swe-internship-scraper 1.0.0rc2__tar.gz

swe_internship_scraper-1.0.0rc2/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Furkan Candar
+
+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.

swe_internship_scraper-1.0.0rc2/PKG-INFO

@@ -0,0 +1,114 @@
+Metadata-Version: 2.4
+Name: swe-internship-scraper
+Version: 1.0.0rc2
+Summary: Scrape official ATS job boards for software engineering internships.
+Author: Furkan Candar
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/FurkanSource/swe-internship-scraper
+Project-URL: Documentation, https://github.com/FurkanSource/swe-internship-scraper#readme
+Project-URL: Issues, https://github.com/FurkanSource/swe-internship-scraper/issues
+Project-URL: Changelog, https://github.com/FurkanSource/swe-internship-scraper/blob/main/CHANGELOG.md
+Keywords: internships,jobs,scraper,ats,greenhouse,lever,ashby,workday,smartrecruiters,oracle
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+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: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Internet :: WWW/HTTP :: Indexing/Search
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests<3,>=2.32
+Provides-Extra: browser
+Requires-Dist: scrapling[fetchers]==0.4.15; extra == "browser"
+Dynamic: license-file
+
+# SWE Internship Scraper
+
+[![CI](https://github.com/FurkanSource/swe-internship-scraper/actions/workflows/ci.yml/badge.svg)](https://github.com/FurkanSource/swe-internship-scraper/actions/workflows/ci.yml)
+[![Provider health](https://github.com/FurkanSource/swe-internship-scraper/actions/workflows/provider-health.yml/badge.svg)](https://github.com/FurkanSource/swe-internship-scraper/actions/workflows/provider-health.yml)
+[![PyPI](https://img.shields.io/pypi/v/swe-internship-scraper.svg)](https://pypi.org/project/swe-internship-scraper/)
+
+A command-line tool for finding software engineering internships on official public job boards.
+
+## Quick start
+
+**You do not need to clone or download this repository to use the scraper.** Install
+the package with Python 3.10–3.14, then run a small sample scan. The CSV file is
+written to the folder where you run the command.
+
+Windows PowerShell:
+
+```powershell
+py -m pip install --pre swe-internship-scraper
+py -m swe_scraper scan --quick --output internships.csv
+```
+
+macOS or Linux:
+
+```sh
+python3 -m venv .venv
+.venv/bin/python -m pip install --pre swe-internship-scraper
+.venv/bin/python -m swe_scraper scan --quick --output internships.csv
+```
+
+Open `internships.csv` in a spreadsheet. `--quick` checks the small set of monitored
+boards; it is a sample, not the full catalog. Omit `--quick` for the default
+priority boards, or use `--target-set all` for the entire catalog. The `--pre`
+install flag is needed while the first release is a release candidate; it can be
+removed for stable `1.0.0`.
+
+Want to run the source code you downloaded from GitHub? Follow the
+[source checkout guide](docs/getting-started.md). It has exact Windows and
+macOS/Linux commands, without requiring PowerShell activation.
+
+## What you install
+
+`swe-internship-scraper` is the main package. It includes the command and six
+providers: Greenhouse, Lever, Ashby, Workday, SmartRecruiters, and Oracle.
+The separate `swe-scraper-icims` package is an **optional, experimental** plugin
+for public iCIMS portals. Most users only need the main package. See the
+[plugin guide](docs/icims-plugin.md) if you have an iCIMS portal to scan.
+
+The repository contains scraper code and a public employer catalog. It does not
+include an application tracker, personal data, or applicant ranking rules.
+
+## Commands
+
+```powershell
+py -m swe_scraper scan --output internships.csv
+py -m swe_scraper scan --location "New York" --output nyc-internships.csv
+py -m swe_scraper scan --target-set all --output all-internships.csv
+py -m swe_scraper providers
+py -m swe_scraper --help
+```
+
+The installed `swe-scraper` command is equivalent to `py -m swe_scraper` on
+Windows or `python3 -m swe_scraper` in a Python environment on macOS/Linux.
+For JSON output, use a `.json` filename. See the
+[full command guide](docs/command-line.md) for custom targets, watching, health
+checks, and deduplication reports.
+
+## Output and deduplication
+
+Schema v2 keeps the familiar primary job fields and adds:
+
+- `sources`: every provider, source ID, and direct application URL represented by the record;
+- `merge_evidence`: the rule and confidence for each merged source.
+
+Exact canonical URLs and provider/source identities have confidence `1.0`. Semantic merging requires canonical company, equivalent title including season and year, and equivalent location. Uncertain pairs remain separate and can be written to the optional deduplication audit.
+
+Primary record selection uses completeness and stable lexical tie breakers, so thread completion order does not change output. See [the schema reference](docs/output-schema.md) and [the v2 migration guide](docs/schema-v2-migration.md).
+
+## Development
+
+Read [CONTRIBUTING.md](CONTRIBUTING.md), [the provider guide](docs/provider-development.md),
+and [the support policy](SUPPORT.md) before opening an issue or pull request.
+
+## License
+
+MIT

