resumeminer 0.1.0__tar.gz

resumeminer-0.1.0/.gitignore

@@ -0,0 +1,8 @@
+.venv/
+__pycache__/
+*.py[cod]
+*.egg-info/
+dist/
+build/
+.pytest_cache/
+*.egg

resumeminer-0.1.0/CHANGELOG.md

@@ -0,0 +1,20 @@
+# Changelog
+
+All notable changes to this project are documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [0.1.0] - 2026-06-18
+
+### Added
+
+- PDF text extraction for resume files using `pypdf`
+- Email and phone number extraction
+- LinkedIn, GitHub, and portfolio URL extraction
+- Configurable skill matching with a bundled default skills list
+- `ResumeParser` class and `parse_resume()` convenience function
+- CLI: `resumeminer parse <file>` with human-readable and `--json` output
+- Python 3.9+ support
+
+[0.1.0]: https://github.com/alixaprodev/resumeminer/releases/tag/v0.1.0

resumeminer-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 H. Ali
+
+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.

resumeminer-0.1.0/PKG-INFO

@@ -0,0 +1,178 @@
+Metadata-Version: 2.4
+Name: resumeminer
+Version: 0.1.0
+Summary: A lightweight Python library for extracting structured information from PDF resumes
+Project-URL: Homepage, https://github.com/alixaprodev/resumeminer
+Project-URL: Repository, https://github.com/alixaprodev/resumeminer
+Project-URL: Issues, https://github.com/alixaprodev/resumeminer/issues
+Project-URL: Documentation, https://github.com/alixaprodev/resumeminer#readme
+Author-email: "H. Ali" <haxratali0@gmail.com>
+License-Expression: MIT
+License-File: LICENSE
+Keywords: cv,parser,pdf,recruitment,resume
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+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 :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing
+Requires-Python: >=3.9
+Requires-Dist: pypdf<6,>=4.0
+Provides-Extra: dev
+Requires-Dist: build>=1.0; extra == 'dev'
+Requires-Dist: pytest>=7.0; extra == 'dev'
+Requires-Dist: twine>=5.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# ResumeMiner
+
+A lightweight Python library for extracting structured information from PDF resumes.
+
+## Features
+
+- PDF text extraction via `pypdf`
+- Email and phone number extraction
+- LinkedIn, GitHub, and portfolio URL extraction
+- Configurable skill matching against a bundled default list
+- Simple API and command-line interface
+- Structured dictionary output with raw extracted text
+
+## Installation
+
+```bash
+pip install resumeminer
+```
+
+Requires Python 3.9 or newer.
+
+### Development
+
+```bash
+git clone https://github.com/alixaprodev/resumeminer.git
+cd resumeminer
+pip install -e ".[dev]"
+```
+
+## Quick Start
+
+```python
+from resumeminer import ResumeParser
+
+parser = ResumeParser("resume.pdf")
+result = parser.parse()
+
+print(result["email"])
+print(result["skills"])
+```
+
+```python
+from resumeminer import parse_resume
+
+result = parse_resume("resume.pdf")
+print(result)
+```
+
+Optional custom skills list:
+
+```python
+parser = ResumeParser("resume.pdf", skills=["Python", "Rust", "Go"])
+result = parser.parse()
+```
+
+## CLI Usage
+
+Parse a resume:
+
+```bash
+resumeminer parse resume.pdf
+```
+
+Human-readable output (default):
+
+```text
+Email:     jane.developer@example.com
+Phone:     +1 (555) 123-4567
+LinkedIn:  https://linkedin.com/in/jane-developer
+GitHub:    https://github.com/janedev
+Portfolio: https://janedeveloper.dev
+Skills:    Python, Django, React, Docker, AWS
+```
+
+Full JSON output (includes `raw_text`):
+
+```bash
+resumeminer parse resume.pdf --json
+```
+
+Print version:
+
+```bash
+resumeminer --version
+```
+
+## Output Example
+
+```python
+{
+    "email": "jane.developer@example.com",
+    "phone": "+1 (555) 123-4567",
+    "links": {
+        "linkedin": "https://linkedin.com/in/jane-developer",
+        "github": "https://github.com/janedev",
+        "portfolio": "https://janedeveloper.dev"
+    },
+    "skills": ["Python", "Django", "React", "Docker", "AWS"],
+    "raw_text": "..."
+}
+```
+
+## Supported Files
+
+- PDF resumes with extractable text
+
+Scanned or image-only PDFs are not supported in v0.1.0.
+
+## Limitations
+
+- Extraction quality depends on PDF structure and formatting
+- Regex-based parsing may miss or misread fields on unusual layouts
+- Skill detection uses a fixed default list unless a custom list is provided
+- Phone and portfolio URL extraction may return imperfect matches on some resumes
+
+## Roadmap
+
+- OCR support for scanned resumes
+- DOCX and TXT file support
+- Name, education, and experience extraction
+- Section-based parsing
+- Custom skill dictionary file path
+- JSON schema output
+- Batch parsing CLI
+
+## Contributing
+
+Contributions are welcome.
+
+1. Fork [github.com/alixaprodev/resumeminer](https://github.com/alixaprodev/resumeminer)
+2. Create a feature branch
+3. Add tests for behavior changes
+4. Run `pytest`
+5. Open a pull request
+
+Report issues on [GitHub Issues](https://github.com/alixaprodev/resumeminer/issues).
+
+## License
+
+MIT License. See [LICENSE](LICENSE).
+
+## Author
+
+**H. Ali**
+
+- GitHub: [github.com/alixaprodev](https://github.com/alixaprodev)
+- Email: [haxratali0@gmail.com](mailto:haxratali0@gmail.com)

