├── .gitignore ├── LICENSE ├── README.md ├── README_zh.md ├── docker └── Dockerfile ├── pdf_parser ├── .gitignore ├── __init__.py ├── __main__.py ├── backends │ ├── __init__.py │ ├── base.py │ ├── cermine.py │ ├── grobid.py │ ├── pdffigures.py │ ├── pdffigures2.py │ └── scienceparse.py ├── bin │ └── pdffigures ├── jar │ ├── cermine-1.13.jar │ └── pdffigures2-0.1.0.jar └── parser.py ├── requirements.txt └── setup.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/README.md -------------------------------------------------------------------------------- /README_zh.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/README_zh.md -------------------------------------------------------------------------------- /docker/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/docker/Dockerfile -------------------------------------------------------------------------------- /pdf_parser/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/pdf_parser/.gitignore -------------------------------------------------------------------------------- /pdf_parser/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/pdf_parser/__init__.py -------------------------------------------------------------------------------- /pdf_parser/__main__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/pdf_parser/__main__.py -------------------------------------------------------------------------------- /pdf_parser/backends/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/pdf_parser/backends/__init__.py -------------------------------------------------------------------------------- /pdf_parser/backends/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/pdf_parser/backends/base.py -------------------------------------------------------------------------------- /pdf_parser/backends/cermine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/pdf_parser/backends/cermine.py -------------------------------------------------------------------------------- /pdf_parser/backends/grobid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/pdf_parser/backends/grobid.py -------------------------------------------------------------------------------- /pdf_parser/backends/pdffigures.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/pdf_parser/backends/pdffigures.py -------------------------------------------------------------------------------- /pdf_parser/backends/pdffigures2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/pdf_parser/backends/pdffigures2.py -------------------------------------------------------------------------------- /pdf_parser/backends/scienceparse.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/pdf_parser/backends/scienceparse.py -------------------------------------------------------------------------------- /pdf_parser/bin/pdffigures: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/pdf_parser/bin/pdffigures -------------------------------------------------------------------------------- /pdf_parser/jar/cermine-1.13.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/pdf_parser/jar/cermine-1.13.jar -------------------------------------------------------------------------------- /pdf_parser/jar/pdffigures2-0.1.0.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/pdf_parser/jar/pdffigures2-0.1.0.jar -------------------------------------------------------------------------------- /pdf_parser/parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/pdf_parser/parser.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | setuptools==46.1.3 2 | requests==2.23.0 3 | science-parse-api==1.0.1 -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Acemap/pdf_parser/HEAD/setup.py --------------------------------------------------------------------------------