yshalsager

from pathlib import Path

import httpx
from parsel import Selector

root_url = "http://alandals.net"
response = httpx.get(f"{root_url}/Sections.php")
selector = Selector(response.text)
sections_links = selector.css("tr a::attr(href)").getall()

yshalsager

// ==UserScript==
// @name         Islamweb extract audio with names
// @namespace    http://tampermonkey.net/
// @version      0.1
// @description  Copy audio files URL and names from Islamweb.
// @author       yshalsager
// @match        *://audio.islamweb.net/audio/*
// @match        *://audio.islamweb.com/audio/*
// @icon         https://www.google.com/s2/favicons?sz=64&domain=islamweb.net
// @run-at document-idle

yshalsager

// ==UserScript==
// @name         Binaa Manhaji Download Questions as CSV
// @namespace    http://tampermonkey.net/
// @version      0.1
// @description  Adds a download button to binaamanhaji quiz pages to get all questions as CSV file, so they can be imported to Anki.
// @author       yshalsager
// @match        *://*.binaamanhaji.com/usercontrol/excercise?lesson_id=*
// @match        *://*.binaamanhaji.com/usercontrol/exam*
// @icon         https://www.google.com/s2/favicons?sz=64&domain=binaamanhaji.com
// @grant        none

yshalsager

#!/bin/bash
# Scrapes mp3 files links from audio.islamweb.com links into csv data: url, filename
function islamweb_get_mp3() {
    URL=$1
    PAGES="${2:-1}"
    for page in $(seq 1 $PAGES); do
        case $URL in
        *pageno=*)
            URL=$(echo $URL | sed "s|pageno=[0-9]\+|pageno=$page|g");;
        *)

yshalsager

# sed -r -e 's/\r$//;/^[0-9]+$/{N;/\n[0-9]/d;}' -> remove lines with timestamps
# sed -e '/^$/d' -> remove empty lines
# perl -p -e 's|(.*[^\.]$)\n|\1 |g' -> remove new line between paragragh lines.
# ${1%.*} -> input filename without extension

function srt2txt() {
    cat $1 | sed -r -e 's/\r$//;/^[0-9]+$/{N;/\n[0-9]/d;}' | sed -e '/^$/d' | perl -p -e 's|(.*[^\.]$)\n|\1 |g' > "${1%.*}".txt
}

yshalsager

#!/usr/bin/env python3
from urllib.parse import urlparse

from requests import get
from bs4 import BeautifulSoup
from requests.api import head

def get_url_hostname(url):
    parsed_uri = urlparse(url)
    return f'{parsed_uri.scheme}://{parsed_uri.netloc}' 

yshalsager

#!/usr/bin/env python3

from humanize import naturalsize
from requests import get

org = ""

org_size = []
repo_count = 0
response = get(f"https://api.github.com/orgs/{org}/repos")

yshalsager

from requests import get
from bs4 import BeautifulSoup

site = "https://www.princeofwales.gov.uk"
url = f"{site}/biographies/hrh-prince-wales/speeches?title=&mrfs=All&date_from=&date_to=&page="


for page in range(0, 77):  # hardcoded page number
  print(page)
  speeches = BeautifulSoup(get(f"{url}{page}").content, "html.parser").select("div.views-row > div:nth-child(1) > h2:nth-child(1) > a:nth-child(1)")

yshalsager

#!/usr/bin/env python3

from requests import get
from bs4 import BeautifulSoup

chapter = input("Enter Sura number\n")

url = f"http://corpus.quran.com/translation.jsp?chapter={chapter}"
page = BeautifulSoup(get(f'{url}&verse=1').content, "html.parser")
verses = int(page.select_one("#verseList > option:last-of-type")['value'])

yshalsager

#!/usr/bin/env python3.7
"""
A script that calcuate sum of github organization's repositories stargazers
"""

from requests import get

ORG = "XiaomiFirmwareUpdater"
START_PAGE = 1
END_PAGE = 2