op-helper.py v0.2 by C-Anon

#!/usr/bin/env python3
# op-helper.py for making threads on /vt/
# Released under MIT License, software is provided as-is and all that crap.
# v0.2 by C-Anon

import re, json, urllib.request
import datetime, time


##########################
#   CONFIGURATION

# Ignore streams if they're set this amount of days from now (or more)
ignore_days = 10

# Sort streams by starting timestamp
sort_streams = False

# Show stream titles
show_live_titles = False
show_upcoming_titles = False

# Show timezones
show_timezones = False

# If true, data is output to a file instead of the terminal
output_to_file = True
outfname = 'op-helper.txt'

# Channel data
#   The format is channel ID followed by a space, then followed
#   by the name of the channel. Empty lines are ignored
channel_data = """
UC8P3OkWBUsrk93f1pV0b5bQ Ageha Himeragi
UCEnhASxlFG-ZPCpYDTYIQZA Charo Nemurime
UCAx0YWXJgyvXx5oDvrDaN_A Himari Inumaki
UCvm34tgJ0ZaKzTinWVyXpcA Himea D'Almaria
UC6tSB9TnO0f01OBeo9UEJZA Hina Misora
UCVtuciDzkjxCP_O7r-0QhXQ Ito Shinonome
UCJePO0Zl-zZTqjpHO82RNNA Lia Mitsurugi
UCN3mosAMYBdogyQovOhPrxA Luna Rurine
UClXfBZMVxt-JgNMaHGr5NMQ Mahiru Kumaboshi
UCUUjykb68Lf85CbWX6gAmog Mireille Kuuma
UCM6iy_rSgSMbFjx10Z6VVGA Miu Hizuki
UCIm8pnnTNhCgGAtNxrQQv-g Yue Saohime
"""

# Timezone data
#   You can specify timezones to display along with the other information.
#   The format is the name of the timezone followed by a space, then followed
#   by the number of hours from UTC (e.g. Mexico City timezone is GMT-5 in summer)
#
#   This might need to be adjusted as countries adopt and abandon daylight savings time
#   throughout the year.
timezone_data = """
MEX -5
ARG -3
ESP 2
JAP 9
"""

#   END OF CONFIGURATION
##########################

now = time.time

def getStreams(channel_id, channel_owner):
    url = 'https://www.youtube.com/channel/%s/' % (channel_id)
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:104.0) Gecko/20100101 Firefox/104.0',
        'Accept-Language': 'en-US,en;q=0.5'
    }

    try:
        req = urllib.request.Request(url, headers=headers)
        conn = urllib.request.urlopen(req)
    except (urllib.error.URLError, ValueError) as e:
        print("Error! Couldn't retrieve URL. ", str(e).capitalize())
        return
    response = conn.read().decode('utf-8')
    temp = re.findall('<script nonce="[^"]+">var ytInitialData = (.*?);</script>', response)
    if not temp:
        return

    streams = {}
    json_obj = json.loads(temp[0])
    first_tab = json_obj['contents']['twoColumnBrowseResultsRenderer']['tabs'][0]
    for section in first_tab['tabRenderer']['content']['sectionListRenderer']['contents']:
        if 'shelfRenderer' not in section['itemSectionRenderer']['contents'][0]:
            continue
        shelf_type = section['itemSectionRenderer']['contents'][0]['shelfRenderer']['title']['runs'][0]['text']
        if  shelf_type not in ['Live now', 'Upcoming live streams']:
            continue