swe_internship_scraper-1.0.0rc2/README.md

@@ -0,0 +1,85 @@
+# SWE Internship Scraper
+
+[![CI](https://github.com/FurkanSource/swe-internship-scraper/actions/workflows/ci.yml/badge.svg)](https://github.com/FurkanSource/swe-internship-scraper/actions/workflows/ci.yml)
+[![Provider health](https://github.com/FurkanSource/swe-internship-scraper/actions/workflows/provider-health.yml/badge.svg)](https://github.com/FurkanSource/swe-internship-scraper/actions/workflows/provider-health.yml)
+[![PyPI](https://img.shields.io/pypi/v/swe-internship-scraper.svg)](https://pypi.org/project/swe-internship-scraper/)
+
+A command-line tool for finding software engineering internships on official public job boards.
+
+## Quick start
+
+**You do not need to clone or download this repository to use the scraper.** Install
+the package with Python 3.10–3.14, then run a small sample scan. The CSV file is
+written to the folder where you run the command.
+
+Windows PowerShell:
+
+```powershell
+py -m pip install --pre swe-internship-scraper
+py -m swe_scraper scan --quick --output internships.csv
+```
+
+macOS or Linux:
+
+```sh
+python3 -m venv .venv
+.venv/bin/python -m pip install --pre swe-internship-scraper
+.venv/bin/python -m swe_scraper scan --quick --output internships.csv
+```
+
+Open `internships.csv` in a spreadsheet. `--quick` checks the small set of monitored
+boards; it is a sample, not the full catalog. Omit `--quick` for the default
+priority boards, or use `--target-set all` for the entire catalog. The `--pre`
+install flag is needed while the first release is a release candidate; it can be
+removed for stable `1.0.0`.
+
+Want to run the source code you downloaded from GitHub? Follow the
+[source checkout guide](docs/getting-started.md). It has exact Windows and
+macOS/Linux commands, without requiring PowerShell activation.
+
+## What you install
+
+`swe-internship-scraper` is the main package. It includes the command and six
+providers: Greenhouse, Lever, Ashby, Workday, SmartRecruiters, and Oracle.
+The separate `swe-scraper-icims` package is an **optional, experimental** plugin
+for public iCIMS portals. Most users only need the main package. See the
+[plugin guide](docs/icims-plugin.md) if you have an iCIMS portal to scan.
+
+The repository contains scraper code and a public employer catalog. It does not
+include an application tracker, personal data, or applicant ranking rules.
+
+## Commands
+
+```powershell
+py -m swe_scraper scan --output internships.csv
+py -m swe_scraper scan --location "New York" --output nyc-internships.csv
+py -m swe_scraper scan --target-set all --output all-internships.csv
+py -m swe_scraper providers
+py -m swe_scraper --help
+```
+
+The installed `swe-scraper` command is equivalent to `py -m swe_scraper` on
+Windows or `python3 -m swe_scraper` in a Python environment on macOS/Linux.
+For JSON output, use a `.json` filename. See the
+[full command guide](docs/command-line.md) for custom targets, watching, health
+checks, and deduplication reports.
+
+## Output and deduplication
+
+Schema v2 keeps the familiar primary job fields and adds:
+
+- `sources`: every provider, source ID, and direct application URL represented by the record;
+- `merge_evidence`: the rule and confidence for each merged source.
+
+Exact canonical URLs and provider/source identities have confidence `1.0`. Semantic merging requires canonical company, equivalent title including season and year, and equivalent location. Uncertain pairs remain separate and can be written to the optional deduplication audit.
+
+Primary record selection uses completeness and stable lexical tie breakers, so thread completion order does not change output. See [the schema reference](docs/output-schema.md) and [the v2 migration guide](docs/schema-v2-migration.md).
+
+## Development
+
+Read [CONTRIBUTING.md](CONTRIBUTING.md), [the provider guide](docs/provider-development.md),
+and [the support policy](SUPPORT.md) before opening an issue or pull request.
+
+## License
+
+MIT

