tech234a
/
ytcc-archive
espelhamento de https://github.com/Data-Horde/ytcc-archive
1
0
Fork 0
Código Issues 0 Versões 0 Wiki Atividade
archiving community contributions on YouTube: unpublished captions, title and description translations and caption credits
Você não pode selecionar mais de 25 tópicos Os tópicos devem começar com uma letra ou um número, podem incluir traços ('-') e podem ter até 35 caracteres.
6 Commits
7 Branches
545 KiB
 
 
Tag: fa440e5f7b
Branches Tags
${ item.name }
Criar branch ${ searchTerm }
de fa440e5f7b
${ noResults }
ytcc-archive/discovery.py

104 linhas
9.4 KiB
Original Anotar Histórico 

  1. import requests

  2. from json import loads

  3. 

  4. langcodes = {"Afar": "aa", "Abkhazian": "ab", "Afrikaans": "af", "Akan": "ak", "all": "all", "Amharic": "am", "Aragonese": "an", "Arabic": "ar", "Aramaic": "arc", "Algerian Arabic": "arq", "Assamese": "as", "American Sign Language": "ase", "Asturian": "ast", "Avaric": "av", "Aymara": "ay", "Azerbaijani": "az", "Bashkir": "ba", "Belarusian": "be", "Bulgarian": "bg", "Bihari": "bh", "Bislama": "bi", "Bangla": "bn", "Tibetan": "bo", "Breton": "br", "Bosnian": "bs", "Catalan": "ca", "Cebuano": "ceb", "Choctaw": "cho", "Cherokee": "chr", "Corsican": "co", "Czech": "cs", "Church Slavic": "cu", "Welsh": "cy", "Danish": "da", "Danish (Denmark)": "da-DK", "German": "de", "German (Austria)": "de-AT", "German (Switzerland)": "de-CH", "German (Germany)": "de-DE", "Divehi": "dv", "Dzongkha": "dz", "Ewe": "ee", "Greek": "el", "English": "en", "English (United Arab Emirates)": "en-AE", "English (Canada)": "en-CA", "English (United Kingdom)": "en-GB", "English (Ireland)": "en-IE", "English (India)": "en-IN", "English (United States)": "en-US", "Esperanto": "eo", "Spanish": "es", "Spanish (Latin America)": "es-419", "Spanish (Argentina)": "es-AR", "Spanish (Chile)": "es-CL", "Spanish (Colombia)": "es-CO", "Spanish (Costa Rica)": "es-CR", "Spanish (Spain)": "es-ES", "Spanish (Mexico)": "es-MX", "Spanish (Nicaragua)": "es-NI", "Spanish (United States)": "es-US", "Estonian": "et", "Basque": "eu", "Persian": "fa", "Persian (Afghanistan)": "fa-AF", "Persian (Iran)": "fa-IR", "Fulah": "ff", "Finnish": "fi", "Filipino": "fil", "Fijian": "fj", "Faroese": "fo", "French": "fr", "French (Belgium)": "fr-BE", "French (Canada)": "fr-CA", "French (Switzerland)": "fr-CH", "French (France)": "fr-FR", "Western Frisian": "fy", "Irish": "ga", "Scottish Gaelic": "gd", "Galician": "gl", "Guarani": "gn", "Swiss German": "gsw", "Gujarati": "gu", "Hausa": "ha", "Hakka Chinese": "hak", "Hakka Chinese (Taiwan)": "hak-TW", "Hindi": "hi-Latn", "Hmong": "hmn", "Croatian": "hr", "Haitian Creole": "ht", "Hungarian": "hu", "Armenian": "hy", "Interlingua": "ia", "Indonesian": "id", "Interlingue": "ie", "Igbo": "ig", "Sichuan