From 82b4772f1c0bbb9772c51598625958eef3676b4f Mon Sep 17 00:00:00 2001 From: Pawky Laguish Date: Wed, 27 Nov 2024 22:41:19 +0000 Subject: should mostly work I guess --- soundcloud.py | 113 +++++++++++----------------------------------------------- 1 file changed, 21 insertions(+), 92 deletions(-) (limited to 'soundcloud.py') diff --git a/soundcloud.py b/soundcloud.py index 40c20fd..de0e930 100755 --- a/soundcloud.py +++ b/soundcloud.py @@ -1,7 +1,7 @@ #!/usr/bin/env python3 -from html.parser import HTMLParser +from urllib.parse import urlencode,urlparse from urllib.request import urlopen - +from json import loads as json_loads class SoundCloud: video_type = "" @@ -24,101 +24,30 @@ class SoundCloud: return r - class parseprop(HTMLParser): - def __init__(self): - print("soundcloud parse init") - HTMLParser.__init__(self) - self.itemprops_list = ["name", "duration", "byArtist"] - self.h = {} - self.readartist=False - - def handle_starttag(self, tag, attrs): - print("yo",tag,attrs) - if (tag != "meta" and tag != "link" and tag != "div") or ( - ( - [i for i in attrs if "itemprop" in i] == [] - and ("name", "title") not in attrs - ) - or (tag == "meta" and ("itemprop", "name") in attrs and self.readartist!=True) - ): - print("skip",tag,attrs) - return - # print(self,tag,attrs) - for k, v in attrs: - if k == "itemprop": - if v not in self.itemprops_list: - print("skipprop",tag,attrs) - return - x = [v] - if tag == "link" and v == "name": - x = ["channelName"] - elif k == "content": - #if attrs[0][1] == "interactionCount": - # v = int(v) - x += [v] - elif k == "name" and v == "title": - x = [v] - else: - return - print({x[0]: x[1]}) - self.h.update({x[0]: x[1]}) - # print(x[0],"=",x[1]) - - def fmt_dur(dur): - h, m, s = 0, 0, 0 - dur=dur.removeprefix("PT").removesuffix("S") - h,m = dur.split("H") - m,s = dur.removeprefix(f"{h}H").split("M") - #s = int(m[1][:-1]) - #m = int(m[0]) - h,m,s=int(h),int(m),int(s) - 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 yt(self, url): + def soundcloud(self, url): # self.util.mesg("dbg hello") url = url.rstrip("\x01") - p = self.parseprop() - # use premature optimization? it should be SLIGHTLY faster, but can sometimes fail - data = b"" - if False: #self.premature_optimization: - url_h = urlopen(url) - # 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() - url_h.close() - data = data.decode() # bytes to utf-8 - if ( - data.find('meta itemprop="duration"') == -1 - or data.find('meta itemprop="name"') == -1 - ): # acts as both fallback for optimization, and in case optimization's turned off - # just read all of the html - data = urlopen(url).read().decode() - # print(f"\x1b[31m my data is: {data}\x1b[0m") - p.feed(data) - if p.h == {}: + url=urlparse(url) + url=url.scheme+"://"+url.netloc+url.path + url = f"https://soundcloud.com/oembed?{urlencode([('url',url),('format','json')])}" + data=urlopen(url).read().decode() + data=json_loads(data) + """ {'version': 1.0, 'type': 'rich', 'provider_name': 'SoundCloud', 'provider_url': 'https://soundcloud.com', 'height': 400, 'width': '100%', 'title': 'Doses And Mimosas - Cherub (Mocha Remix) by Mocha Music', 'description': 'One of my favorite songs ever with a dubstep twist! Hope you enjoy :)', 'thumbnail_url': 'https://i1.sndcdn.com/artworks-768QwHQ4tGr0P4wc-iH0Zww-t500x500.jpg', 'html': '', 'author_name': 'Mocha Music', 'author_url': 'https://soundcloud.com/mochamusic11' }""" + #print(data["title"].removesuffix(" by "+data["author_name"]),data["author_name"]) + try: + artist=data["author_name"];title=data["title"].removesuffix(" by "+artist) + except KeyError: + title="";artist="" + print(title.removesuffix(" by "+artist),"|",artist) + if title == "": irc_string = "[\x0304SoundCloud\x03] \x0307ERROR:\x0308 got no data from server! \x0315(check your URL for typos!)\x03" ansi_string = "[\x1b[31mSoundCloud\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 - y = p.h - print(y) - y.update(duration=self.fmt_dur(y["duration"])) - #irc_string = f"[\x0303SoundCloud\x03] \x02{y['title']}\x02 ({y['duration']}) uploaded by \x1d{y['channelName']}\x1d on {y['uploadDate']}, {y['interactionCount']:,} views" - #ansi_string = f"[\x1b[32mSoundCloud\x1b[0m] \x1b[1m{y['title']}\x1b[0m ({y['duration']}) uploaded by \x1b[03m{y['channelName']}\x1b[0m on {y['uploadDate']}, {y['interactionCount']:,} views" - irc_string="dummy";ansi_string="dummy" - print(y) + irc_string = f"[\x0303SoundCloud\x03] \x02{title}\x02 uploaded by \x1d{artist}\x1d" + ansi_string = f"[\x1b[32mSoundCloud\x1b[0m] \x1b[1m{title}\x1b[0m uploaded by \x1b[03m{artist}\x1b[0m" + #""" + #irc_string="dummy";ansi_string="dummy" print(ansi_string) return irc_string, False @@ -126,4 +55,4 @@ class SoundCloud: if __name__ == "__main__": import sys - SoundCloud.yt(SoundCloud, sys.argv[1]) + SoundCloud.soundcloud(SoundCloud, sys.argv[1]) -- cgit 1.4.1-2-gfad0