        if 'expandedShelfContentsRenderer' not in section['itemSectionRenderer']['contents'][0]['shelfRenderer']['content']:
            row = section['itemSectionRenderer']['contents'][0]['shelfRenderer']['content']['horizontalListRenderer']['items']
            vrname = 'gridVideoRenderer'
        else:
            row = section['itemSectionRenderer']['contents'][0]['shelfRenderer']['content']['expandedShelfContentsRenderer']['items']
            vrname = 'videoRenderer'
        for elem in row:
            new_stream = {'videoId': '', 'type'   : '', 'start'  : '', 'title'  : '', 'owner':''}
            if shelf_type == "Live now":
                new_stream['videoId'] = elem[vrname]['videoId']
                new_stream['type']    = "live"
                new_stream['start']   = ""
                new_stream['owner']   = channel_owner
                new_stream['title']   = elem[vrname]['title']['simpleText']
                if 'live' not in streams:
                    streams['live'] = [new_stream]
                else:
                    streams['live'].append(new_stream)
            elif shelf_type == "Upcoming live streams":
                if 'upcomingEventData' not in elem[vrname]:
                    continue
                new_stream['videoId'] = elem[vrname]['videoId']
                new_stream['type']    = "upcoming"
                new_stream['start']   = elem[vrname]['upcomingEventData']['startTime']
                new_stream['owner']   = channel_owner
                new_stream['title']   = elem[vrname]['title']['simpleText']
                if 'upcoming' not in streams:
                    streams['upcoming'] = [new_stream]
                else:
                    streams['upcoming'].append(new_stream)
    return streams

def getTimeString(ts):
    ret = ""
    last_date = ""
    for tz in timezones:
        dts = ts + (tz['delta'] * 3600)
        dts = datetime.datetime.utcfromtimestamp(dts)
        date = datetime.datetime.strftime(dts, '%Y-%m-%d')
        if last_date != date:
            ret += date + " "
        ret += datetime.datetime.strftime(dts, '%H:%M') + " " + tz['name'] + " "
        last_date = date
    return ret

def log(txt):
    if output_to_file and fp:
        fp.write(txt + "\n")
    else:
        print(txt)

channels = []
for line in channel_data.splitlines():
    if not line or line == "":
        continue
    tmp = line.split(' ')
    channels.append({'channelId': tmp[0], 'channelOwner': " ".join(tmp[1:])})

timezones = []
for line in timezone_data.splitlines():
    if not line or line == "":
        continue
    tmp = line.split(' ')
    timezones.append({'name': tmp[0], 'delta': float(tmp[1])})

# Sort timezones
timezones = sorted(timezones, key=lambda kv: kv['delta'])

live_streams = []
upcoming_streams = []
# Retrieve information from channels
for chan in channels:
    print("Retrieving %s channel (%s)" % (chan['channelOwner'], chan['channelId']))
    streams = getStreams(chan['channelId'], chan['channelOwner'])
    if not streams:
        continue
    if 'live' in streams:
        live_streams += streams['live']
    if 'upcoming' in streams:
        upcoming_streams += streams['upcoming']

if output_to_file:
    fp = open(outfname, 'w', encoding='utf-8')

live_streams = sorted(live_streams, key=lambda kv: kv['owner'])
if live_streams:
    log('LIVE STREAMS:')
    last_owner = ""
    for stream in live_streams:
        if stream['owner'] != last_owner:
            log("\n" + stream['owner'])
        if show_live_titles:
            log(stream['title'])
        log("https://youtu.be/%s" % stream['videoId'])
        last_owner = stream['owner']
log("")
if sort_streams:
    upcoming_streams = sorted(upcoming_streams, key=lambda kv: kv['start'])
if upcoming_streams:
    log('UPCOMING STREAMS:')
    last_owner = ''
    for stream in upcoming_streams:
        # If upcoming stream is more than 'ignore_days' days away, ignore it
        if now() + (60 * 60 * 24 * ignore_days) < int(stream['start']):
            continue

        timestr = getTimeString(int(stream['start']))
        if stream['owner'] != last_owner:
            log("\n" + stream['owner'])
        if show_upcoming_titles:
            log(stream['title'])
        log("https://youtu.be/%s" % (stream['videoId']))
        if show_timezones:
            log(timestr)
        last_owner = stream['owner']
if output_to_file:
    print("Output to file %s" % outfname)