resumeminer-0.1.0/README.md

@@ -0,0 +1,147 @@
+# ResumeMiner
+
+A lightweight Python library for extracting structured information from PDF resumes.
+
+## Features
+
+- PDF text extraction via `pypdf`
+- Email and phone number extraction
+- LinkedIn, GitHub, and portfolio URL extraction
+- Configurable skill matching against a bundled default list
+- Simple API and command-line interface
+- Structured dictionary output with raw extracted text
+
+## Installation
+
+```bash
+pip install resumeminer
+```
+
+Requires Python 3.9 or newer.
+
+### Development
+
+```bash
+git clone https://github.com/alixaprodev/resumeminer.git
+cd resumeminer
+pip install -e ".[dev]"
+```
+
+## Quick Start
+
+```python
+from resumeminer import ResumeParser
+
+parser = ResumeParser("resume.pdf")
+result = parser.parse()
+
+print(result["email"])
+print(result["skills"])
+```
+
+```python
+from resumeminer import parse_resume
+
+result = parse_resume("resume.pdf")
+print(result)
+```
+
+Optional custom skills list:
+
+```python
+parser = ResumeParser("resume.pdf", skills=["Python", "Rust", "Go"])
+result = parser.parse()
+```
+
+## CLI Usage
+
+Parse a resume:
+
+```bash
+resumeminer parse resume.pdf
+```
+
+Human-readable output (default):
+
+```text
+Email:     jane.developer@example.com
+Phone:     +1 (555) 123-4567
+LinkedIn:  https://linkedin.com/in/jane-developer
+GitHub:    https://github.com/janedev
+Portfolio: https://janedeveloper.dev
+Skills:    Python, Django, React, Docker, AWS
+```
+
+Full JSON output (includes `raw_text`):
+
+```bash
+resumeminer parse resume.pdf --json
+```
+
+Print version:
+
+```bash
+resumeminer --version
+```
+
+## Output Example
+
+```python
+{
+    "email": "jane.developer@example.com",
+    "phone": "+1 (555) 123-4567",
+    "links": {
+        "linkedin": "https://linkedin.com/in/jane-developer",
+        "github": "https://github.com/janedev",
+        "portfolio": "https://janedeveloper.dev"
+    },
+    "skills": ["Python", "Django", "React", "Docker", "AWS"],
+    "raw_text": "..."
+}
+```
+
+## Supported Files
+
+- PDF resumes with extractable text
+
+Scanned or image-only PDFs are not supported in v0.1.0.
+
+## Limitations
+
+- Extraction quality depends on PDF structure and formatting
+- Regex-based parsing may miss or misread fields on unusual layouts
+- Skill detection uses a fixed default list unless a custom list is provided
+- Phone and portfolio URL extraction may return imperfect matches on some resumes
+
+## Roadmap
+
+- OCR support for scanned resumes
+- DOCX and TXT file support
+- Name, education, and experience extraction
+- Section-based parsing
+- Custom skill dictionary file path
+- JSON schema output
+- Batch parsing CLI
+
+## Contributing
+
+Contributions are welcome.
+
+1. Fork [github.com/alixaprodev/resumeminer](https://github.com/alixaprodev/resumeminer)
+2. Create a feature branch
+3. Add tests for behavior changes
+4. Run `pytest`
+5. Open a pull request
+
+Report issues on [GitHub Issues](https://github.com/alixaprodev/resumeminer/issues).
+
+## License
+
+MIT License. See [LICENSE](LICENSE).
+
+## Author
+
+**H. Ali**
+
+- GitHub: [github.com/alixaprodev](https://github.com/alixaprodev)
+- Email: [haxratali0@gmail.com](mailto:haxratali0@gmail.com)

