update indexed tags

This commit is contained in:
Jack Robison 2020-09-24 12:58:49 -04:00
parent 43c2e8d8e9
commit 7000ac3f3f
No known key found for this signature in database
GPG key ID: DF25C68FE0239BB2

View file

@ -13,209 +13,306 @@ STREAM_TYPES = {
'model': 6
}
# 9/21/2020
MOST_USED_TAGS = {
"gaming",
"people & blogs",
"entertainment",
"music",
"pop culture",
"education",
"technology",
"blockchain",
"news",
"funny",
"science & technology",
"learning",
"gameplay",
"news & politics",
"comedy",
"bitcoin",
"beliefs",
"nature",
"art",
"economics",
"film & animation",
"lets play",
"games",
"sports",
"howto & style",
"game",
"cryptocurrency",
"playstation 4",
"automotive",
"crypto",
"mature",
"sony interactive entertainment",
"walkthrough",
"tutorial",
"video game",
"weapons",
"pc",
"playthrough",
"anime",
"how to",
"btc",
"fun",
"ethereum",
"food",
"travel & events",
"minecraft",
"science",
"autos & vehicles",
"play",
"politics",
"commentary",
"twitch",
"ps4live",
"love",
"ps4",
"nonprofits & activism",
"ps4share",
"fortnite",
"xbox",
"porn",
"video games",
"trump",
"español",
"money",
"music video",
"movie",
"coronavirus",
"nintendo",
"donald trump",
"steam",
"trailer",
"android",
"podcast",
"xbox one",
"survival",
"linux",
"travel",
"funny moments",
"audio",
"litecoin",
"animation",
"gamer",
"lets",
"playstation",
"bitcoin news",
"history",
"fox news",
"xxx",
"god",
"dance",
"adventure",
"liberal",
"horror",
"government",
"freedom",
"2020",
"reaction",
"meme",
"photography",
"truth"
}
MATURE_TAGS = [
'nsfw', 'porn', 'xxx', 'mature', 'adult', 'sex'
]
def normalize_tag(tag):
return tag.replace(" ", "_").replace("&", "and").replace("-", "_")
COMMON_TAGS = {
"gaming": "gaming",
"people & blogs": "people_and_blogs",
"pop culture": "pop_culture",
"entertainment": "entertainment",
"technology": "technology",
"music": "music",
"funny": "funny",
"education": "education",
"learning": "learning",
"news": "news",
"gameplay": "gameplay",
"science & technology": "science_and_technology",
"playstation 4": "playstation_4",
"beliefs": "beliefs",
"nature": "nature",
"news & politics": "news_and_politics",
"comedy": "comedy",
"games": "games",
"sony interactive entertainment": "sony_interactive_entertainment",
"film & animation": "film_and_animation",
"game": "game",
"howto & style": "howto_and_style",
"weapons": "weapons",
"blockchain": "blockchain",
"video game": "video_game",
"sports": "sports",
"walkthrough": "walkthrough",
"ps4live": "ps4live",
"art": "art",
"pc": "pc",
"economics": "economics",
"automotive": "automotive",
"minecraft": "minecraft",
"playthrough": "playthrough",
"ps4share": "ps4share",
"tutorial": "tutorial",
"play": "play",
"twitch": "twitch",
"how to": "how_to",
"ps4": "ps4",
"bitcoin": "bitcoin",
"fortnite": "fortnite",
"commentary": "commentary",
"lets play": "lets_play",
"fun": "fun",
"politics": "politics",
"xbox": "xbox",
"autos & vehicles": "autos_and_vehicles",
"travel & events": "travel_and_events",
"food": "food",
"science": "science",
"mature": "mature",
"xbox one": "xbox_one",
"liberal": "liberal",
"democrat": "democrat",
"progressive": "progressive",
"survival": "survival",
"nonprofits & activism": "nonprofits_and_activism",
"cryptocurrency": "cryptocurrency",
"playstation": "playstation",
"nintendo": "nintendo",
"government": "government",
"steam": "steam",
"podcast": "podcast",
"horror": "horror",
"conservative": "conservative",
"reaction": "reaction",
"trailer": "trailer",
"love": "love",
"cnn": "cnn",
"republican": "republican",
"gamer": "gamer",
"political": "political",
"hangoutsonair": "hangoutsonair",
"hoa": "hoa",
"msnbc": "msnbc",
"cbs": "cbs",
"donald trump": "donald_trump",
"fiction": "fiction",
