RazhanHameed

"""
This script can scrape rudaw.net in two stages

1. `python rudaw.py links` collect links for each category
2. `python rudaw.py content` collect content for each link and writes it to rudaw.csv
"""

import sys
import os
import csv

RazhanHameed

import re

def resolve_ae(text):
    """
    This function takes a text input in Central Kurdish (Sorani) script and performs a series of character replacements
    to standardize variations in the script. Specifically, it addresses cases where the character 'ە' (Arabic letter
    AE) may be used in different contexts.
    """
    # First replace all occurrences of 'ه' with 'ە'
    text = re.sub("ه", "ە", text)

RazhanHameed

import requests
from bs4 import BeautifulSoup
import time


url = 'https://www.kurdfonts.com/browse/categories'
response = requests.get(url)

soup = BeautifulSoup(response.content, 'html.parser')