resumeminer-0.1.0/pyproject.toml

@@ -0,0 +1,63 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "resumeminer"
+version = "0.1.0"
+description = "A lightweight Python library for extracting structured information from PDF resumes"
+readme = "README.md"
+license = "MIT"
+license-files = ["LICENSE"]
+requires-python = ">=3.9"
+authors = [
+    { name = "H. Ali", email = "haxratali0@gmail.com" },
+]
+keywords = ["resume", "parser", "pdf", "cv", "recruitment"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Text Processing",
+]
+dependencies = [
+    "pypdf>=4.0,<6",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0",
+    "build>=1.0",
+    "twine>=5.0",
+]
+
+[project.scripts]
+resumeminer = "resumeminer.cli:main"
+
+[project.urls]
+Homepage = "https://github.com/alixaprodev/resumeminer"
+Repository = "https://github.com/alixaprodev/resumeminer"
+Issues = "https://github.com/alixaprodev/resumeminer/issues"
+Documentation = "https://github.com/alixaprodev/resumeminer#readme"
+
+[tool.hatch.build.targets.wheel]
+packages = ["resumeminer"]
+
+[tool.hatch.build.targets.sdist]
+include = [
+    "/resumeminer",
+    "/tests",
+    "/README.md",
+    "/LICENSE",
+    "/CHANGELOG.md",
+]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

resumeminer-0.1.0/resumeminer/__init__.py

@@ -0,0 +1,6 @@
+"""A lightweight Python library for extracting structured information from PDF resumes."""
+
+from resumeminer.parser import ResumeParser, parse_resume
+
+__all__ = ["ResumeParser", "parse_resume", "__version__"]
+__version__ = "0.1.0"

resumeminer-0.1.0/resumeminer/cli.py

@@ -0,0 +1,87 @@
+"""Command-line interface for ResumeMiner."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import sys
+from pathlib import Path
+from typing import Any
+
+from resumeminer import __version__
+from resumeminer.extractors.pdf import PDFExtractionError
+from resumeminer.parser import parse_resume
+
+ParseResult = dict[str, Any]
+
+
+def build_parser() -> argparse.ArgumentParser:
+    """Build the CLI argument parser."""
+    parser = argparse.ArgumentParser(
+        prog="resumeminer",
+        description="A lightweight Python library for extracting structured information from PDF resumes.",
+    )
+    parser.add_argument(
+        "--version",
+        action="version",
+        version=f"resumeminer {__version__}",
+    )
+
+    subparsers = parser.add_subparsers(dest="command", required=True)
+
+    parse_cmd = subparsers.add_parser("parse", help="Parse a PDF resume")
+    parse_cmd.add_argument("file", type=Path, help="Path to the PDF resume")
+    parse_cmd.add_argument(
+        "--json",
+        action="store_true",
+        help="Print full structured output as JSON (includes raw_text)",
+    )
+
+    return parser
+
+
+def format_result(result: ParseResult) -> str:
+    """Format parse result as human-readable text."""
+    skills = ", ".join(result["skills"]) if result["skills"] else "—"
+    lines = [
+        f"Email:     {result['email'] or '—'}",
+        f"Phone:     {result['phone'] or '—'}",
+        f"LinkedIn:  {result['links']['linkedin'] or '—'}",
+        f"GitHub:    {result['links']['github'] or '—'}",
+        f"Portfolio: {result['links']['portfolio'] or '—'}",
+        f"Skills:    {skills}",
+    ]
+    return "\n".join(lines)
+
+
+def main(argv: list[str] | None = None) -> int:
+    """Entry point for the resumeminer CLI."""
+    parser = build_parser()
+    args = parser.parse_args(argv)
+
+    if args.command == "parse":
+        if not args.file.exists():
+            print(f"Error: file not found: {args.file}", file=sys.stderr)
+            return 1
+
+        try:
+            result = parse_resume(args.file)
+        except PDFExtractionError as exc:
+            print(f"Error: {exc}", file=sys.stderr)
+            return 1
+        except FileNotFoundError as exc:
+            print(f"Error: {exc}", file=sys.stderr)
+            return 1
+
+        if args.json:
+            print(json.dumps(result, indent=2))
+        else:
+            print(format_result(result))
+
+        return 0
+
+    return 1
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

