####################################################
Python Module for Scraping Email Addresses from HTML
####################################################
The `email_scraper` module provides a simple method that extracts email addresses from HTML. It is able to find emails
in plain text, links, `atob()` obfuscation and HTML entities obfuscation.
Available on PyPI_.
.. _PyPI: https://pypi.org/pypi/email-scraper/
.. image:: https://github.com/kichik/email-scraper/workflows/Build/badge.svg
:target: https://github.com/kichik/email-scraper/actions
.. image:: https://badge.fury.io/py/email-scraper.svg
:target: https://badge.fury.io/py/email-scraper
Usage
-----
>>> from email_scraper import scrape_emails
>>> scrape_emails('<html><body><a href="mailto:hello@world.com">email me</a></body></html>')
{'hello@world.com'}
>>> scarpe_emails('<a href="javascript:window.location.href=atob(\'bWFpbHRvOmVtYWlsQGV4YW1wbGUuY29t\')">E-Mail</a>')
{'email@example.com'}
Raw data
{
"_id": null,
"home_page": "https://github.com/kichik/email-scraper",
"name": "email-scraper",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "email scraping web obfuscate",
"author": "Amir Szekely",
"author_email": "kichik@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/8e/a3/1c0fa833145e677cc8e5940e5787542c9628853f2c6181c721c199295fc4/email-scraper-0.4.tar.gz",
"platform": "",
"description": "####################################################\nPython Module for Scraping Email Addresses from HTML\n####################################################\n\nThe `email_scraper` module provides a simple method that extracts email addresses from HTML. It is able to find emails\nin plain text, links, `atob()` obfuscation and HTML entities obfuscation.\n\nAvailable on PyPI_.\n\n.. _PyPI: https://pypi.org/pypi/email-scraper/\n\n.. image:: https://github.com/kichik/email-scraper/workflows/Build/badge.svg\n :target: https://github.com/kichik/email-scraper/actions\n\n.. image:: https://badge.fury.io/py/email-scraper.svg\n :target: https://badge.fury.io/py/email-scraper\n\nUsage\n-----\n\n >>> from email_scraper import scrape_emails\n >>> scrape_emails('<html><body><a href=\"mailto:hello@world.com\">email me</a></body></html>')\n {'hello@world.com'}\n >>> scarpe_emails('<a href=\"javascript:window.location.href=atob(\\'bWFpbHRvOmVtYWlsQGV4YW1wbGUuY29t\\')\">E-Mail</a>')\n {'email@example.com'}\n\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Simple utility to extract email addresses from HTML, including obfuscated email addresses",
"version": "0.4",
"split_keywords": [
"email",
"scraping",
"web",
"obfuscate"
],
"urls": [
{
"comment_text": "",
"digests": {
"md5": "c2f5b10a8e3a7f6ee380b3d0b1fb7b4b",
"sha256": "af015e725c0ee0d7ef8d2d60bf3fb1ae9e1dfda70059a09106941f300efdea0f"
},
"downloads": -1,
"filename": "email_scraper-0.4-py2.py3-none-any.whl",
"has_sig": false,
"md5_digest": "c2f5b10a8e3a7f6ee380b3d0b1fb7b4b",
"packagetype": "bdist_wheel",
"python_version": "py2.py3",
"requires_python": null,
"size": 3999,
"upload_time": "2021-03-24T18:12:42",
"upload_time_iso_8601": "2021-03-24T18:12:42.674679Z",
"url": "https://files.pythonhosted.org/packages/6e/aa/19891f399376dd0d69399b55404487ec3f6c245e231a09c3a018b37ea313/email_scraper-0.4-py2.py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"md5": "e7fc63886aa30ac47a2d1c97b02ded65",
"sha256": "8749d8b7fa6f02543343a5d1c814d9eb21ebb291b203594f06120f223160d52d"
},
"downloads": -1,
"filename": "email-scraper-0.4.tar.gz",
"has_sig": false,
"md5_digest": "e7fc63886aa30ac47a2d1c97b02ded65",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 2782,
"upload_time": "2021-03-24T18:12:43",
"upload_time_iso_8601": "2021-03-24T18:12:43.767883Z",
"url": "https://files.pythonhosted.org/packages/8e/a3/1c0fa833145e677cc8e5940e5787542c9628853f2c6181c721c199295fc4/email-scraper-0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2021-03-24 18:12:43",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": null,
"github_project": "kichik",
"error": "Could not fetch GitHub repository",
"lcname": "email-scraper"
}
JSON
