├── .github └── workflows │ ├── ci-build.yml │ └── ci-release.yml ├── .gitignore ├── LICENSE ├── MANIFEST.in ├── Readme.md ├── config.json ├── example.py ├── grobid_client ├── __init__.py ├── client.py ├── format │ ├── TEI2LossyJSON.py │ ├── TEI2Markdown.py │ ├── __init__.py │ └── validate_json_refs.py └── grobid_client.py ├── pyproject.toml ├── pytest.ini ├── requirements.txt ├── resources ├── 20180928112135.png ├── 20180928112138.csv ├── test_pdf │ ├── 0046d83a-edd6-4631-b57c-755cdcce8b7f.pdf │ └── 0046d83a-edd6-4631-b57c-755cdcce8b7f.tei.xml └── test_txt │ ├── reference-strings-1.txt │ ├── reference-strings-2.txt │ ├── reference-strings-3.txt │ ├── reference-strings-4.txt │ ├── reference-strings-5.txt │ ├── reference-strings-6.txt │ └── reference-strings-7.txt └── tests ├── __init__.py ├── conftest.py ├── resources ├── 0046d83a-edd6-4631-b57c-755cdcce8b7f.tei.xml ├── __init__.py └── refs_offsets │ ├── 10.1038_s41477-023-01501-1.grobid.tei.xml │ ├── 10.1038_s41477-023-01501-1.json │ ├── 10.1038_s41586-023-05895-y.grobid.tei.xml │ ├── 10.1038_s41586-023-05895-y.json │ ├── 10.1038_s41598-023-32039-z.grobid.tei.xml │ ├── 10.1038_s41598-023-32039-z.json │ ├── 10.1371_journal.pone.0218311.grobid.tei.xml │ ├── 10.1371_journal.pone.0218311.json │ ├── 10.7554_elife.78558.grobid.tei.xml │ ├── 10.7554_elife.78558.json │ └── 2021.naacl-main.224.grobid.tei.xml ├── run_tests.py ├── test_client.py ├── test_config.json ├── test_conversions.py ├── test_grobid_client.py └── test_integration.py /.github/workflows/ci-build.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/.github/workflows/ci-build.yml -------------------------------------------------------------------------------- /.github/workflows/ci-release.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/.github/workflows/ci-release.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/LICENSE -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- 1 | include Readme.md -------------------------------------------------------------------------------- /Readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/Readme.md -------------------------------------------------------------------------------- /config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/config.json -------------------------------------------------------------------------------- /example.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/example.py -------------------------------------------------------------------------------- /grobid_client/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /grobid_client/client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/grobid_client/client.py -------------------------------------------------------------------------------- /grobid_client/format/TEI2LossyJSON.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/grobid_client/format/TEI2LossyJSON.py -------------------------------------------------------------------------------- /grobid_client/format/TEI2Markdown.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/grobid_client/format/TEI2Markdown.py -------------------------------------------------------------------------------- /grobid_client/format/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /grobid_client/format/validate_json_refs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/grobid_client/format/validate_json_refs.py -------------------------------------------------------------------------------- /grobid_client/grobid_client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/grobid_client/grobid_client.py -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/pyproject.toml -------------------------------------------------------------------------------- /pytest.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/pytest.ini -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | requests 2 | dateparser 3 | beautifulsoup4 4 | lxml -------------------------------------------------------------------------------- /resources/20180928112135.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/resources/20180928112135.png -------------------------------------------------------------------------------- /resources/20180928112138.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/resources/20180928112138.csv -------------------------------------------------------------------------------- /resources/test_pdf/0046d83a-edd6-4631-b57c-755cdcce8b7f.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/resources/test_pdf/0046d83a-edd6-4631-b57c-755cdcce8b7f.pdf -------------------------------------------------------------------------------- /resources/test_pdf/0046d83a-edd6-4631-b57c-755cdcce8b7f.tei.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/resources/test_pdf/0046d83a-edd6-4631-b57c-755cdcce8b7f.tei.xml -------------------------------------------------------------------------------- /resources/test_txt/reference-strings-1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/resources/test_txt/reference-strings-1.txt -------------------------------------------------------------------------------- /resources/test_txt/reference-strings-2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/resources/test_txt/reference-strings-2.txt -------------------------------------------------------------------------------- /resources/test_txt/reference-strings-3.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/resources/test_txt/reference-strings-3.txt -------------------------------------------------------------------------------- /resources/test_txt/reference-strings-4.