"fox news": "fox_news",
"anime": "anime",
"crypto": "crypto",
"ethereum": "ethereum",
"call of duty": "call_of_duty",
"multiplayer": "multiplayer",
"android": "android",
"epic": "epic",
"rpg": "rpg",
"adventure": "adventure",
"secular talk": "secular_talk",
"btc": "btc",
"atheist": "atheist",
"atheism": "atheism",
"ps3": "ps3",
"video games": "video_games",
"cod": "cod",
"agnostic": "agnostic",
"movie": "movie",
"online": "online",
"fps": "fps",
"mod": "mod",
"reviews": "reviews",
"sharefactory": "sharefactory",
"world": "world",
"space": "space",
"hilarious": "hilarious",
"stream": "stream",
"lol": "lol",
"sony": "sony",
"god": "god",
"lets": "lets",
"dance": "dance",
"pvp": "pvp",
"tech": "tech",
"zombies": "zombies",
"pokemon": "pokemon",
"fail": "fail",
"xbox 360": "xbox_360",
"film": "film",
"unboxing": "unboxing",
"animation": "animation",
"travel": "travel",
"money": "money",
"wwe": "wwe",
"how": "how",
"mods": "mods",
"pubg": "pubg",
"indie": "indie",
"strategy": "strategy",
"history": "history",
"rap": "rap",
"ios": "ios",
"sony computer entertainment": "sony_computer_entertainment",
"mobile": "mobile",
"trump": "trump",
"flat earth": "flat_earth",
"hack": "hack",
"trap": "trap",
"fox": "fox",
"vlogging": "vlogging",
"news radio": "news_radio",
"humor": "humor",
"facebook": "facebook",
"edm": "edm",
"fitness": "fitness",
"vaping": "vaping",
"hip hop": "hip_hop",
"secular": "secular",
"jesus": "jesus",
"vape": "vape",
"song": "song",
"remix": "remix",
"guitar": "guitar",
"daily": "daily",
"mining": "mining",
"diy": "diy",
"videogame": "videogame",
"pets & animals": "pets_and_animals",
"funny moments": "funny_moments",
"religion": "religion",
"death": "death",
"media": "media",
"nbc": "nbc",
"war": "war",
"freedom": "freedom",
"viral": "viral",
"meme": "meme",
"family": "family",
"gold": "gold",
"photography": "photography",
"chill": "chill",
"zombie": "zombie",
"computer": "computer",
"sniper": "sniper",
"bible": "bible",
"linux": "linux",
"overwatch": "overwatch",
"pro": "pro",
"dragon": "dragon",
"litecoin": "litecoin",
"gta": "gta",
"iphone": "iphone",
"house": "house",
"bass": "bass",
"bitcoin news": "bitcoin_news",
"wii": "wii",
"crash": "crash",
"league of legends": "league_of_legends",
"grand theft auto v": "grand_theft_auto_v",
"mario": "mario",
"mmorpg": "mmorpg",
"satire": "satire",
"fire": "fire",
"racing": "racing",
"apple": "apple",
"health": "health",
"instrumental": "instrumental",
"destiny": "destiny",
"truth": "truth",
"race": "race"
tag: normalize_tag(tag) for tag in list(MOST_USED_TAGS)
}
INDEXED_LANGUAGES = [
'en',
'aa',
'ab',
'ae',
'af',
'ak',
'am',
'an',
'ar',
'as',
'av',
'ay',
'az',
'ba',
'be',
'bg',
'bh',
'bi',
'bm',
'bn',
'bo',
'br',
'bs',
'ca',
'ce',
'ch',
'co',
'cr',
'cs',
'cu',
'cv',
'cy',
'da',
'de',
'dv',
'dz',
'ee',
'el',
'eo',
'es',
'et',
'eu',
'fa',
'ff',
'fi',
'fj',
'fo',
'fr',
'fy',
'ga',
'gd',
'gl',
'gn',
'gu',
'gv',
'ha',
'he',
'hi',
'ho',
'hr',
'ht',
'hu',
'hy',
'hz',
'ia',
'id',
'ie',
'ig',
'ii',
'ik',
'io',
'is',
'it',
'iu',
'ja',
'jv',
'ka',
'kg',
'ki',
'kj',
'kk',
'kl',
'km',
'kn',
'ko',
'kr',
'ks',
'ku',
'kv',
'kw',
'ky',
'la',
'lb',
'lg',
'li',
'ln',
'lo',
'lt',
'lu',
'lv',
'mg',
'mh',
'mi',
'mk',
'ml',
'mn',
'mr',
'ms',
'mt',
'my',
'na',
'nb',
'nd',
'ne',
'ng',
'nl',
'nn',
'no',
'nr',
'nv',
'ny',
'oc',
'oj',
'om',
'or',
'os',
'pa',
'pi',
'pl',
'ps',
'pt',
'qu',
'rm',
'rn',
'ro',
'ru',
'rw',
'sa',
'sc',
'sd',
'se',
'sg',
'si',
'sk',
'sl',
'sm',
'sn',
'so',
'sq',
'sr',
'ss',
'st',
'su',
'sv',
'sw',
'ta',
'te',
'tg',
'th',
'ti',
'tk',
'tl',
'tn',
'to',
'tr',
'ts',
'tt',
'tw',
'ty',
'ug',
'uk',
'ur',
'uz',
've',
'vi',
'vo',
'wa',
'wo',
'xh',
'yi',
'yo',
'za',
'zh',
'zu'
]