{"id":22974372,"url":"https://github.com/diversen/pdftotext-sanitize","last_synced_at":"2025-08-10T22:42:51.854Z","repository":{"id":138270930,"uuid":"56320494","full_name":"diversen/pdftotext-sanitize","owner":"diversen","description":"Sanitizes pdftotext output","archived":false,"fork":false,"pushed_at":"2016-04-21T09:02:04.000Z","size":14,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-02T07:28:34.489Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"PHP","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/diversen.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":"2016-04-15T13:00:53.000Z","updated_at":"2016-04-15T16:22:44.000Z","dependencies_parsed_at":null,"dependency_job_id":"b728409a-cb7a-4d65-bd0f-d53e9fc179b6","html_url":"https://github.com/diversen/pdftotext-sanitize","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/diversen/pdftotext-sanitize","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diversen%2Fpdftotext-sanitize","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diversen%2Fpdftotext-sanitize/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diversen%2Fpdftotext-sanitize/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diversen%2Fpdftotext-sanitize/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/diversen","download_url":"https://codeload.github.com/diversen/pdftotext-sanitize/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/diversen%2Fpdftotext-sanitize/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259412320,"owners_count":22853404,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":[],"created_at":"2024-12-15T00:00:38.507Z","updated_at":"2025-06-12T06:32:32.848Z","avatar_url":"https://github.com/diversen.png","language":"PHP","funding_links":[],"categories":[],"sub_categories":[],"readme":"# pdftotext sanitize\n\nSanitize output from pdftotext (or pdftohtml)\n\nActually pdftohtml is easier to copy-paste from, than pdftotext\n\nTrim strings\nRemove trailing '-'\nRemove double newlines\n\n# Install\n\n    git clone https://github.com/diversen/pdftotext-sanitize\n\n    cd pdftotext-sanitize\n\n    composer update\n\n    php index.php file-tosanitize.txt\n\nWill echo to std output. \n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdiversen%2Fpdftotext-sanitize","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdiversen%2Fpdftotext-sanitize","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdiversen%2Fpdftotext-sanitize/lists"}