{"id":18838211,"url":"https://github.com/inspirehep/hepcrawl","last_synced_at":"2025-04-11T11:03:50.191Z","repository":{"id":45580471,"uuid":"44979576","full_name":"inspirehep/hepcrawl","owner":"inspirehep","description":"Scrapy project for feeds into INSPIRE-HEP","archived":false,"fork":false,"pushed_at":"2024-07-18T17:44:26.000Z","size":4166,"stargazers_count":18,"open_issues_count":37,"forks_count":30,"subscribers_count":20,"default_branch":"master","last_synced_at":"2025-01-12T15:06:29.035Z","etag":null,"topics":["crawler","harvest-data","publishing","python"],"latest_commit_sha":null,"homepage":"http://inspirehep.net","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/inspirehep.png","metadata":{"files":{"readme":"README.rst","changelog":null,"contributing":"docs/contributing.rst","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}},"created_at":"2015-10-26T15:55:58.000Z","updated_at":"2024-11-30T08:22:17.000Z","dependencies_parsed_at":"2024-02-28T14:45:42.753Z","dependency_job_id":"6a688a34-1876-4897-8838-3c934dea8210","html_url":"https://github.com/inspirehep/hepcrawl","commit_stats":{"total_commits":524,"total_committers":31,"mean_commits":"16.903225806451612","dds":0.7824427480916031,"last_synced_commit":"e3d7264e5887240fe3e54935a8a1dadd7a75d82d"},"previous_names":[],"tags_count":25,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inspirehep%2Fhepcrawl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inspirehep%2Fhepcrawl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inspirehep%2Fhepcrawl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inspirehep%2Fhepcrawl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/inspirehep","download_url":"https://codeload.github.com/inspirehep/hepcrawl/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":234669991,"owners_count":18869115,"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":["crawler","harvest-data","publishing","python"],"created_at":"2024-11-08T02:38:20.332Z","updated_at":"2025-01-19T17:07:11.273Z","avatar_url":"https://github.com/inspirehep.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"..\n    This file is part of hepcrawl.\n    Copyright (C) 2015, 2016, 2017 CERN.\n\n    hepcrawl is a free software; you can redistribute it and/or modify it\n    under the terms of the Revised BSD License; see LICENSE file for\n    more details.\n\n\n==========\n HEPcrawl\n==========\n\n.. image:: https://img.shields.io/travis/inspirehep/hepcrawl.svg\n        :target: https://travis-ci.org/inspirehep/hepcrawl\n\n.. image:: https://img.shields.io/github/tag/inspirehep/hepcrawl.svg\n        :target: https://github.com/inspirehep/hepcrawl/releases\n\n.. image:: https://img.shields.io/pypi/dm/hepcrawl.svg\n        :target: https://pypi.python.org/pypi/hepcrawl\n\n.. image:: https://img.shields.io/github/license/inspirehep/hepcrawl.svg\n        :target: https://github.com/inspirehep/hepcrawl/blob/master/LICENSE\n\n\nHEPcrawl is a harvesting library based on Scrapy (http://scrapy.org) for INSPIRE-HEP\n(http://inspirehep.net) that focuses on automatic and semi-automatic retrieval of\nnew content from all the sources the site aggregates. In particular content from\nmajor and minor publishers in the field of High-Energy Physics.\n\nThe project is currently in early stage of development.\n\nSee full documentation at http://pythonhosted.org/hepcrawl\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finspirehep%2Fhepcrawl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Finspirehep%2Fhepcrawl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finspirehep%2Fhepcrawl/lists"}