{"id":42833607,"url":"https://github.com/linw1995/data_extractor","last_synced_at":"2026-01-30T11:36:32.553Z","repository":{"id":45281906,"uuid":"182090474","full_name":"linw1995/data_extractor","owner":"linw1995","description":"Combine XPath, CSS Selectors and JSONPath for Web data extracting.","archived":false,"fork":false,"pushed_at":"2024-12-25T03:18:00.000Z","size":1124,"stargazers_count":29,"open_issues_count":5,"forks_count":5,"subscribers_count":1,"default_branch":"master","last_synced_at":"2026-01-08T07:56:35.382Z","etag":null,"topics":["css-selectors","data-extraction","data-extractor","jsonpath","xpath"],"latest_commit_sha":null,"homepage":"https://data-extractor.rtfd.io/en/latest/quickstarts.html","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/linw1995.png","metadata":{"files":{"readme":"README.rst","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2019-04-18T13:13:04.000Z","updated_at":"2025-08-13T17:55:15.000Z","dependencies_parsed_at":"2022-09-22T19:21:02.848Z","dependency_job_id":"3173ee5f-e6e1-40ca-bf6e-3007c7195172","html_url":"https://github.com/linw1995/data_extractor","commit_stats":null,"previous_names":[],"tags_count":41,"template":false,"template_full_name":null,"purl":"pkg:github/linw1995/data_extractor","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/linw1995%2Fdata_extractor","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/linw1995%2Fdata_extractor/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/linw1995%2Fdata_extractor/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/linw1995%2Fdata_extractor/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/linw1995","download_url":"https://codeload.github.com/linw1995/data_extractor/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/linw1995%2Fdata_extractor/sbom","scorecard":{"id":591595,"data":{"date":"2025-08-11","repo":{"name":"github.com/linw1995/data_extractor","commit":"ca1a4c4dacec7852590ad7bbf1bee421a3ab1e4a"},"scorecard":{"version":"v5.2.1-40-gf6ed084d","commit":"f6ed084d17c9236477efd66e5b258b9d4cc7b389"},"score":3.1,"checks":[{"name":"Code-Review","score":0,"reason":"Found 0/21 approved changesets -- score normalized to 0","details":null,"documentation":{"short":"Determines if the project requires human code review before pull requests (aka merge requests) are merged.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#code-review"}},{"name":"Dangerous-Workflow","score":10,"reason":"no dangerous workflow patterns detected","details":null,"documentation":{"short":"Determines if the project's GitHub Action workflows avoid dangerous patterns.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#dangerous-workflow"}},{"name":"Packaging","score":-1,"reason":"packaging workflow not detected","details":["Warn: no GitHub/GitLab publishing workflow detected."],"documentation":{"short":"Determines if the project is published as a package that others can easily download, install, easily update, and uninstall.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#packaging"}},{"name":"Maintained","score":0,"reason":"0 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 0","details":null,"documentation":{"short":"Determines if the project is \"actively maintained\".","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#maintained"}},{"name":"Binary-Artifacts","score":10,"reason":"no binaries found in the repo","details":null,"documentation":{"short":"Determines if the project has generated executable (binary) artifacts in the source repository.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#binary-artifacts"}},{"name":"Token-Permissions","score":0,"reason":"detected GitHub workflow tokens with excessive permissions","details":["Warn: no topLevel permission defined: .github/workflows/release.yml:1","Warn: no topLevel permission defined: .github/workflows/test.yml:1","Info: no jobLevel write permissions found"],"documentation":{"short":"Determines if the project's workflows follow the principle of least privilege.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#token-permissions"}},{"name":"Pinned-Dependencies","score":0,"reason":"dependency not pinned by hash detected -- score normalized to 0","details":["Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/release.yml:12: update your workflow using https://app.stepsecurity.io/secureworkflow/linw1995/data_extractor/release.yml/master?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/release.yml:14: update your workflow using https://app.stepsecurity.io/secureworkflow/linw1995/data_extractor/release.