{"id":37711476,"url":"https://github.com/qurator-spk/mods4pandas","last_synced_at":"2026-01-16T13:19:44.367Z","repository":{"id":37444579,"uuid":"204953483","full_name":"qurator-spk/mods4pandas","owner":"qurator-spk","description":"Extract the MODS/ALTO metadata of a bunch of METS/ALTO files into pandas DataFrames for data analysis","archived":false,"fork":false,"pushed_at":"2025-08-06T18:24:29.000Z","size":445,"stargazers_count":12,"open_issues_count":30,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-08-06T20:30:58.338Z","etag":null,"topics":["alto","alto-xml","data-analysis","digital-humanities","library","mets","mods","pandas","qurator"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/qurator-spk.png","metadata":{"files":{"readme":"README-DEV.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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,"zenodo":null}},"created_at":"2019-08-28T14:37:30.000Z","updated_at":"2025-08-06T18:24:33.000Z","dependencies_parsed_at":"2023-11-23T15:23:46.236Z","dependency_job_id":"8bb09c27-0b3a-48c1-b192-b8210b5db6ea","html_url":"https://github.com/qurator-spk/mods4pandas","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/qurator-spk/mods4pandas","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qurator-spk%2Fmods4pandas","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qurator-spk%2Fmods4pandas/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qurator-spk%2Fmods4pandas/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qurator-spk%2Fmods4pandas/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/qurator-spk","download_url":"https://codeload.github.com/qurator-spk/mods4pandas/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/qurator-spk%2Fmods4pandas/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28479026,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-16T11:59:17.896Z","status":"ssl_error","status_checked_at":"2026-01-16T11:55:55.838Z","response_time":107,"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":["alto","alto-xml","data-analysis","digital-humanities","library","mets","mods","pandas","qurator"],"created_at":"2026-01-16T13:19:43.566Z","updated_at":"2026-01-16T13:19:44.355Z","avatar_url":"https://github.com/qurator-spk.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"```\npip install -r requirements-dev.txt\n```\n\nTo run tests:\n```\npip install -e .\npytest\n```\n\nTo run a test with profiling:\n\n1. Make sure graphviz is installed\n2. Run pytest with with profiling enabled:\n  ```\n  pytest --profile-svg -k test_page_info\n  ```\n\nTo directly test the CLIs using our test data, run:\n\n```\nmods4pandas --output-page-info \"page_info_df.parquet\" src/mods4pandas/tests/data/mets-mods\nalto4pandas src/mods4pandas/tests/data/alto\n```\n\n\n# How to use pre-commit\n\nThis project optionally uses [pre-commit](https://pre-commit.com) to check commits. To use it:\n\n- Install pre-commit, e.g. `pip install -r requirements-dev.txt`\n- Install the repo-local git hooks: `pre-commit install`\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqurator-spk%2Fmods4pandas","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fqurator-spk%2Fmods4pandas","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqurator-spk%2Fmods4pandas/lists"}