Yi": "ii", "Inupiaq": "ik", "Icelandic": "is", "Italian": "it", "Italian (Italy)": "it-IT", "Inuktitut": "iu", "Hebrew": "iw", "Japanese": "ja", "Javanese": "jv", "Georgian": "ka", "Kazakh": "kk", "Kalaallisut": "kl", "Khmer": "km", "Kannada": "kn", "Korean": "ko", "Korean (South Korea)": "ko-KR", "Kanuri": "kr", "Kashmiri": "ks", "Kurdish": "ku", "Kyrgyz": "ky", "Latin": "la", "Luxembourgish": "lb", "Lingala": "ln", "Lao": "lo", "Lithuanian": "lt", "Mizo": "lus", "Latvian": "lv", "Masai": "mas", "Malagasy": "mg", "Maori": "mi", "Miscellaneous languages": "mis", "Macedonian": "mk", "Malayalam": "ml", "Mongolian": "mn", "Manipuri": "mni", "Moldavian": "mo", "Marathi": "mr", "Malay": "ms", "Maltese": "mt", "Burmese": "my", "Nauru": "na", "Min Nan Chinese": "nan", "Min Nan Chinese (Taiwan)": "nan-TW", "Nepali": "ne", "Dutch": "nl", "Dutch (Belgium)": "nl-BE", "Dutch (Netherlands)": "nl-NL", "Norwegian Nynorsk": "nn", "Norwegian": "no", "not": "not", "Navajo": "nv", "Occitan": "oc", "Oromo": "om", "Odia": "or", "Punjabi": "pa", "Polish": "pl", "Polish (Poland)": "pl-PL", "Pashto": "ps", "Portuguese": "pt", "Portuguese (Brazil)": "pt-BR", "Portuguese (Portugal)": "pt-PT", "Quechua": "qu", "Romansh": "rm", "Rundi": "rn", "Romanian": "ro", "Romanian (Moldova)": "ro-MD", "Russian": "ru-Latn", "Russian (Russia)": "ru-RU", "Kinyarwanda": "rw", "Sanskrit": "sa", "Sardinian": "sc", "Sicilian": "scn", "Scots": "sco", "Sindhi": "sd", "Sherdukpen": "sdp", "Northern Sami": "se", "Sango": "sg", "Serbo-Croatian": "sh", "Sinhala": "si", "Slovak": "sk", "Slovenian": "sl", "Samoan": "sm", "Shona": "sn", "Somali": "so", "Albanian": "sq", "Serbian": "sr", "Serbian (Cyrillic)": "sr-Cyrl", "Serbian (Latin)": "sr-Latn", "Swati": "ss", "Southern Sotho": "st", "Sundanese": "su", "Swedish": "sv", "Swahili": "sw", "Tamil": "ta", "Telugu": "te", "Tajik": "tg", "Thai": "th", "Tigrinya": "ti", "Turkmen": "tk", "Tagalog": "tl", "Klingon": "tlh", "Tswana": "tn", "Tongan": "to", "Turkish": "tr", "Turkish (Turkey)": "tr-TR", "Tsonga": "ts", "Tatar": "tt", "Twi": "tw", "Ukrainian": "uk", "Urdu": "ur", "Uzbek": "uz", "Vietnamese": "vi", "Volap\\xFCk": "vo", "Wolof": "wo", "Xhosa": "xh", "Yiddish": "yi", "Yoruba": "yo", "Cantonese": "yue", "Cantonese (Hong Kong)": "yue-HK", "Chinese": "zh", "Chinese (China)": "zh-CN", "Chinese (Hong Kong)": "zh-HK", "Chinese (Simplified)": "zh-Hans", "Chinese (Simplified, China)": "zh-Hans-CN", "Chinese (Simplified, Singapore)": "zh-Hans-SG", "Chinese (Traditional)": "zh-Hant", "Chinese (Traditional, Hong Kong)": "zh-Hant-HK", "Chinese (Traditional, Taiwan)": "zh-Hant-TW", "Chinese (Singapore)": "zh-SG", "Chinese (Taiwan)": "zh-TW", "Zulu": "zu", "Hiri Motu": "ho", "Tok Pisin": "tpi", "Voro": "vor"}