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/release.yml:22: update your workflow using https://app.stepsecurity.io/secureworkflow/linw1995/data_extractor/release.yml/master?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/release.yml:31: update your workflow using https://app.stepsecurity.io/secureworkflow/linw1995/data_extractor/release.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/test.yml:16: update your workflow using https://app.stepsecurity.io/secureworkflow/linw1995/data_extractor/test.yml/master?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/test.yml:18: update your workflow using https://app.stepsecurity.io/secureworkflow/linw1995/data_extractor/test.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/test.yml:23: update your workflow using https://app.stepsecurity.io/secureworkflow/linw1995/data_extractor/test.yml/master?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/test.yml:32: update your workflow using https://app.stepsecurity.io/secureworkflow/linw1995/data_extractor/test.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/test.yml:42: update your workflow using https://app.stepsecurity.io/secureworkflow/linw1995/data_extractor/test.yml/master?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/test.yml:44: update your workflow using https://app.stepsecurity.io/secureworkflow/linw1995/data_extractor/test.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/test.yml:49: update your workflow using https://app.stepsecurity.io/secureworkflow/linw1995/data_extractor/test.yml/master?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/test.yml:62: update your workflow using https://app.stepsecurity.io/secureworkflow/linw1995/data_extractor/test.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/test.yml:74: update your workflow using https://app.stepsecurity.io/secureworkflow/linw1995/data_extractor/test.yml/master?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/test.yml:76: update your workflow using https://app.stepsecurity.io/secureworkflow/linw1995/data_extractor/test.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/test.yml:80: update your workflow using https://app.stepsecurity.io/secureworkflow/linw1995/data_extractor/test.yml/master?enable=pin","Warn: third-party GitHubAction not pinned by hash: .github/workflows/test.yml:93: update your workflow using https://app.stepsecurity.io/secureworkflow/linw1995/data_extractor/test.yml/master?enable=pin","Warn: pipCommand not pinned by hash: .github/workflows/release.yml:28","Warn: pipCommand not pinned by hash: .github/workflows/test.yml:30","Warn: pipCommand not pinned by hash: .github/workflows/test.yml:56","Warn: pipCommand not pinned by hash: .github/workflows/test.yml:87","Info:   0 out of   8 GitHub-owned GitHubAction dependencies pinned","Info:   0 out of   8 third-party GitHubAction dependencies pinned","Info:   0 out of   4 pipCommand dependencies pinned"],"documentation":{"short":"Determines if the project has declared and pinned the dependencies of its build process.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#pinned-dependencies"}},{"name":"CII-Best-Practices","score":0,"reason":"no effort to earn an OpenSSF best practices badge detected","details":null,"documentation":{"short":"Determines if the project has an OpenSSF (formerly CII) Best Practices Badge.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#cii-best-practices"}},{"name":"Security-Policy","score":0,"reason":"security policy file not detected","details":["Warn: no security policy file detected","Warn: no security file to analyze","Warn: no security file to analyze","Warn: no security file to analyze"],"documentation":{"short":"Determines if the project has published a security policy.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#security-policy"}},{"name":"Fuzzing","score":0,"reason":"project is not fuzzed","details":["Warn: no fuzzer integrations found"],"documentation":{"short":"Determines if the project uses fuzzing.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#fuzzing"}},{"name":"License","score":10,"reason":"license file detected","details":["Info: project has a license file: LICENSE:0","Info: FSF or OSI recognized license: MIT License: LICENSE:0"],"documentation":{"short":"Determines if the project has defined a license.