paper-search-cli 1.0.2__tar.gz

paper_search_cli-1.0.2/.env.example

@@ -0,0 +1,21 @@
+# paper-search-cli environment configuration
+# Copy this file to .env and fill in the values you need.
+# Preferred format: PAPER_SEARCH_<NAME>
+# Legacy format PAPER_SEARCH_MCP_<NAME> is also supported.
+
+# Core optional keys/tokens
+PAPER_SEARCH_SEMANTIC_SCHOLAR_API_KEY=
+PAPER_SEARCH_CORE_API_KEY=
+PAPER_SEARCH_UNPAYWALL_EMAIL=
+PAPER_SEARCH_DOAJ_API_KEY=
+PAPER_SEARCH_ZENODO_ACCESS_TOKEN=
+PAPER_SEARCH_GOOGLE_SCHOLAR_PROXY_URL=
+
+# Optional provider-specific keys
+PAPER_SEARCH_OPENAIRE_API_KEY=
+PAPER_SEARCH_CITESEERX_API_KEY=
+PAPER_SEARCH_IEEE_API_KEY=
+PAPER_SEARCH_ACM_API_KEY=
+
+# Optional: override env file path if needed
+# PAPER_SEARCH_ENV_FILE=/absolute/path/to/.env

paper_search_cli-1.0.2/.github/workflows/publish.yml

@@ -0,0 +1,180 @@
+name: Auto Publish
+
+on:
+  push:
+    branches: [main]
+    paths-ignore:
+      - '*.md'
+      - 'LICENSE'
+      - '.gitignore'
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.10', '3.12', '3.13']
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - uses: astral-sh/setup-uv@v4
+
+      - name: Install dependencies
+        run: |
+          uv pip install --system -e ".[dev]" 2>/dev/null || uv pip install --system -e .
+          uv pip install --system pytest
+
+      - name: Run tests
+        run: python -m pytest tests/ -x -q --tb=short
+
+  bump-and-publish:
+    needs: test
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      contents: write
+      id-token: write
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+
+      - uses: astral-sh/setup-uv@v4
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+          registry-url: 'https://registry.npmjs.org'
+
+      # --- Auto bump version ---
+      - name: Bump version
+        id: bump
+        run: |
+          # Read current version from pyproject.toml
+          CURRENT=$(grep '^version' pyproject.toml | head -1 | sed 's/.*"\(.*\)".*/\1/')
+          echo "Current version: $CURRENT"
+
+          # Bump patch version
+          IFS='.' read -r MAJOR MINOR PATCH <<< "$CURRENT"
+          NEW_PATCH=$((PATCH + 1))
+          NEW_VERSION="${MAJOR}.${MINOR}.${NEW_PATCH}"
+          echo "New version: $NEW_VERSION"
+
+          # Update pyproject.toml
+          sed -i "s/^version = \"$CURRENT\"/version = \"$NEW_VERSION\"/" pyproject.toml
+
+          # Update version in cli.py
+          sed -i "s/%(prog)s $CURRENT/%(prog)s $NEW_VERSION/" paper_search/cli.py 2>/dev/null || true
+
+          echo "version=$NEW_VERSION" >> "$GITHUB_OUTPUT"
+
+      - name: Commit version bump
+        run: |
+          git config user.name "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+          git add pyproject.toml paper_search/cli.py
+          git diff --cached --quiet || git commit -m "chore: bump version to ${{ steps.bump.outputs.version }}"
+          git tag "v${{ steps.bump.outputs.version }}"
+          git push && git push --tags
+
+      # --- Publish to PyPI ---
+      - name: Build Python package
+        run: uv build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+      # --- Publish to npm ---
+      - name: Prepare npm package
+        run: |
+          VERSION="${{ steps.bump.outputs.version }}"
+          mkdir -p npm-pkg/bin
+
+          # Create the npm wrapper script
+          cat > npm-pkg/bin/paper-search <<'SCRIPT'
+          #!/usr/bin/env node
+          const { execFileSync } = require("child_process");
+          const args = process.argv.slice(2);
+
+          // Try system-installed paper-search first, then fall back to uvx
+          try {
+            execFileSync("paper-search", args, { stdio: "inherit" });
+          } catch {
+            try {
+              execFileSync("uvx", ["paper-search-cli", ...args], { stdio: "inherit" });
+            } catch {
+              console.error(
+                "paper-search-cli is not installed.\n" +
+                "Install with: pip install paper-search-cli  OR  uv tool install paper-search-cli"
+              );
+              process.exit(1);
+            }
+          }
+          SCRIPT
+          chmod +x npm-pkg/bin/paper-search
+
+          # Create package.json
+          cat > npm-pkg/package.json <<EOF
+          {
+            "name": "paper-search-cli",
+            "version": "$VERSION",
+            "description": "CLI tool for searching and downloading academic papers from 20+ sources",
+            "bin": { "paper-search": "bin/paper-search" },
+            "keywords": ["academic", "papers", "search", "arxiv", "cli", "claude-skill"],
+            "license": "MIT",
+            "repository": {
+              "type": "git",
+              "url": "https://github.com/openags/paper-search-cli"
+            },
+            "author": "P.S Zhang <pengsongzhang96@gmail.com>"
+          }
+          EOF
+
+          # Create README for npm
+          cat > npm-pkg/README.md <<'EOF'
+          # paper-search-cli
+
+          CLI tool for searching and downloading academic papers from 20+ sources.
+
+          ## Usage via npx
+
+          ```bash
+          npx paper-search-cli search "transformer architecture"
+          npx paper-search-cli sources
+          ```
+
+          ## Prerequisite
+
+          Requires Python 3.10+ with `paper-search-cli` installed:
+
+          ```bash
+          pip install paper-search-cli
+          # or
+          uv tool install paper-search-cli
+          ```
+
+          See https://github.com/openags/paper-search-cli for full documentation.
+          EOF
+
+      - name: Publish to npm
+        working-directory: npm-pkg
+        run: npm publish --access public
+        env:
+          NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
+
+      # --- GitHub Release ---
+      - name: Create GitHub Release
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: "v${{ steps.bump.outputs.version }}"
+          generate_release_notes: true
+          files: dist/*

