{"id":13994176,"url":"https://github.com/smyja/blackmaria","last_synced_at":"2026-01-14T08:12:33.751Z","repository":{"id":147934878,"uuid":"619136448","full_name":"smyja/blackmaria","owner":"smyja","description":"Python package for webscraping in Natural language","archived":false,"fork":false,"pushed_at":"2023-10-28T14:19:50.000Z","size":113,"stargazers_count":148,"open_issues_count":1,"forks_count":11,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-10-29T00:09:18.978Z","etag":null,"topics":["gpt-3","nlp","openai","python","webscraping"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/smyja.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null},"funding":{"custom":["https://bmc.link/mxro"]}},"created_at":"2023-03-26T11:33:53.000Z","updated_at":"2025-10-04T14:17:22.000Z","dependencies_parsed_at":"2023-05-28T17:15:46.839Z","dependency_job_id":null,"html_url":"https://github.com/smyja/blackmaria","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/smyja/blackmaria","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smyja%2Fblackmaria","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smyja%2Fblackmaria/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smyja%2Fblackmaria/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smyja%2Fblackmaria/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/smyja","download_url":"https://codeload.github.com/smyja/blackmaria/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smyja%2Fblackmaria/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28413625,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-14T05:26:33.345Z","status":"ssl_error","status_checked_at":"2026-01-14T05:21:57.251Z","response_time":107,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":["gpt-3","nlp","openai","python","webscraping"],"created_at":"2024-08-09T14:02:44.961Z","updated_at":"2026-01-14T08:12:33.728Z","avatar_url":"https://github.com/smyja.png","language":"Python","funding_links":["https://bmc.link/mxro"],"categories":["Python"],"sub_categories":[],"readme":"## Black Maria\n\n### Getting Started\n#### Prerequisites\n- [Python 3.6+](https://www.python.org/downloads/)\n\n#### Installation\n- export `OPEN_AI_KEY` to your environment variables\n- `pip install blackmaria`\n\n### What is Black Maria?\nBlack Maria is a Python library for web scraping any webpage using natural language.\n\n### How to use Black Maria?\nBlack Maria uses [guardrails](https://github.com/ShreyaR/guardrails). Guardrails are a set of instructions that tell the LLM what the output should look like. \n\n```python\nfrom blackmaria import maria\n\nurl=\"https://yellowjackets.fandom.com/wiki/F_Sharp\"\nspec=(\"\"\"\n    \u003crail version=\"0.1\"\u003e\n\n    \u003coutput\u003e\n        \u003cobject name=\"movie\" format=\"length: 2\"\u003e\n            \u003cstring\n                name=\"summary\"\n                description=\"the summary section of the movie\"\n                format=\"length: 200 240\"\n                on-fail-length=\"noop\"\n            /\u003e\n            \u003cobject name=\"cast\" description=\"The cast in the movie\" format=\"length: 3\"\u003e\n            \u003clist name=\"starring\"\u003e\n        \n                \u003cstring format=\"two-words\"\n                on-fail-two-words=\"reask\"\n                description=\"The starring section for the movie and roles\"\n        \n                \n                /\u003e\n            \u003c/list\u003e\n            \u003clist name=\"guest_starring\"\u003e\n            \n            \u003cstring format=\"two-words\"\n                on-fail-two-words=\"reask\"\n                description=\"The Guest starring section and roles\"\n                /\u003e\n            \u003c/list\u003e\n            \u003clist name=\"co-starring\"\u003e\n            \n            \u003cstring format=\"two-words\"\n                on-fail-two-words=\"reask\"\n                description=\"the starring section\"\n                /\u003e\n            \u003c/list\u003e\n            \n            \u003c/object\u003e\n\n\n        \u003c/object\u003e\n    \u003c/output\u003e\n\n\n    \u003cprompt\u003e\n\n    Query string here.\n\n    @xml_prefix_prompt\n\n    {output_schema}\n\n    @json_suffix_prompt_v2_wo_none\n    \u003c/prompt\u003e\n    \u003c/rail\u003e\n    \"\"\")\nquery=\"provide details about the movie,summary,cast,cast.starring,cast.guest_starring,cast.co-starring\"\nquery_response=maria.night_crawler(url=url,spec=spec,query=query)\nprint(query_response)\n\n\n```\n### Output\n```json\n{\n  \"movie\": {\n    \"summary\": \"As the teens get their bearings among the wreckage, Misty finds hell on earth quite becoming. In the present: revenge, sex homework and the policeman formerly known as Goth.\",\n    \"cast\": {\n      \"starring\": [\n        \"Lottie Matthews\",\n        \"Vanessa Palmer\",\n        \"Misty Quigley\",\n        \"Shauna Sadecki\",\n        \"Natalie Scatorccio\",\n        \"Taissa Turner\"\n      ],\n      \"guest_starring\": [\n        \"Akilah\",\n        \"Laura Lee\",\n        \"Mari\",\n        \"Adam Martin\",\n        \"Javi Martinez\",\n        \"Travis Martinez\",\n        \"Jessica Roberts\",\n        \"Jeff Sadecki\",\n        \"Ben Scott\",\n        \"Jackie Taylor\"\n      ],\n      \"co-starring\": [\"Kevyn Tan\", \"Simone\"]\n    }\n  }\n}\n\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsmyja%2Fblackmaria","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsmyja%2Fblackmaria","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsmyja%2Fblackmaria/lists"}