This code takes a LinkedIn post URL and returns the exact date of the post

linkedin_post_date_extractor.py

"""
This code takes a LinkedIn URL and returns the date of the post.

The code uses the following steps:

1. Extracts the post ID from the URL.
2. Converts the post ID to a Unix timestamp.
3. Converts the Unix timestamp to a human-readable date.

The code uses the following libraries:

* `re`: Regular expressions
* `datetime`: Date and time handling

"""

import re
from datetime import datetime


def get_post_id(url):
    """
    This function extracts the post ID from a LinkedIn URL.

    Args:
        url: The LinkedIn URL.

    Returns:
        The post ID.
    """

    # Check if the URL is a valid LinkedIn URL.
    if not re.match(r"https://www.linkedin.com/post/[0-9]+", url):
        raise ValueError("Invalid URL")

    # Extract the post ID from the URL.
    post_id = re.search(r"([0-9]{19})", url).group()

    return post_id


def extract_unix_timestamp(post_id):
    """
    This function converts a post ID to a Unix timestamp.

    Args:
        post_id: The post ID.

    Returns:
        The Unix timestamp.
    """

    # Convert the post ID to a binary string.
    as_binary = format(int(post_id), "b")

    # Take the first 41 characters of the binary string.
    first_41_chars = as_binary[:41]

    # Convert the binary string to a Unix timestamp.
    timestamp = int(first_41_chars, 2) / 1000

    return timestamp


def unix_timestamp_to_human_date(timestamp):
    """
    This function converts a Unix timestamp to a human-readable date.

    Args:
        timestamp: The Unix timestamp.

    Returns:
        The human-readable date.
    """

    # Create a datetime object from the Unix timestamp.
    date_object = datetime.utcfromtimestamp(timestamp)

    # Format the datetime object in a human-readable format.
    human_date_format = date_object.strftime("%a, %d %b %Y %H:%M:%S GMT")

    return human_date_format


def unix_timestamp_to_string(timestamp):
    """
    This function converts a Unix timestamp to a string.

    Args:
        timestamp: The Unix timestamp.

    Returns:
        The string.
    """

    # Create a datetime object from the Unix timestamp.
    date_object = datetime.utcfromtimestamp(timestamp)

    # Format the datetime object in a string format.
    formatted_date = date_object.strftime("%Y-%m-%d %H:%M")

    return formatted_date


def get_date(url):
    """
    This function takes a LinkedIn URL and returns the date of the post.

    Args:
        url: The LinkedIn URL.

    Returns:
        The date of the post.
    """

    # Extract the post ID from the URL.
    post_id = get_post_id(url)

    # Convert the post ID to a Unix timestamp.
    unix_timestamp = extract_unix_timestamp(post_id)

    # Convert the Unix timestamp to a human-readable date.
    human_date_format = unix_timestamp_to_string(unix_timestamp)

    return human_date_format


if __name__ == "__main__":
    # Get the date of the post from the given URL.
    post_url = "https://www.linkedin.com/post/6782523308840636416"
    date = get_date(post_url)

    # Print the date.
    print(date)