swe_internship_scraper-1.0.0rc2/pyproject.toml

@@ -0,0 +1,76 @@
+[build-system]
+requires = ["setuptools>=77", "wheel>=0.43"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "swe-internship-scraper"
+version = "1.0.0rc2"
+description = "Scrape official ATS job boards for software engineering internships."
+readme = "README.md"
+requires-python = ">=3.10"
+license = "MIT"
+license-files = ["LICENSE"]
+authors = [{name = "Furkan Candar"}]
+keywords = ["internships", "jobs", "scraper", "ats", "greenhouse", "lever", "ashby", "workday", "smartrecruiters", "oracle"]
+classifiers = [
+  "Development Status :: 4 - Beta",
+  "Environment :: Console",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Programming Language :: Python :: 3.14",
+  "Topic :: Internet :: WWW/HTTP :: Indexing/Search",
+]
+dependencies = [
+  "requests>=2.32,<3",
+]
+
+[project.urls]
+Homepage = "https://github.com/FurkanSource/swe-internship-scraper"
+Documentation = "https://github.com/FurkanSource/swe-internship-scraper#readme"
+Issues = "https://github.com/FurkanSource/swe-internship-scraper/issues"
+Changelog = "https://github.com/FurkanSource/swe-internship-scraper/blob/main/CHANGELOG.md"
+
+[project.optional-dependencies]
+browser = ["scrapling[fetchers]==0.4.15"]
+
+[project.scripts]
+swe-scraper = "swe_scraper.cli:main"
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+swe_scraper = ["data/*.json", "py.typed"]
+
+[tool.ruff]
+target-version = "py310"
+line-length = 92
+extend-exclude = ["tools", "server.py", "pipeline_store.py"]
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP", "B", "SIM", "RUF"]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/*.py" = ["S101"]
+
+[tool.mypy]
+python_version = "3.10"
+strict = true
+files = ["src/swe_scraper", "plugins/icims/src"]
+warn_unreachable = true
+
+[tool.coverage.run]
+branch = true
+source = ["swe_scraper", "swe_scraper_icims"]
+
+[tool.coverage.report]
+fail_under = 90
+show_missing = true
+skip_covered = true

swe_internship_scraper-1.0.0rc2/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

