Metadata-Version: 2.4
Name: boltpy
Version: 0.1.4
Summary: BOLT: Bibliographic Orchestration for Literature Triage
License: MIT License
        
        Copyright (c) 2025 filcivilini
        
        Permission is hereby granted, free of charge, to any person obtaining a copy
        of this software and associated documentation files (the "Software"), to deal
        in the Software without restriction, including without limitation the rights
        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
        copies of the Software, and to permit persons to whom the Software is
        furnished to do so, subject to the following conditions:
        
        The above copyright notice and this permission notice shall be included in all
        copies or substantial portions of the Software.
        
        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
        SOFTWARE.
License-File: LICENSE
Keywords: bibliography,literature-review,metadata,research,scraping,systematic-review
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Classifier: Topic :: Text Processing :: General
Requires-Python: >=3.10
Requires-Dist: feedparser>=6.0
Requires-Dist: pandas>=2.0
Requires-Dist: rapidfuzz>=3.0
Requires-Dist: requests>=2.31
Provides-Extra: dev
Requires-Dist: build>=1.2; extra == 'dev'
Requires-Dist: mypy>=1.10; extra == 'dev'
Requires-Dist: pytest>=8; extra == 'dev'
Requires-Dist: ruff>=0.6; extra == 'dev'
Requires-Dist: twine>=5.1; extra == 'dev'
Description-Content-Type: text/markdown

# boltpy (BOLT)

**BOLT** = **B**ibliographic **O**rchestration for **L**iterature **T**riage

`boltpy` is a Python toolkit to collect and triage literature results from multiple scholarly sources
(Crossref, OpenAlex, PubMed, arXiv, Europe PMC, Zenodo, and optionally Elsevier Scopus).

It is designed for literature reviews where you want to:
- choose a set of keywords,
- choose which APIs/sources to query,
- provide API keys when required,
- set a maximum number of results per source,
- receive a clean, deduplicated dataset (plus an ASReview-friendly export).

---

## Features

- Multi-source harvesting (select the APIs you want)
- Per-source ceilings (`ceilings={"crossref": 150, "openalex": 200, ...}`)
- Optional API key support # currently only Elsevier Scopus is supported
- Deduplication:
  - DOI-based
  - exact normalized title
  - fuzzy title matching
- Export:
  - full CSV (all fields)
  - ASReview CSV (title/abstract/authors/year/doi/url)
  - PRISMA-style counters (JSON)

---

## Install

pip install boltpy


## Example

from boltpy.core import HarvestConfig, harvest

cfg = HarvestConfig(
    keywords=["your keyword 1", "your keyword 2"],
    apis=["crossref", "openalex", "pubmed", "arxiv", "europe_pmc", "zenodo"],
    default_ceiling=100,
    output_dir="outputs",          # optional: exports CSV + JSON
    export_prefix="boltpy_demo",
)

res = harvest(cfg)

# Full dataset (all fields)
print(res.full.head())

# PRISMA-like counters
print(res.prisma)

# Written files (if output_dir is set)
print(res.output_paths)