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#license"}},{"name":"Signed-Releases","score":0,"reason":"Project has not signed or included provenance with any releases.","details":["Warn: release artifact v1.0.1 not signed: https://api.github.com/repos/linw1995/data_extractor/releases/179667301","Warn: release artifact v1.0.0 not signed: https://api.github.com/repos/linw1995/data_extractor/releases/179632269","Warn: release artifact v0.10.2 not signed: https://api.github.com/repos/linw1995/data_extractor/releases/47988483","Warn: release artifact v1.0.0b2 not signed: https://api.github.com/repos/linw1995/data_extractor/releases/46731939","Warn: release artifact v1.0.0b1 not signed: https://api.github.com/repos/linw1995/data_extractor/releases/46650819","Warn: release artifact v1.0.1 does not have provenance: https://api.github.com/repos/linw1995/data_extractor/releases/179667301","Warn: release artifact v1.0.0 does not have provenance: https://api.github.com/repos/linw1995/data_extractor/releases/179632269","Warn: release artifact v0.10.2 does not have provenance: https://api.github.com/repos/linw1995/data_extractor/releases/47988483","Warn: release artifact v1.0.0b2 does not have provenance: https://api.github.com/repos/linw1995/data_extractor/releases/46731939","Warn: release artifact v1.0.0b1 does not have provenance: https://api.github.com/repos/linw1995/data_extractor/releases/46650819"],"documentation":{"short":"Determines if the project cryptographically signs release artifacts.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#signed-releases"}},{"name":"Branch-Protection","score":-1,"reason":"internal error: error during branchesHandler.setup: internal error: githubv4.Query: Resource not accessible by integration","details":null,"documentation":{"short":"Determines if the default and release branches are protected with GitHub's branch protection settings.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#branch-protection"}},{"name":"SAST","score":0,"reason":"SAST tool is not run on all commits -- score normalized to 0","details":["Warn: 0 commits out of 13 are checked with a SAST tool"],"documentation":{"short":"Determines if the project uses static code analysis.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#sast"}},{"name":"Vulnerabilities","score":6,"reason":"4 existing vulnerabilities detected","details":["Warn: Project is vulnerable to: GHSA-cpwx-vrp4-4pq7","Warn: Project is vulnerable to: GHSA-9hjg-9r4m-mvj7","Warn: Project is vulnerable to: GHSA-48p4-8xcf-vxj5","Warn: Project is vulnerable to: GHSA-pq67-6m6q-mj2v"],"documentation":{"short":"Determines if the project has open, known unfixed vulnerabilities.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#vulnerabilities"}}]},"last_synced_at":"2025-08-20T22:05:03.771Z","repository_id":45281906,"created_at":"2025-08-20T22:05:03.772Z","updated_at":"2025-08-20T22:05:03.772Z"},"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28911821,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-30T08:15:08.179Z","status":"ssl_error","status_checked_at":"2026-01-30T08:14:31.507Z","response_time":66,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 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":["css-selectors","data-extraction","data-extractor","jsonpath","xpath"],"created_at":"2026-01-30T11:36:31.867Z","updated_at":"2026-01-30T11:36:32.547Z","avatar_url":"https://github.com/linw1995.png","language":"Python","readme":"==============\nData Extractor\n==============\n\n|license| |Pypi Status| |Python version| |Package version| |PyPI - Downloads|\n|GitHub last commit| |Code style: black| |Build Status| |codecov|\n|Documentation Status| |PDM managed|\n\nCombine **XPath**, **CSS Selectors** and **JSONPath** for Web data extracting.\n\nQuickstarts\n\u003c\u003c\u003c\u003c\u003c\u003c\u003c\u003c\u003c\u003c\u003c\n\nInstallation\n~~~~~~~~~~~~\n\nInstall the stable version from PYPI.\n\n.. code-block:: shell\n\n    pip install \"data-extractor[jsonpath-extractor]\"  # for extracting JSON data\n    pip install \"data-extractor[lxml]\"  # for extracting HTML data\n\nOr install the latest version from Github.\n\n.. code-block:: shell\n\n    pip install \"data-extractor[jsonpath-extractor] @ git+https://github.com/linw1995/data_extractor.git@master\"\n\nExtract JSON data\n~~~~~~~~~~~~~~~~~\n\nCurrently supports to extract JSON data with below optional dependencies\n\n- jsonpath-extractor_\n- jsonpath-rw_\n- jsonpath-rw-ext_\n\n.. _jsonpath-extractor: https://github.com/linw1995/jsonpath\n.. _jsonpath-rw: https://github.com/kennknowles/python-jsonpath-rw\n.. _jsonpath-rw-ext: https://python-jsonpath-rw-ext.readthedocs.org/en/latest/\n\ninstall one dependency of them to extract JSON data.