{"id":20706497,"url":"https://github.com/pythoncoderunicorn/harrypotterbooks","last_synced_at":"2026-04-18T20:02:19.525Z","repository":{"id":79731699,"uuid":"541217818","full_name":"PythonCoderUnicorn/HarryPotterBooks","owner":"PythonCoderUnicorn","description":"Harry Potter books for Text Analysis","archived":false,"fork":false,"pushed_at":"2022-09-25T16:01:35.000Z","size":2333,"stargazers_count":3,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-11T05:18:39.556Z","etag":null,"topics":["books","harrypotter","nlp","text-analysis"],"latest_commit_sha":null,"homepage":"","language":"R","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/PythonCoderUnicorn.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-09-25T15:32:29.000Z","updated_at":"2024-10-16T09:25:11.000Z","dependencies_parsed_at":"2023-03-12T09:07:53.478Z","dependency_job_id":null,"html_url":"https://github.com/PythonCoderUnicorn/HarryPotterBooks","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/PythonCoderUnicorn/HarryPotterBooks","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PythonCoderUnicorn%2FHarryPotterBooks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PythonCoderUnicorn%2FHarryPotterBooks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PythonCoderUnicorn%2FHarryPotterBooks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PythonCoderUnicorn%2FHarryPotterBooks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/PythonCoderUnicorn","download_url":"https://codeload.github.com/PythonCoderUnicorn/HarryPotterBooks/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PythonCoderUnicorn%2FHarryPotterBooks/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31982755,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-18T17:30:12.329Z","status":"ssl_error","status_checked_at":"2026-04-18T17:29:59.069Z","response_time":103,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["books","harrypotter","nlp","text-analysis"],"created_at":"2024-11-17T01:23:28.705Z","updated_at":"2026-04-18T20:02:19.507Z","avatar_url":"https://github.com/PythonCoderUnicorn.png","language":"R","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n\u003cimg height='250' align='right' src=\"img/harrypotter.png\"\u003e\n\n# Harry Potter Books\n\nHarry Potter books for Text Analysis.\n\nThis work was inspired by [Bradley Boehmke's R package](https://github.com/bradleyboehmke/harrypotter) which claimed to have\nclean and tidy text data. Upon further inspection the text was in need of further\ntext cleaning, including adding paragraphs to the end of a chapter and removing the many\nspecial characters. \n\n\nThis repository has kept each book in `csv` files as to be most applicable to any user who wants to do text analysis and not deal with a `.rda` file. Each `csv` is a book and each book has 2 columns: chapter (in uppercase) and text.\n\n\nThe book order:\n\n- `philosophers_stone`: Harry Potter and the Philosophers Stone, published in 1997\n- `chamber_of_secrets`: Harry Potter and the Chamber of Secrets, published in 1998\n- `prisoner_of_azkaban`: Harry Potter and the Prisoner of Azkaban, published in 1999\n- `goblet_of_fire`: Harry Potter and the Goblet of Fire, published in 2000\n- `order_of_the_phoenix`: Harry Potter and the Order of the Phoenix, published in 2003\n- `half_blood_prince`: Harry Potter and the Half-Blood Prince, published in 2005\n- `deathly_hallows`: Harry Potter and the Deathly Hallows, published in 2007\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpythoncoderunicorn%2Fharrypotterbooks","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpythoncoderunicorn%2Fharrypotterbooks","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpythoncoderunicorn%2Fharrypotterbooks/lists"}