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/resources/test_txt/reference-strings-4.txt -------------------------------------------------------------------------------- /resources/test_txt/reference-strings-5.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/resources/test_txt/reference-strings-5.txt -------------------------------------------------------------------------------- /resources/test_txt/reference-strings-6.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/resources/test_txt/reference-strings-6.txt -------------------------------------------------------------------------------- /resources/test_txt/reference-strings-7.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/resources/test_txt/reference-strings-7.txt -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- 1 | # Test package for grobid-client-python 2 | 3 | -------------------------------------------------------------------------------- /tests/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/conftest.py -------------------------------------------------------------------------------- /tests/resources/0046d83a-edd6-4631-b57c-755cdcce8b7f.tei.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/resources/0046d83a-edd6-4631-b57c-755cdcce8b7f.tei.xml -------------------------------------------------------------------------------- /tests/resources/__init__.py: -------------------------------------------------------------------------------- 1 | import os 2 | 3 | TEST_DATA_PATH = os.path.dirname(__file__) -------------------------------------------------------------------------------- /tests/resources/refs_offsets/10.1038_s41477-023-01501-1.grobid.tei.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/resources/refs_offsets/10.1038_s41477-023-01501-1.grobid.tei.xml -------------------------------------------------------------------------------- /tests/resources/refs_offsets/10.1038_s41477-023-01501-1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/resources/refs_offsets/10.1038_s41477-023-01501-1.json -------------------------------------------------------------------------------- /tests/resources/refs_offsets/10.1038_s41586-023-05895-y.grobid.tei.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/resources/refs_offsets/10.1038_s41586-023-05895-y.grobid.tei.xml -------------------------------------------------------------------------------- /tests/resources/refs_offsets/10.1038_s41586-023-05895-y.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/resources/refs_offsets/10.1038_s41586-023-05895-y.json -------------------------------------------------------------------------------- /tests/resources/refs_offsets/10.1038_s41598-023-32039-z.grobid.tei.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/resources/refs_offsets/10.1038_s41598-023-32039-z.grobid.tei.xml -------------------------------------------------------------------------------- /tests/resources/refs_offsets/10.1038_s41598-023-32039-z.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/resources/refs_offsets/10.1038_s41598-023-32039-z.json -------------------------------------------------------------------------------- /tests/resources/refs_offsets/10.1371_journal.pone.0218311.grobid.tei.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/resources/refs_offsets/10.1371_journal.pone.0218311.grobid.tei.xml -------------------------------------------------------------------------------- /tests/resources/refs_offsets/10.1371_journal.pone.0218311.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/resources/refs_offsets/10.1371_journal.pone.0218311.json -------------------------------------------------------------------------------- /tests/resources/refs_offsets/10.7554_elife.78558.grobid.tei.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/resources/refs_offsets/10.7554_elife.78558.grobid.tei.xml -------------------------------------------------------------------------------- /tests/resources/refs_offsets/10.7554_elife.78558.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/resources/refs_offsets/10.7554_elife.78558.json -------------------------------------------------------------------------------- /tests/resources/refs_offsets/2021.naacl-main.224.grobid.tei.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/resources/refs_offsets/2021.naacl-main.224.grobid.tei.xml -------------------------------------------------------------------------------- /tests/run_tests.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/run_tests.py -------------------------------------------------------------------------------- /tests/test_client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/test_client.py -------------------------------------------------------------------------------- /tests/test_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/test_config.json -------------------------------------------------------------------------------- /tests/test_conversions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/test_conversions.py -------------------------------------------------------------------------------- /tests/test_grobid_client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/test_grobid_client.py -------------------------------------------------------------------------------- /tests/test_integration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kermitt2/grobid-client-python/HEAD/tests/test_integration.py --------------------------------------------------------------------------------