RADIO1.HU WorldIsMine RadioShow Downloader Script

r1dl.py

# original made by a-sync: https://gist.github.com/a-sync/e8c1f1d01b8ff8ce0181051cb72bda04
# python version by mva-one: https://gist.github.com/mva-one/b6426b7469faa7c572c3d1be93082c6c

from os import getcwd
import re
import shutil
import urllib3
from unidecode import unidecode

urllist = [
    "https://radio1.hu/tracklista/metzker-viktoria-mix/",
    "https://radio1.hu/tracklista/world-is-mine-radio-show-jauri-mix/",
    "https://radio1.hu/tracklista/bricklake-mix/",
    "https://radio1.hu/tracklista/world-is-mine-radio-show-willcox-mix/",
    "https://radio1.hu/tracklista/purebeat-mix/",
    "https://radio1.hu/tracklista/loving-arms-mix/",
    "https://radio1.hu/tracklista/world-is-mine-radio-show-stadium-x-mix/",
    "https://radio1.hu/tracklista/world-is-mine-radio-show-antonyo-mix/",
    "https://radio1.hu/tracklista/world-is-mine-radio-show-joerjunior-mix/",
    "https://radio1.hu/tracklista/world-is-mine-radio-show-regan-lili-mix/",
    "https://radio1.hu/tracklista/andro-mix/",
    "https://radio1.hu/tracklista/world-is-mine-radio-show-nigel-stately-mix/",
    "https://radio1.hu/tracklista/world-is-mine-radio-show-yamina-mix/",
    "https://radio1.hu/tracklista/newik-mix/",
    "https://radio1.hu/tracklista/world-is-mine-radio-show-lotfi-begi-mix/"
]


# repeat for all desired mixes
for url in urllist:

    # get the html, and parse the audio elements
    http = urllib3.PoolManager()
    html = http.request('GET', url).data.decode('utf-8')
    # nice RegEx made by https://github.com/a-sync
    pattern = """<audio data-artist="(.*?)" data-title="(.*?)".*?>\n.*?<source src="(.*?)" type="audio/mp3">""" 
    matches = re.findall(pattern, html, re.IGNORECASE)
    
    # for each audio, download the file and name it like desired
    for match in matches:
        title = match[0]
        datetime = match[1]
        source = "https://www.radio1.hu" + match[2]        
        
        dlheaders = urllib3._collections.HTTPHeaderDict()
        dlheaders.add("Referer", url)
        dlheaders.add("Connection", "keep-alive")
        dlheaders.add("Host", "radio1.hu")

        titlesplit = title.split("-",1)
        if len(titlesplit) == 2:
            artist = unidecode(title.split("-",1)[1].replace(" ", ""))
        else:
            artist = "ERROR"

        date = unidecode(datetime.split(":")[0].replace(" ",""))

        filename = getcwd() + "\\R1_WIM_" + artist + "_" + date + ".mp3"
        
        print("Filename: " + filename + " Title: " + title + "  Date: " + datetime + "  Source: " + source)

        # Download file(s)
        try:
            with http.request('GET', source, headers=dlheaders, preload_content=False) as r, open(filename, "wb") as file:
                print("STATUS = " + str(r.status))
                shutil.copyfileobj(r, file)
        except:
            print("An exception occured!")