paper_search_cli-1.0.2/.gitignore

@@ -0,0 +1,175 @@
+.DS_Store
+scratch/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+!.env.example
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# vscode
+.vscode/
+**/CLAUDE.local.md
+
+./downloads
+./test_downloads
+downloads/
+test_downloads/

paper_search_cli-1.0.2/Dockerfile

@@ -0,0 +1,26 @@
+FROM python:3.12-slim AS builder
+
+WORKDIR /app
+COPY pyproject.toml README.md LICENSE ./
+COPY paper_search/ paper_search/
+
+RUN pip install --no-cache-dir build \
+    && python -m build --wheel \
+    && pip install --no-cache-dir dist/*.whl
+
+FROM python:3.12-slim
+
+WORKDIR /app
+COPY --from=builder /usr/local/lib/python3.12/site-packages /usr/local/lib/python3.12/site-packages
+COPY --from=builder /usr/local/bin/paper-search /usr/local/bin/paper-search
+
+ENV PAPER_SEARCH_UNPAYWALL_EMAIL=""
+ENV PAPER_SEARCH_CORE_API_KEY=""
+ENV PAPER_SEARCH_SEMANTIC_SCHOLAR_API_KEY=""
+ENV PAPER_SEARCH_ZENODO_ACCESS_TOKEN=""
+ENV PAPER_SEARCH_DOAJ_API_KEY=""
+ENV PAPER_SEARCH_GOOGLE_SCHOLAR_PROXY_URL=""
+ENV PAPER_SEARCH_IEEE_API_KEY=""
+ENV PAPER_SEARCH_ACM_API_KEY=""
+
+ENTRYPOINT ["paper-search"]

paper_search_cli-1.0.2/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 OPENAGS
+
+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.

