workbench/trove-newspaper-harvester",
"conformsTo": {
"@id": "https://purl.archive.org/textcommons/profile#Notebook"
},
"description": "",
"encodingFormat": "application/x-ipynb+json",
"name": "Trove Newspaper & Gazette Harvester",
"programmingLanguage": {
"@id": "https://www.python.org/downloads/release/python-31012/"
}
},
{
"@id": "Using-TroveHarvester-to-get-newspaper-articles-in-bulk.ipynb",
"@type": [
"File",
"SoftwareSourceCode"
],
"author": [
{
"@id": "https://orcid.org/0000-0001-7956-4498"
}
],
"codeRepository": "https://github.com/GLAM-Workbench/trove-newspaper-harvester",
"conformsTo": {
"@id": "https://purl.archive.org/textcommons/profile#Notebook"
},
"description": "",
"encodingFormat": "application/x-ipynb+json",
"name": "Using TroveHarvester to get newspaper and gazette articles in bulk",
"programmingLanguage": {
"@id": "https://www.python.org/downloads/release/python-31012/"
}
},
{
"@id": "Explore-harvested-text-files.ipynb",
"@type": [
"File",
"SoftwareSourceCode"
],
"author": [
{
"@id": "https://orcid.org/0000-0001-7956-4498"
}
],
"codeRepository": "https://github.com/GLAM-Workbench/trove-newspaper-harvester",
"conformsTo": {
"@id": "https://purl.archive.org/textcommons/profile#Notebook"
},
"description": "",
"encodingFormat": "application/x-ipynb+json",
"name": "Explore harvested text files",
"programmingLanguage": {
"@id": "https://www.python.org/downloads/release/python-31012/"
}
},
{
"@id": "display_harvest_results_using_datasette.ipynb",
"@type": [
"File",
"SoftwareSourceCode"
],
"author": [
{
"@id": "https://orcid.org/0000-0001-7956-4498"
}
],
"codeRepository": "https://github.com/GLAM-Workbench/trove-newspaper-harvester",
"conformsTo": {
"@id": "https://purl.archive.org/textcommons/profile#Notebook"
},
"description": "",
"encodingFormat": "application/x-ipynb+json",
"name": "Display the results of a harvest as a searchable database using Datasette",
"programmingLanguage": {
"@id": "https://www.python.org/downloads/release/python-31012/"
}
},
{
"@id": "Exploring-your-TroveHarvester-data.ipynb",
"@type": [
"File",
"SoftwareSourceCode"
],
"author": [
{
"@id": "https://orcid.org/0000-0001-7956-4498"
}
],
"codeRepository": "https://github.com/GLAM-Workbench/trove-newspaper-harvester",
"conformsTo": {
"@id": "https://purl.archive.org/textcommons/profile#Notebook"
},
"description": "",
"encodingFormat": "application/x-ipynb+json",
"name": "Exploring your harvested data",
"programmingLanguage": {
"@id": "https://www.python.org/downloads/release/python-31012/"
}
},
{
"@id": "harvest-specific-days.ipynb",
"@type": [
"File",
"SoftwareSourceCode"
],
"author": [
{
"@id": "https://orcid.org/0000-0001-7956-4498"
}
],
"codeRepository": "https://github.com/GLAM-Workbench/trove-newspaper-harvester",
"conformsTo": {
"@id": "https://purl.archive.org/textcommons/profile#Notebook"
},
"description": "",
"encodingFormat": "application/x-ipynb+json",
"name": "Harvesting articles that mention \"Anzac Day\" on Anzac Day",
"programmingLanguage": {
"@id": "https://www.python.org/downloads/release/python-31012/"
}
},
{
"@id": "https://orcid.org/0000-0001-7956-4498",
"@type": "Person",
"name": "Sherratt, Tim"
},
{
"@id": "https://spdx.org/licenses/MIT",
"@type": "CreativeWork",
"name": "MIT License",
"url": "https://spdx.org/licenses/MIT.html"
},
{
"@id": "https://creativecommons.org/publicdomain/zero/1.0/",
"@type": "CreativeWork",
"name": "CC0 Public Domain Dedication",
"url": "https://creativecommons.org/publicdomain/zero/1.0/"
},
{
"@id": "https://www.python.org/downloads/release/python-31012/",
"@type": [
"ComputerLanguage",
"SoftwareApplication"
],
"name": "Python 3.10.12",
"url": "https://www.python.org/downloads/release/python-31012/",
"version": "3.10.12"
},
{
"@id": "#create_version_v2_0_1",
"@type": "UpdateAction",
"actionStatus": {
"@id": "http://schema.org/CompletedActionStatus"
},
"endDate": "2023-10-25",
"name": "Create version v2.0.1"
}
]
}
The guide to Trove data will document in detail the types of content available through Trove, and what data is accessible for each content type. It will describe both the possibilities and limits of Trove data, enabling researchers to develop a critical understanding of Trove as a source for digital research.