===========
selectorlib
===========
.. image:: https://img.shields.io/pypi/v/selectorlib.svg
:target: https://pypi.python.org/pypi/selectorlib
.. image:: https://img.shields.io/travis/scrapehero/selectorlib.svg
:target: https://travis-ci.org/scrapehero/selectorlib
.. image:: https://readthedocs.org/projects/selectorlib/badge/?version=latest
:target: https://selectorlib.readthedocs.io/en/latest/?badge=latest
:alt: Documentation Status
.. image:: https://pyup.io/repos/github/scrapehero/selectorlib/shield.svg
:target: https://pyup.io/repos/github/scrapehero/selectorlib/
:alt: Updates
A library to read a YML file with Xpath or CSS Selectors and extract data from HTML pages using them
* Free software: MIT license
* Documentation: https://selectorlib.readthedocs.io.
Example
--------
>>> from selectorlib import Extractor
>>> yaml_string = """
title:
css: "h1"
type: Text
link:
css: "h2 a"
type: Link
"""
>>> extractor = Extractor.from_yaml_string(yaml_string)
>>> html = """
<h1>Title</h1>
<h2>Usage
<a class="headerlink" href="http://test">ΒΆ</a>
</h2>
"""
>>> extractor.extract(html)
{'title': 'Title', 'link': 'http://test'}
=======
History
=======
Raw data
{
"_id": null,
"home_page": "https://github.com/scrapehero/selectorlib",
"name": "selectorlib",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "selectorlib",
"author": "scrapehero",
"author_email": "pypi@scrapehero.com",
"download_url": "https://files.pythonhosted.org/packages/00/57/f1ae8c2740980eec4a142fd8b1f6603294bba079add5e29bf62f51503c96/selectorlib-0.16.0.tar.gz",
"platform": "",
"description": "===========\nselectorlib\n===========\n\n\n.. image:: https://img.shields.io/pypi/v/selectorlib.svg\n :target: https://pypi.python.org/pypi/selectorlib\n\n.. image:: https://img.shields.io/travis/scrapehero/selectorlib.svg\n :target: https://travis-ci.org/scrapehero/selectorlib\n\n.. image:: https://readthedocs.org/projects/selectorlib/badge/?version=latest\n :target: https://selectorlib.readthedocs.io/en/latest/?badge=latest\n :alt: Documentation Status\n\n\n.. image:: https://pyup.io/repos/github/scrapehero/selectorlib/shield.svg\n :target: https://pyup.io/repos/github/scrapehero/selectorlib/\n :alt: Updates\n\n\n\nA library to read a YML file with Xpath or CSS Selectors and extract data from HTML pages using them\n\n* Free software: MIT license\n* Documentation: https://selectorlib.readthedocs.io.\n\n\nExample\n--------\n\n>>> from selectorlib import Extractor\n>>> yaml_string = \"\"\"\n title:\n css: \"h1\"\n type: Text\n link:\n css: \"h2 a\"\n type: Link\n \"\"\"\n>>> extractor = Extractor.from_yaml_string(yaml_string)\n>>> html = \"\"\"\n <h1>Title</h1>\n <h2>Usage\n <a class=\"headerlink\" href=\"http://test\">\u00b6</a>\n </h2>\n \"\"\"\n>>> extractor.extract(html)\n{'title': 'Title', 'link': 'http://test'}\n\n\n=======\nHistory\n=======\n\n\n",
"bugtrack_url": null,
"license": "MIT license",
"summary": "A library to read a YML file with Xpath or CSS Selectors and extract data from HTML pages using them",
"version": "0.16.0",
"project_urls": {
"Homepage": "https://github.com/scrapehero/selectorlib"
},
"split_keywords": [
"selectorlib"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "1e3e7ad0a01b07c066cf79c431324970869345e4d249242d70f20e939a5c630b",
"md5": "8aa1a3ca4568c3d278192b6d8766f1e9",
"sha256": "007c156d01ab8de86f72f0914d66d704f6fb4ebda0db0e04f204083d63e55bc6"
},
"downloads": -1,
"filename": "selectorlib-0.16.0-py2.py3-none-any.whl",
"has_sig": false,
"md5_digest": "8aa1a3ca4568c3d278192b6d8766f1e9",
"packagetype": "bdist_wheel",
"python_version": "py2.py3",
"requires_python": null,
"size": 5832,
"upload_time": "2020-01-08T14:50:57",
"upload_time_iso_8601": "2020-01-08T14:50:57.800178Z",
"url": "https://files.pythonhosted.org/packages/1e/3e/7ad0a01b07c066cf79c431324970869345e4d249242d70f20e939a5c630b/selectorlib-0.16.0-py2.py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "0057f1ae8c2740980eec4a142fd8b1f6603294bba079add5e29bf62f51503c96",
"md5": "da86499c58c7e12a63e77ab592240e61",
"sha256": "154f7c5f39bc825a0717b24ca2cc0b95dcb2caa1669239f3d4ac6e41af398731"
},
"downloads": -1,
"filename": "selectorlib-0.16.0.tar.gz",
"has_sig": false,
"md5_digest": "da86499c58c7e12a63e77ab592240e61",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 188826,
"upload_time": "2020-01-08T14:50:58",
"upload_time_iso_8601": "2020-01-08T14:50:58.964482Z",
"url": "https://files.pythonhosted.org/packages/00/57/f1ae8c2740980eec4a142fd8b1f6603294bba079add5e29bf62f51503c96/selectorlib-0.16.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2020-01-08 14:50:58",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "scrapehero",
"github_project": "selectorlib",
"travis_ci": true,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "Click",
"specs": [
[
">=",
"6.0"
]
]
},
{
"name": "pyyaml",
"specs": [
[
">=",
"3.12"
]
]
},
{
"name": "parsel",
"specs": [
[
">=",
"1.5.1"
]
]
}
],
"tox": true,
"lcname": "selectorlib"
}
JSON
