tech234a
/
ytcc-archive
miroir de https://github.com/Data-Horde/ytcc-archive
1
0
Bifurcation 0
Code Tickets 0 Versions 0 Wiki Activité
archiving community contributions on YouTube: unpublished captions, title and description translations and caption credits
Vous ne pouvez pas sélectionner plus de 25 sujets Les noms de sujets doivent commencer par une lettre ou un nombre, peuvent contenir des tirets ('-') et peuvent comporter jusqu'à 35 caractères.
12 Révisions
7 Branches
323 KiB
 
 
Aborescence: 22ca4edb30
Branches Tags
${ item.name }
Créer la branche ${ searchTerm }
de '22ca4edb30'
${ noResults }
ytcc-archive/discovery.py

108 lignes
9.6 KiB
Brut Annotations Historique 

  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.                         try:

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

  68.                         except KeyError as e:

  69.                             print("Unable to extract channel:")

  70.                             print(recmd["compactVideoRenderer"])

  71. 

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

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

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

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

  76. 

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

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

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

  80. 

  81.             creditdata = {}

  82.             try:

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

  84.                 for item in mdinfo:

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

  86.                         try:

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

  88.                         except KeyError as e:

  89.                             print(e)

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

  91.                         creditdata[desl] = []

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

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

  94. 

  95.             except KeyError as e:

  96.                 print(e)

  97.         

  98.         if initplay and initdata:

  99.             break

  100. 

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

  102. 

  103. if __name__ == "__main__":

  104.     from sys import argv

  105.     vidl = argv

  106.     vidl.pop(0)

  107.     for video in vidl:

  108.         print(getmetadata(video))