swe_internship_scraper-1.0.0rc2/src/swe_internship_scraper.egg-info/PKG-INFO

@@ -0,0 +1,114 @@
+Metadata-Version: 2.4
+Name: swe-internship-scraper
+Version: 1.0.0rc2
+Summary: Scrape official ATS job boards for software engineering internships.
+Author: Furkan Candar
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/FurkanSource/swe-internship-scraper
+Project-URL: Documentation, https://github.com/FurkanSource/swe-internship-scraper#readme
+Project-URL: Issues, https://github.com/FurkanSource/swe-internship-scraper/issues
+Project-URL: Changelog, https://github.com/FurkanSource/swe-internship-scraper/blob/main/CHANGELOG.md
+Keywords: internships,jobs,scraper,ats,greenhouse,lever,ashby,workday,smartrecruiters,oracle
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+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: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Internet :: WWW/HTTP :: Indexing/Search
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests<3,>=2.32
+Provides-Extra: browser
+Requires-Dist: scrapling[fetchers]==0.4.15; extra == "browser"
+Dynamic: license-file
+
+# SWE Internship Scraper
+
+[![CI](https://github.com/FurkanSource/swe-internship-scraper/actions/workflows/ci.yml/badge.svg)](https://github.com/FurkanSource/swe-internship-scraper/actions/workflows/ci.yml)
+[![Provider health](https://github.com/FurkanSource/swe-internship-scraper/actions/workflows/provider-health.yml/badge.svg)](https://github.com/FurkanSource/swe-internship-scraper/actions/workflows/provider-health.yml)
+[![PyPI](https://img.shields.io/pypi/v/swe-internship-scraper.svg)](https://pypi.org/project/swe-internship-scraper/)
+
+A command-line tool for finding software engineering internships on official public job boards.
+
+## Quick start
+
+**You do not need to clone or download this repository to use the scraper.** Install
+the package with Python 3.10–3.14, then run a small sample scan. The CSV file is
+written to the folder where you run the command.
+
+Windows PowerShell:
+
+```powershell
+py -m pip install --pre swe-internship-scraper
+py -m swe_scraper scan --quick --output internships.csv
+```
+
+macOS or Linux:
+
+```sh
+python3 -m venv .venv
+.venv/bin/python -m pip install --pre swe-internship-scraper
+.venv/bin/python -m swe_scraper scan --quick --output internships.csv
+```
+
+Open `internships.csv` in a spreadsheet. `--quick` checks the small set of monitored
+boards; it is a sample, not the full catalog. Omit `--quick` for the default
+priority boards, or use `--target-set all` for the entire catalog. The `--pre`
+install flag is needed while the first release is a release candidate; it can be
+removed for stable `1.0.0`.
+
+Want to run the source code you downloaded from GitHub? Follow the
+[source checkout guide](docs/getting-started.md). It has exact Windows and
+macOS/Linux commands, without requiring PowerShell activation.
+
+## What you install
+
+`swe-internship-scraper` is the main package. It includes the command and six
+providers: Greenhouse, Lever, Ashby, Workday, SmartRecruiters, and Oracle.
+The separate `swe-scraper-icims` package is an **optional, experimental** plugin
+for public iCIMS portals. Most users only need the main package. See the
+[plugin guide](docs/icims-plugin.md) if you have an iCIMS portal to scan.
+
+The repository contains scraper code and a public employer catalog. It does not
+include an application tracker, personal data, or applicant ranking rules.
+
+## Commands
+
+```powershell
+py -m swe_scraper scan --output internships.csv
+py -m swe_scraper scan --location "New York" --output nyc-internships.csv
+py -m swe_scraper scan --target-set all --output all-internships.csv
+py -m swe_scraper providers
+py -m swe_scraper --help
+```
+
+The installed `swe-scraper` command is equivalent to `py -m swe_scraper` on
+Windows or `python3 -m swe_scraper` in a Python environment on macOS/Linux.
+For JSON output, use a `.json` filename. See the
+[full command guide](docs/command-line.md) for custom targets, watching, health
+checks, and deduplication reports.
+
+## Output and deduplication
+
+Schema v2 keeps the familiar primary job fields and adds:
+
+- `sources`: every provider, source ID, and direct application URL represented by the record;
+- `merge_evidence`: the rule and confidence for each merged source.
+
+Exact canonical URLs and provider/source identities have confidence `1.0`. Semantic merging requires canonical company, equivalent title including season and year, and equivalent location. Uncertain pairs remain separate and can be written to the optional deduplication audit.
+
+Primary record selection uses completeness and stable lexical tie breakers, so thread completion order does not change output. See [the schema reference](docs/output-schema.md) and [the v2 migration guide](docs/schema-v2-migration.md).
+
+## Development
+
+Read [CONTRIBUTING.md](CONTRIBUTING.md), [the provider guide](docs/provider-development.md),
+and [the support policy](SUPPORT.md) before opening an issue or pull request.
+
+## License
+
+MIT