\n\nExtract HTML(XML) data\n~~~~~~~~~~~~~~~~~~~~~~\n\nCurrently supports to extract HTML(XML) data with below optional dependencies\n\n- lxml_ for using XPath_\n- cssselect_ for using CSS-Selectors_\n\n.. _lxml: https://lxml.de/\n.. _XPath: https://www.w3.org/TR/xpath-10/\n.. _cssselect: https://cssselect.readthedocs.io/en/latest/\n.. _CSS-Selectors: https://www.w3.org/TR/selectors-3/\n\nUsage\n~~~~~\n\n.. code-block:: python3\n\n    from data_extractor import Field, Item, JSONExtractor\n\n\n    class Count(Item):\n        followings = Field(JSONExtractor(\"countFollowings\"))\n        fans = Field(JSONExtractor(\"countFans\"))\n\n\n    class User(Item):\n        name_ = Field(JSONExtractor(\"name\"), name=\"name\")\n        age = Field(JSONExtractor(\"age\"), default=17)\n        count = Count()\n\n\n    assert User(JSONExtractor(\"data.users[*]\"), is_many=True).extract(\n        {\n            \"data\": {\n                \"users\": [\n                    {\n                        \"name\": \"john\",\n                        \"age\": 19,\n                        \"countFollowings\": 14,\n                        \"countFans\": 212,\n                    },\n                    {\n                        \"name\": \"jack\",\n                        \"description\": \"\",\n                        \"countFollowings\": 54,\n                        \"countFans\": 312,\n                    },\n                ]\n            }\n        }\n    ) == [\n        {\"name\": \"john\", \"age\": 19, \"count\": {\"followings\": 14, \"fans\": 212}},\n        {\"name\": \"jack\", \"age\": 17, \"count\": {\"followings\": 54, \"fans\": 312}},\n    ]\n\nChangelog\n\u003c\u003c\u003c\u003c\u003c\u003c\u003c\u003c\u003c\n\nv1.0.1\n~~~~~~\n\n**Build**\n\n- Supports Python 3.13\n\n\n\nContributing\n\u003c\u003c\u003c\u003c\u003c\u003c\u003c\u003c\u003c\u003c\u003c\u003c\n\n\nEnvironment Setup\n~~~~~~~~~~~~~~~~~\n\nClone the source codes from Github.\n\n.. code-block:: shell\n\n    git clone https://github.com/linw1995/data_extractor.git\n    cd data_extractor\n\nSetup the development environment.\nPlease make sure you install the pdm_,\npre-commit_ and nox_ CLIs in your environment.\n\n.. code-block:: shell\n\n    make init\n    make PYTHON=3.7 init  # for specific python version\n\nLinting\n~~~~~~~\n\nUse pre-commit_ for installing linters to ensure a good code style.\n\n.. code-block:: shell\n\n    make pre-commit\n\nRun linters. Some linters run via CLI nox_, so make sure you install it.\n\n.. code-block:: shell\n\n    make check-all\n\nTesting\n~~~~~~~\n\nRun quick tests.\n\n.. code-block:: shell\n\n    make\n\nRun quick tests with verbose.\n\n.. code-block:: shell\n\n    make vtest\n\nRun tests with coverage.\nTesting in multiple Python environments is powered by CLI nox_.\n\n.. code-block:: shell\n\n    make cov\n\n.. _pdm: https://github.com/pdm-project/pdm\n.. _pre-commit: https://pre-commit.com/\n.. _nox: https://nox.thea.codes/en/stable/\n\n.. |license| image:: https://img.shields.io/github/license/linw1995/data_extractor.svg\n    :target: https://github.com/linw1995/data_extractor/blob/master/LICENSE\n\n.. |Pypi Status| image:: https://img.shields.io/pypi/status/data_extractor.svg\n    :target: https://pypi.org/project/data_extractor\n\n.. |Python version| image:: https://img.shields.io/pypi/pyversions/data_extractor.svg\n    :target: https://pypi.org/project/data_extractor\n\n.. |Package version| image:: https://img.shields.io/pypi/v/data_extractor.svg\n    :target: https://pypi.org/project/data_extractor\n\n.. |PyPI - Downloads| image:: https://img.shields.io/pypi/dm/data-extractor.svg\n    :target: https://pypi.org/project/data_extractor\n\n.. |GitHub last commit| image:: https://img.shields.io/github/last-commit/linw1995/data_extractor.svg\n    :target: https://github.com/linw1995/data_extractor\n\n.. |Code style: black| image:: https://img.shields.io/badge/code%20style-black-000000.svg\n    :target: https://github.com/ambv/black\n\n.. |Build Status| image:: https://github.com/linw1995/data_extractor/workflows/Lint\u0026Test/badge.svg\n    :target: https://github.com/linw1995/data_extractor/actions?query=workflow%3ALint%26Test\n\n.. |codecov| image:: https://codecov.io/gh/linw1995/data_extractor/branch/master/graph/badge.svg\n    :target: https://codecov.io/gh/linw1995/data_extractor\n\n.. |Documentation Status| image:: https://readthedocs.org/projects/data-extractor/badge/?version=latest\n    :target: https://data-extractor.readthedocs.io/en/latest/?badge=latest\n\n.. |PDM managed| image:: https://img.shields.io/badge/pdm-managed-blueviolet\n    :target: https://pdm.fming.dev\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flinw1995%2Fdata_extractor","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flinw1995%2Fdata_extractor","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flinw1995%2Fdata_extractor/lists"}