algorithm/Python
1
0
Fork 0
mirror of https://github.com/TheAlgorithms/Python.git synced 2025-07-05 17:34:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

Lukazlim: Replace dependency requests with httpx (#12744)

Browse Source 
* 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>
This commit is contained in:
Christian Clauss
2025-05-14 03:42:11 +02:00
committed by GitHub
parent 6e4d1b3765
commit a2fa32c7ad
40 changed files with 957 additions and 640 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
web_programming/emails_from_url.py
View File

@ -1,5 +1,12 @@
"""Get the site emails from URL."""
# /// script
# requires-python = ">=3.13"
# dependencies = [
# "httpx",
# ]
# ///
from __future__ import annotations
__author__ = "Muhammad Umer Farooq"
@ -13,7 +20,7 @@ import re
from html.parser import HTMLParser
from urllib import parse
import requests
import httpx
class Parser(HTMLParser):
@ -72,7 +79,7 @@ def emails_from_url(url: str = "https://github.com") -> list[str]:
try:
# Open URL
r = requests.get(url, timeout=10)
r = httpx.get(url, timeout=10, follow_redirects=True)
# pass the raw HTML to the parser to get links
parser.feed(r.text)
@ -81,9 +88,15 @@ def emails_from_url(url: str = "https://github.com") -> list[str]:
valid_emails = set()
for link in parser.urls:
# open URL.
# read = requests.get(link)
# 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 = requests.get(link, timeout=10)
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.