swe_internship_scraper-1.0.0rc2/src/swe_internship_scraper.egg-info/SOURCES.txt

@@ -0,0 +1,49 @@
+LICENSE
+README.md
+pyproject.toml
+src/swe_internship_scraper.egg-info/PKG-INFO
+src/swe_internship_scraper.egg-info/SOURCES.txt
+src/swe_internship_scraper.egg-info/dependency_links.txt
+src/swe_internship_scraper.egg-info/entry_points.txt
+src/swe_internship_scraper.egg-info/requires.txt
+src/swe_internship_scraper.egg-info/top_level.txt
+src/swe_scraper/__init__.py
+src/swe_scraper/__main__.py
+src/swe_scraper/cli.py
+src/swe_scraper/config.py
+src/swe_scraper/dedupe.py
+src/swe_scraper/filters.py
+src/swe_scraper/health.py
+src/swe_scraper/models.py
+src/swe_scraper/normalize.py
+src/swe_scraper/notifications.py
+src/swe_scraper/py.typed
+src/swe_scraper/scanner.py
+src/swe_scraper/validation.py
+src/swe_scraper/watch.py
+src/swe_scraper/data/__init__.py
+src/swe_scraper/data/targets.json
+src/swe_scraper/exporters/__init__.py
+src/swe_scraper/exporters/csv_exporter.py
+src/swe_scraper/exporters/json_exporter.py
+src/swe_scraper/providers/__init__.py
+src/swe_scraper/providers/ashby.py
+src/swe_scraper/providers/base.py
+src/swe_scraper/providers/greenhouse.py
+src/swe_scraper/providers/http.py
+src/swe_scraper/providers/lever.py
+src/swe_scraper/providers/oracle.py
+src/swe_scraper/providers/registry.py
+src/swe_scraper/providers/smartrecruiters.py
+src/swe_scraper/providers/workday.py
+tests/test_catalog_discovery.py
+tests/test_dedupe_benchmark.py
+tests/test_hardening.py
+tests/test_models_and_normalization.py
+tests/test_provider_contract_fixtures.py
+tests/test_provider_failures.py
+tests/test_providers.py
+tests/test_release_quality.py
+tests/test_scanner_cli.py
+tests/test_v1_contract.py
+tests/test_weekly_health.py

swe_internship_scraper-1.0.0rc2/src/swe_internship_scraper.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

swe_internship_scraper-1.0.0rc2/src/swe_internship_scraper.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+swe-scraper = swe_scraper.cli:main

swe_internship_scraper-1.0.0rc2/src/swe_internship_scraper.egg-info/requires.txt

@@ -0,0 +1,4 @@
+requests<3,>=2.32
+
+[browser]
+scrapling[fetchers]==0.4.15

swe_internship_scraper-1.0.0rc2/src/swe_internship_scraper.egg-info/top_level.txt

@@ -0,0 +1 @@
+swe_scraper

swe_internship_scraper-1.0.0rc2/src/swe_scraper/__init__.py

@@ -0,0 +1,13 @@
+"""Reusable software engineering internship scraper."""
+
+__version__ = "1.0.0rc2"
+
+from .models import Job, JobSource, MatchEvidence, ProviderFailure, ScanResult
+
+__all__ = [
+    "Job",
+    "JobSource",
+    "MatchEvidence",
+    "ProviderFailure",
+    "ScanResult",
+]

swe_internship_scraper-1.0.0rc2/src/swe_scraper/__main__.py

@@ -0,0 +1,4 @@
+from .cli import main
+
+if __name__ == "__main__":
+    raise SystemExit(main())