  5. 

  6. def getmetadata(vid):

  7.     params = (

  8.         ("v", vid),

  9.     )

  10. 

  11.     headers = {

  12.         "Accept-Language": "en-US",

  13.     }

  14. 

  15.     wpage = requests.get("https://www.youtube.com/watch", headers=headers, params=params)

  16. 

  17.     wptext = wpage.text

  18. 

  19.     initplay = None

  20.     initdata = None

  21. 

  22.     recvids  = set()

  23.     recchans = set()

  24.     recmixes = set()

  25.     recplayl = set()

  26. 

  27.     for line in wptext.splitlines():

  28.         if line.strip().startswith('window["ytInitialPlayerResponse"] = '):

  29.             initplay = loads(line.split('window["ytInitialPlayerResponse"] = ', 1)[1].strip()[:-1])

  30. 

  31.             if initplay["playabilityStatus"]["status"] == "ERROR":

  32.                 print(vid, "unavailable")

  33.                 return False, recvids, recchans, recmixes, recplayl

  34.             

  35.             if "endscreen" in initplay.keys():

  36.                 for el in initplay["endscreen"]["endscreenRenderer"]:

  37. 

  38.                     elint = el["endscreenElementRenderer"]

  39. 

  40.                     if elint["style"] == "VIDEO":

  41.                         recvids.add(elint["endpoint"]["watchEndpoint"]["videoId"])

  42. 

  43.                     elif elint["style"] == "CHANNEL":

  44.                         recchans.add(elint["endpoint"]["browseEndpoint"]["browseId"])

  45. 

  46.                     elif elint["style"] == "PLAYLIST":

  47.                         recvids.add(elint["endpoint"]["watchEndpoint"]["videoId"])

  48.                         recplayl.add(elint["endpoint"]["watchEndpint"]["playlistId"])

  49. 

  50.             if "captions" in initplay.keys():

  51.                 ccenabled = "contribute" in initplay["captions"]["playerCaptionsRenderer"]

  52.             else:

  53.                 ccenabled = False # if captions information is not present, community contributions are not enabled

  54. 

  55.             recchans.add(initplay["videoDetails"]["channelId"])

  56.         elif line.strip().startswith('window["ytInitialData"] = '):

  57.             initdata = loads(line.split('window["ytInitialData"] = ', 1)[1].strip()[:-1])

  58.             if "contents" in initdata.keys(): #prevent exception

  59.                 for recmd in initdata["contents"]["twoColumnWatchNextResults"]["secondaryResults"]["secondaryResults"]["results"]:

  60.                     #auto is like the others

  61.                     if "compactAutoplayRenderer" in recmd.keys():

  62.                         recmd = recmd["compactAutoplayRenderer"]["contents"][0]

  63. 

  64.                     if "compactVideoRenderer" in recmd.keys():

  65.                         recvids.add(recmd["compactVideoRenderer"]["videoId"])

  66.                         recchans.add(recmd["compactVideoRenderer"]["channelId"])

  67. 

  68.                     elif "compactPlaylistRenderer" in recmd.keys():

  69.                         recplayl.add(recmd["compactPlaylistRenderer"]["playlistId"])

  70.                         recvids.add(recmd["compactPlaylistRenderer"]["navigationEndpoint"]["watchEndpoint"]["videoId"])

  71.                         recchans.add(recmd["compactPlaylistRenderer"]["shortBylineText"]["navigationEndpoint"]["browseEndpoint"]["browseId"])

  72. 

  73.                     elif "compactRadioRenderer" in recmd.keys(): #mix playlist

  74.                         recmixes.add(recmd["compactRadioRenderer"]["playlistId"])

  75.                     # todo: find out if channels can be suggested

  76. 

  77.             creditdata = {}

  78.             try:

  79.                 mdinfo = initdata["contents"]["twoColumnWatchNextResults"]["results"]["results"]["contents"][1]["videoSecondaryInfoRenderer"]["metadataRowContainer"]["metadataRowContainerRenderer"]["rows"]

  80.                 for item in mdinfo:

  81.                     if item["metadataRowRenderer"]["title"]["simpleText"].startswith("Caption author"): #the request to /watch needs to be in English for this to work

  82.                         try:

  83.                             desl = langcodes[item["metadataRowRenderer"]["title"]["simpleText"].split("(", 1)[1][:-1]]

  84.                         except KeyError as e:

  85.                             print(e)

  86.                             desl = item["metadataRowRenderer"]["title"]["simpleText"].split("(", 1)[1][:-1]

  87.                         creditdata[desl] = []

  88.                         for itemint in item["metadataRowRenderer"]["contents"]:

  89.                             creditdata[desl].append({"name": itemint["runs"][0]["text"], "channel": itemint["runs"][0]["navigationEndpoint"]["browseEndpoint"]["browseId"]})

  90. 

  91.             except KeyError as e:

  92.                 print(e)

  93.         

  94.         if initplay and initdata:

  95.             break

  96. 

  97.     return ccenabled, creditdata, recvids, recchans, recmixes, recplayl

  98. 

  99. if __name__ == "__main__":

  100.     from sys import argv

  101.     vidl = argv

  102.     vidl.pop(0)

  103.     for video in vidl:

  104.         print(getmetadata(video))