#!/usr/bin/env python3 from html.parser import HTMLParser from urllib.request import urlopen import json class Spotify: def __init__(self): self.ldjson=None def mesg(self, msg, t=None): self.util.mesg(msg, t) def match_urls(self, str): r = [ i for i in str.split() if "https://open.spotify.com/" in i ] r = list(dict.fromkeys(r)) n = 0 for i in r: if not i.startswith("http"): r.pop(n) n += 1 return r class parseprop(HTMLParser): def __init__(self): print("spotify parse init") HTMLParser.__init__(self) self.ldjson=False def handle_starttag(self, tag, attrs): if (tag == "script" and ('type', 'application/ld+json') in attrs): self.ldjson=True else: self.ldjson=False def handle_endtag(self,tag): self.ldjson=False def handle_data(self,data): if self.ldjson: Spotify.ldjson=data return def fmt_dur(dur): h, m, s = 0, 0, 0 m = dur[2:].split("M") s = int(m[1][:-1]) m = int(m[0]) if m >= 60: h = m // 60 m = round((m / 60 - h) * 60) return f"{h}h {m}m {s}s" elif h == 0 and m == 0 and s == 0: return "LIVE" elif m == 0 and s != 0: return f"{s}s" elif s == 0: return f"{m}m" else: return f"{m}m {s}s" def spotify(self, url): # self.util.mesg("dbg hello") url = url.rstrip("\x01") p = self.parseprop() # use premature optimization? it should be SLIGHTLY faster if self.premature_optimization: url_h, data = urlopen(url), b"" # appears on approximately line 21 or 22, so we read 24 lines to be safe (23-25 should be license comment) # I tried to read byte amounts but it's hard to make sure no invalid utf8 bytes happen due to partial reads for i in range(24): data += url_h.readline() data = data.decode() # bytes to utf-8 url_h.close() else: # just read all of the html data = urlopen(url).read().decode() # print(f"\x1b[31m my data is: {data}\x1b[0m") p.feed(data) # irc_string = "[\x0304Youtube\x03] \x0307ERROR:\x0308 got no data from server! \x0315(check your URL for typos!)\x03" # ansi_string = "[\x1b[31mYoutube\x1b[0m] \x1b[33;2mERROR:\x1b[33;1m got no data from server! \x1b[37;2m(check your URL for typos!)\x1b[0m" # print(ansi_string) # return irc_string, True #irc_string = f"[\x0303Youtube\x03] \x02{y['title']}\x02 ({y['duration']}) uploaded by \x1d{y['channelName']}\x1d on {y['uploadDate']}, {y['interactionCount']:,} views" #ansi_string = f"[\x1b[32mYoutube\x1b[0m] \x1b[1m{y['title']}\x1b[0m ({y['duration']}) uploaded by \x1b[03m{y['channelName']}\x1b[0m on {y['uploadDate']}, {y['interactionCount']:,} views" #print(ansi_string) data=(json.loads(Spotify.ldjson)) #'@type': 'MusicRecording', '@id': 'https://open.spotify.com/track/7hoyhyjcZvOCC9Tv9JgRhr', 'url': 'https://open.spotify.com/track/7hoyhyjcZvOCC9Tv9JgRhr', 'name': 'YO HO (PEG THE POOPDECK)', 'description': 'Listen to YO HO (PEG THE POOPDECK) on Spotify. Song · TheDooo · 2023', 'datePublished': '2023-08-30' #Listen to The Evolution of Tears on Spotify · Album · The Gentle Men · 2021 · 10 songs type=data["@type"] id=data["@id"] name=data["name"] date=data["datePublished"] artists=data["description"] artists=artists.removeprefix(f'Listen to {name} on Spotify') artists=artists.removeprefix('.').strip() artists=artists.removeprefix('· ') if artists.startswith("Song · "): artists=artists.removeprefix("Song · ") elif artists.startswith("Album · "): artists=artists.removeprefix("Album · ") #removes the "10 songs" part artists=artists[::-1].split(" · ",1)[1][::-1] artists=artists.removesuffix(f" · {date[:4]}") #print(type,id,name,"|"+artists+"|",date) print(("Song: " if type=="MusicRecording" else "Album: " if type=="MusicAlbum" else f"Unknown type ({type}): ")+'"'+name+'"'+" by "+'"'+artists+'"'+" released on "+date) irc_string="dummy" return irc_string, False if __name__ == "__main__": import sys Spotify.premature_optimization = False Spotify.spotify(Spotify, sys.argv[1])