resumeminer-0.1.0/resumeminer/data/skills.txt

@@ -0,0 +1,16 @@
+Python
+Django
+Flask
+FastAPI
+JavaScript
+TypeScript
+React
+Node.js
+PostgreSQL
+MySQL
+MongoDB
+Docker
+Kubernetes
+AWS
+Git
+Linux

resumeminer-0.1.0/resumeminer/extractors/__init__.py

@@ -0,0 +1,5 @@
+"""Text extraction from resume files."""
+
+from resumeminer.extractors.pdf import PDFExtractor, extract_text_from_pdf
+
+__all__ = ["PDFExtractor", "extract_text_from_pdf"]

resumeminer-0.1.0/resumeminer/extractors/pdf.py

@@ -0,0 +1,75 @@
+"""PDF text extraction using pypdf."""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Union
+
+from pypdf import PdfReader
+from pypdf.errors import PdfReadError
+
+PathLike = Union[str, Path]
+
+
+class PDFExtractionError(Exception):
+    """Raised when PDF text extraction fails."""
+
+
+def _normalize_text(text: str) -> str:
+    """Collapse excessive whitespace while preserving line breaks."""
+    lines = [line.strip() for line in text.splitlines()]
+    cleaned = "\n".join(line for line in lines if line)
+    return cleaned.strip()
+
+
+def extract_text_from_pdf(file_path: PathLike) -> str:
+    """Extract text from all pages of a PDF file.
+
+    Args:
+        file_path: Path to the PDF file.
+
+    Returns:
+        Extracted and cleaned text, or an empty string if no text is found.
+
+    Raises:
+        FileNotFoundError: If the file does not exist.
+        PDFExtractionError: If the PDF cannot be read or parsed.
+    """
+    path = Path(file_path)
+    if not path.exists():
+        raise FileNotFoundError(f"PDF file not found: {path}")
+
+    if path.suffix.lower() != ".pdf":
+        raise PDFExtractionError(f"Expected a PDF file, got: {path.suffix}")
+
+    try:
+        reader = PdfReader(str(path))
+    except PdfReadError as exc:
+        raise PDFExtractionError(f"Failed to read PDF: {path}") from exc
+    except Exception as exc:
+        raise PDFExtractionError(f"Failed to open PDF: {path}") from exc
+
+    if reader.is_encrypted:
+        try:
+            reader.decrypt("")
+        except Exception as exc:
+            raise PDFExtractionError(f"PDF is encrypted and cannot be read: {path}") from exc
+
+    page_texts: list[str] = []
+    for page in reader.pages:
+        try:
+            page_text = page.extract_text() or ""
+        except Exception:
+            page_text = ""
+        if page_text.strip():
+            page_texts.append(page_text)
+
+    return _normalize_text("\n".join(page_texts))
+
+
+class PDFExtractor:
+    """Extract text from PDF resume files."""
+
+    def extract(self, file_path: PathLike) -> str:
+        """Extract text from a PDF file."""
+        return extract_text_from_pdf(file_path)