mirror of
https://github.com/TheAlgorithms/Python.git
synced 2025-05-18 15:11:28 +00:00
a2fa32c7ad
* Replace dependency `requests` with `httpx` Fixes #12742 Signed-off-by: Lim, Lukaz Wei Hwang <lukaz.wei.hwang.lim@intel.com> * updating DIRECTORY.md * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Signed-off-by: Lim, Lukaz Wei Hwang <lukaz.wei.hwang.lim@intel.com> Co-authored-by: Lim, Lukaz Wei Hwang <lukaz.wei.hwang.lim@intel.com> Co-authored-by: cclauss <cclauss@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
118 lines
3.3 KiB
Python
118 lines
3.3 KiB
Python
"""Get the site emails from URL."""
|
|
|
|
# /// script
|
|
# requires-python = ">=3.13"
|
|
# dependencies = [
|
|
# "httpx",
|
|
# ]
|
|
# ///
|
|
|
|
from __future__ import annotations
|
|
|
|
__author__ = "Muhammad Umer Farooq"
|
|
__license__ = "MIT"
|
|
__version__ = "1.0.0"
|
|
__maintainer__ = "Muhammad Umer Farooq"
|
|
__email__ = "contact@muhammadumerfarooq.me"
|
|
__status__ = "Alpha"
|
|
|
|
import re
|
|
from html.parser import HTMLParser
|
|
from urllib import parse
|
|
|
|
import httpx
|
|
|
|
|
|
class Parser(HTMLParser):
|
|
def __init__(self, domain: str) -> None:
|
|
super().__init__()
|
|
self.urls: list[str] = []
|
|
self.domain = domain
|
|
|
|
def handle_starttag(self, tag: str, attrs: list[tuple[str, str | None]]) -> None:
|
|
"""
|
|
This function parse html to take takes url from tags
|
|
"""
|
|
# Only parse the 'anchor' tag.
|
|
if tag == "a":
|
|
# Check the list of defined attributes.
|
|
for name, value in attrs:
|
|
# If href is defined, not empty nor # print it and not already in urls.
|
|
if name == "href" and value not in (*self.urls, "", "#"):
|
|
url = parse.urljoin(self.domain, value)
|
|
self.urls.append(url)
|
|
|
|
|
|
# Get main domain name (example.com)
|
|
def get_domain_name(url: str) -> str:
|
|
"""
|
|
This function get the main domain name
|
|
|
|
>>> get_domain_name("https://a.b.c.d/e/f?g=h,i=j#k")
|
|
'c.d'
|
|
>>> get_domain_name("Not a URL!")
|
|
''
|
|
"""
|
|
return ".".join(get_sub_domain_name(url).split(".")[-2:])
|
|
|
|
|
|
# Get sub domain name (sub.example.com)
|
|
def get_sub_domain_name(url: str) -> str:
|
|
"""
|
|
>>> get_sub_domain_name("https://a.b.c.d/e/f?g=h,i=j#k")
|
|
'a.b.c.d'
|
|
>>> get_sub_domain_name("Not a URL!")
|
|
''
|
|
"""
|
|
return parse.urlparse(url).netloc
|
|
|
|
|
|
def emails_from_url(url: str = "https://github.com") -> list[str]:
|
|
"""
|
|
This function takes url and return all valid urls
|
|
"""
|
|
# Get the base domain from the url
|
|
domain = get_domain_name(url)
|
|
|
|
# Initialize the parser
|
|
parser = Parser(domain)
|
|
|
|
try:
|
|
# Open URL
|
|
r = httpx.get(url, timeout=10, follow_redirects=True)
|
|
|
|
# pass the raw HTML to the parser to get links
|
|
parser.feed(r.text)
|
|
|
|
# Get links and loop through
|
|
valid_emails = set()
|
|
for link in parser.urls:
|
|
# open URL.
|
|
# Check if the link is already absolute
|
|
if not link.startswith("http://") and not link.startswith("https://"):
|
|
# Prepend protocol only if link starts with domain, normalize otherwise
|
|
if link.startswith(domain):
|
|
link = f"https://{link}"
|
|
else:
|
|
link = parse.urljoin(f"https://{domain}", link)
|
|
try:
|
|
read = httpx.get(link, timeout=10, follow_redirects=True)
|
|
# Get the valid email.
|
|
emails = re.findall("[a-zA-Z0-9]+@" + domain, read.text)
|
|
# If not in list then append it.
|
|
for email in emails:
|
|
valid_emails.add(email)
|
|
except ValueError:
|
|
pass
|
|
except ValueError:
|
|
raise SystemExit(1)
|
|
|
|
# Finally return a sorted list of email addresses with no duplicates.
|
|
return sorted(valid_emails)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
emails = emails_from_url("https://github.com")
|
|
print(f"{len(emails)} emails found:")
|
|
print("\n".join(sorted(emails)))
|