paper_search_cli-1.0.2/PKG-INFO

@@ -0,0 +1,191 @@
+Metadata-Version: 2.4
+Name: paper-search-cli
+Version: 1.0.2
+Summary: CLI tool for searching and downloading academic papers from 20+ sources.
+Project-URL: Homepage, https://github.com/openags/paper-search-cli
+Project-URL: Repository, https://github.com/openags/paper-search-cli
+Project-URL: Issues, https://github.com/openags/paper-search-cli/issues
+Author-email: "P.S Zhang" <pengsongzhang96@gmail.com>
+License-Expression: MIT
+License-File: LICENSE
+Keywords: academic,arxiv,claude-skill,cli,papers,pubmed,search,semantic-scholar
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3.10
+Requires-Dist: beautifulsoup4>=4.12.0
+Requires-Dist: feedparser
+Requires-Dist: httpx[socks]>=0.28.1
+Requires-Dist: lxml>=4.9.0
+Requires-Dist: pypdf2>=3.0.0
+Requires-Dist: requests
+Description-Content-Type: text/markdown
+
+# paper-search-cli
+
+A CLI tool for searching and downloading academic papers from 20+ sources. Also works as a **Claude Code Skill** for AI-assisted research.
+
+## Features
+
+- **20+ academic sources**: arXiv, PubMed, Semantic Scholar, CrossRef, OpenAlex, CORE, bioRxiv, medRxiv, and more
+- **Concurrent search**: searches multiple sources in parallel with automatic deduplication
+- **Smart download**: multi-stage fallback chain (source -> OA repositories -> Unpaywall -> Sci-Hub)
+- **PDF text extraction**: download and extract text from papers in one step
+- **JSON output**: machine-readable output for scripting and AI integration
+- **Claude Code Skill**: use as a slash command in Claude Code
+
+## Installation
+
+### pip
+
+```bash
+pip install paper-search-cli
+```
+
+### uv
+
+```bash
+uv tool install paper-search-cli
+```
+
+### From source
+
+```bash
+git clone https://github.com/openags/paper-search-cli.git
+cd paper-search-cli
+uv sync
+```
+
+### Docker
+
+```bash
+docker build -t paper-search .
+docker run paper-search search "transformer architecture"
+```
+
+## Usage
+
+### Search papers
+
+```bash
+# Search all sources
+paper-search search "transformer architecture"
+
+# Search specific sources
+paper-search search "quantum computing" --sources arxiv,semantic --max-results 5
+
+# Filter by year (Semantic Scholar)
+paper-search search "large language models" --sources semantic --year 2023-2024
+
+# JSON output (for scripting / AI tools)
+paper-search search "CRISPR" --json
+```
+
+### Download a paper
+
+```bash
+paper-search download 2106.12345 --source arxiv
+paper-search download 2106.12345 --source arxiv --output-dir ./papers
+```
+
+### Download with fallback chain
+
+```bash
+paper-search download-fallback 2106.12345 --source arxiv \
+  --doi 10.48550/arXiv.2106.12345 --title "Paper Title"
+```
+
+### Read (download + extract text)
+
+```bash
+paper-search read 2106.12345 --source arxiv
+```
+
+### List available sources
+
+```bash
+paper-search sources
+```
+
+## Claude Code Skill
+
+This tool can be used as a [Claude Code Skill](https://docs.anthropic.com/en/docs/claude-code/skills) for AI-assisted academic research.
+
+### Setup
+
+Copy the skill file to your project:
+
+```bash
+mkdir -p .claude/commands
+cp claude-skill/paper-search.md .claude/commands/paper-search.md
+```
+
+Or for global access (all projects):
+
+```bash
+mkdir -p ~/.claude/commands
+cp claude-skill/paper-search.md ~/.claude/commands/paper-search.md
+```
+
+Then in Claude Code, use:
+
+```
+/paper-search transformer architecture in NLP
+```
+
+## Available Sources
+
+| Source | Search | Download | Read | Notes |
+|--------|--------|----------|------|-------|
+| arXiv | yes | yes | yes | Open API, reliable |
+| PubMed | yes | no | no | Metadata only |
+| bioRxiv | yes | yes | yes | Category-based search |
+| medRxiv | yes | yes | yes | Category-based search |
+| Google Scholar | limited | no | no | Bot-detection active |
+| IACR | yes | yes | yes | Cryptography focus |
+| Semantic Scholar | yes | OA | OA | Year filter support |
+| CrossRef | yes | no | no | DOI metadata |
+| OpenAlex | yes | no | no | Broad metadata |
+| PMC | yes | OA | OA | Open access only |
+| CORE | yes | yes | yes | API key recommended |
+| Europe PMC | yes | OA | OA | Open access only |
+| dblp | yes | no | no | CS bibliography |
+| OpenAIRE | yes | no | no | EU research |
+| CiteSeerX | limited | yes | limited | Intermittent |
+| DOAJ | yes | limited | limited | Open access journals |
+| BASE | limited | yes | yes | OAI-PMH based |
+| Zenodo | yes | yes | yes | Record-dependent |
+| HAL | yes | yes | yes | French archives |
+| SSRN | limited | limited | limited | Metadata only |
+| Unpaywall | DOI | no | no | DOI lookup only |
+| Sci-Hub | limited | yes | no | Optional fallback |
+| IEEE | key | key | key | Requires API key |
+| ACM | key | key | key | Requires API key |
+
+## Environment Variables
+
+All environment variables are optional. Set them in a `.env` file or export them.
+
+| Variable | Purpose |
+|----------|---------|
+| `PAPER_SEARCH_UNPAYWALL_EMAIL` | Required for Unpaywall DOI resolution |
+| `PAPER_SEARCH_CORE_API_KEY` | Better rate limits for CORE |
+| `PAPER_SEARCH_SEMANTIC_SCHOLAR_API_KEY` | Better rate limits for Semantic Scholar |
+| `PAPER_SEARCH_ZENODO_ACCESS_TOKEN` | Access embargoed Zenodo records |
+| `PAPER_SEARCH_DOAJ_API_KEY` | Higher rate limits for DOAJ |
+| `PAPER_SEARCH_GOOGLE_SCHOLAR_PROXY_URL` | Proxy for Google Scholar |
+| `PAPER_SEARCH_IEEE_API_KEY` | Enable IEEE Xplore |
+| `PAPER_SEARCH_ACM_API_KEY` | Enable ACM Digital Library |
+
+Legacy `PAPER_SEARCH_MCP_*` prefix is also supported for backward compatibility.
+
+## License
+
+MIT