Add comprehensive YouTube language codes arrays for transcript downloader
This commit is contained in:
35
language_codes.py
Normal file
35
language_codes.py
Normal file
@@ -0,0 +1,35 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Global array of all 2-letter language codes supported by YouTube"""
|
||||
|
||||
# Complete list of 2-letter language codes supported by YouTube
|
||||
YOUTUBE_LANGUAGE_CODES = [
|
||||
"af", "sq", "am", "ar", "hy", "az", "eu", "be", "bn", "bs", "bg", "ca", "ceb", "zh", "zh-Hant",
|
||||
"co", "hr", "cs", "da", "nl", "en", "eo", "et", "fi", "fr", "fy", "gl", "ka", "de", "el", "gu",
|
||||
"ht", "ha", "haw", "iw", "hi", "hmn", "hu", "is", "ig", "id", "ga", "it", "ja", "jw", "kn", "kk",
|
||||
"km", "rw", "ko", "ku", "ky", "lo", "la", "lv", "lt", "lb", "mk", "mg", "ms", "ml", "mt", "mi",
|
||||
"mr", "mn", "my", "ne", "no", "ny", "or", "ps", "fa", "pl", "pt", "pa", "ro", "ru", "sm", "gd",
|
||||
"sr", "st", "sn", "sd", "si", "sk", "sl", "so", "es", "su", "sw", "sv", "tl", "tg", "ta", "tt",
|
||||
"te", "th", "tr", "tk", "uk", "ur", "ug", "uz", "vi", "cy", "fy", "xh", "yi", "yo", "zu"
|
||||
]
|
||||
|
||||
# Alternative: More focused list of commonly used languages for fallback
|
||||
COMMON_FALLBACK_LANGUAGES = [
|
||||
"en", "en-US", "en-GB", # English variants
|
||||
"de", "fr", "es", "it", "pt", # Major European languages
|
||||
"ru", "ja", "ko", "zh", "zh-Hant", # Major Asian languages
|
||||
"ar", "hi", "bn", "pa", # Major world languages
|
||||
"tr", "nl", "pl", "sv", "da", "fi", "no", # Nordic/Scandinavian
|
||||
"cs", "sk", "hu", "ro", "bg", "hr", "sl", "pl", "lt", "lv", "et" # Eastern European
|
||||
]
|
||||
ENGLISH_LANGUAGES = ['en', 'en-US', 'en-GB']
|
||||
# This can be used as the list of allowed fallback languages
|
||||
ALLOWED_FALLBACK_LANGUAGES = COMMON_FALLBACK_LANGUAGES
|
||||
|
||||
if __name__ == "__main__":
|
||||
print("YouTube Language Codes:")
|
||||
print(f"Total codes: {len(YOUTUBE_LANGUAGE_CODES)}")
|
||||
print("First 10:", YOUTUBE_LANGUAGE_CODES[:10])
|
||||
print()
|
||||
print("Common fallback languages:")
|
||||
print(f"Total fallback codes: {len(ALLOWED_FALLBACK_LANGUAGES)}")
|
||||
print("Fallback codes:", ALLOWED_FALLBACK_LANGUAGES)
|
||||
Reference in New Issue
Block a user