{"action":"create","ckan_id":null,"date_created":"Wed, 03 Sep 2025 20:59:55 GMT","date_finished":null,"harvest_job_id":"22b5b228-5c22-478f-beac-c2ad93490783","harvest_source_id":"8e0c0837-e26e-432c-bb3b-dd0df4f1b9af","id":"0c5ca480-e848-440d-8b16-950fe7dd8398","identifier":"https://data.cdc.gov/api/views/7rih-tqi5","parent_identifier":null,"source_hash":"c818d29f2c28aafb8fe40f4892692452e325bffc6e0d20e3ed191f9f12452a1d","source_raw":"{\"@type\": \"dcat:Dataset\", \"accessLevel\": \"public\", \"accrualPeriodicity\": \"Irregular\", \"bureauCode\": [\"009:20\"], \"contactPoint\": {\"@type\": \"vcard:Contact\", \"fn\": \"NCSTLTPHIW(PHIC)\", \"hasEmail\": \"mailto:cdcinfo@cdc.gov\"}, \"describedBy\": \"https://github.com/cmheilig/harvest-cdc-journals?tab=readme-ov-file#cdc-text-corpora-for-learners\", \"description\": \"This landing page is part of the <a href=\\\"https://github.com/cmheilig/harvest-cdc-journals\\\">CDC Text Corpora for Learners</a> program; this includes the compiled 33,576 CDC Text for Learners <a href=\\\"https://data.cdc.gov/National-Center-for-State-Tribal-Local-and-Territo/CDC-Text-Corpora-for-Learners-HTML-Mirrors-of-MMWR/ut5n-bmc3/about_data\\\">HTML mirrors</a> of the MMWR <a href=\\\"https://www.cdc.gov/mmwr/\\\">Morbidity and Mortality Weekly Report</a> including its series: <i>Weekly Reports</i>, <i>Recommendations and Reports</i>, <i>Surveillance Summaries</i>, <i>Supplements</i>, and <i>Notifiable Diseases</i>, a subset of <i>Weekly Reports</i>, constructed ad hoc; EID <a href=\\\"https://www.cdc.gov/eid/\\\">Emerging Infectious Diseases</a>; and PCD <a href=\\\"https://www.cdc.gov/pcd/\\\">Preventing Chronic Disease</a>\\n\\nThe data represented here is the tabulated <a href=\\\"https://github.com/cmheilig/harvest-cdc-journals/blob/main/README.md#metadata-fields\\\">metadata</a> of the combined 33,567 articles of the  <a href=\\\"https://github.com/cmheilig/harvest-cdc-journals?tab=readme-ov-file#collections\\\">MMWR, EID, and PCD collections</a> whose contents are organized into three ZIP archived JSON files per collection. The JSON value output formats include UTF-8 HTML, UTF-8 markdown, and ASCII plain text.\\n\\nThe <a href=\\\"https://github.com/cmheilig/harvest-cdc-journals?tab=readme-ov-file#collections\\\">JSON files</a> are located in the <a href=\\\"https://github.com/cmheilig/harvest-cdc-journals\\\">program's repository.</a> This version was constructed on 2024-03-01 using source content retrieved on 2024-01-09.\", \"distribution\": [{\"@type\": \"dcat:Distribution\", \"downloadURL\": \"https://data.cdc.gov/api/views/7rih-tqi5/rows.csv?accessType=DOWNLOAD\", \"mediaType\": \"text/csv\"}, {\"@type\": \"dcat:Distribution\", \"downloadURL\": \"https://data.cdc.gov/api/views/7rih-tqi5/rows.json?accessType=DOWNLOAD\", \"mediaType\": \"application/json\"}, {\"@type\": \"dcat:Distribution\", \"downloadURL\": \"https://data.cdc.gov/api/views/7rih-tqi5/rows.rdf?accessType=DOWNLOAD\", \"mediaType\": \"application/rdf+xml\"}, {\"@type\": \"dcat:Distribution\", \"downloadURL\": \"https://data.cdc.gov/api/views/7rih-tqi5/rows.xml?accessType=DOWNLOAD\", \"mediaType\": \"application/xml\"}], \"identifier\": \"https://data.cdc.gov/api/views/7rih-tqi5\", \"isPartOf\": \"CDC Text Corpora for Learners\", \"issued\": \"2024-03-19\", \"keyword\": [\"corpora\", \"corpus\", \"data science\", \"eid\", \"harvest-cdc-journals\", \"informatics\", \"language\", \"machine learning\", \"ml\", \"mmwr\", \"ncstltphiw\", \"pcd\", \"phic\", \"smokefree indoor air\", \"text analysis\"], \"landingPage\": \"https://github.com/cmheilig/harvest-cdc-journals\", \"license\": \"http://creativecommons.org/publicdomain/zero/1.0/legalcode\", \"modified\": \"2025-07-16\", \"programCode\": [\"009:020\"], \"publisher\": {\"@type\": \"org:Organization\", \"name\": \"Centers for Disease Control and Prevention\"}, \"references\": [\"\\\"https://github.com/cmheilig/harvest-cdc-journals?tab=readme-ov-file\\\"\", \"\\\"https://www.cdc.gov/mmwr/\\\"\", \"\\\"https://www.cdc.gov/pcd/\\\"\", \"\\\"https://wwwnc.cdc.gov/eid\\\"\"], \"temporal\": \"1982 - 2023\", \"theme\": [\"Local\", \"National Center for State\", \"Tribal\", \"and Territorial Public Health Infrastructure and Workforce\"], \"title\": \"CDC Text Corpora for Learners: MMWR, EID, and PCD Article Metadata\"}","source_transform":null,"status":"error"}