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archiving community contributions on YouTube: unpublished captions, title and description translations and caption credits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.
73 Commits
7 Branches
545 KiB
 
 
Tag: 249c431a89
Branches Tags
${ item.name }
Criar branch ${ searchTerm }
de 249c431a89
${ noResults }
ytcc-archive/discovery.py

135 linhas
11 KiB
Original Anotar Histórico 

  1. from typing import Dict

  2. import requests

  3. from json import loads

  4. 

  5. 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"}

  6. 

  7. def getmetadata(vid):

  8.     params = (

  9.         ("v", vid),

  10.     )

  11. 

  12.     headers = {

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

  14.     }

  15. 

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

  17. 

  18.     wptext = wpage.text

  19. 

  20.     initplay = None

  21.     initdata = None

  22. 

  23.     recvids  = set()

  24.     recchans = set()

  25.     recmixes = set()

  26.     recplayl = set()

  27. 

  28.     ccenabled = False #default values

  29.     creditdata = {}

  30. 

  31.     for line in wptext.splitlines():

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

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

  34. 

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

  36.                 print(vid, "unavailable")

  37.                 return False, {}, recvids, recchans, recmixes, recplayl

  38.             

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

  40.                 if "endscreenRenderer" in initplay["endscreen"].keys():

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

  42. 

  43.                         if type(el) == Dict:

  44.                             elint = el["endscreenElementRenderer"]

  45. 

  46.                             if "endscreenElementRenderer" in el.keys():

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

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

  49. 

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

  51.                                     try:

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

  53.                                     except:

  54.                                         print("Channel endscreen error")

  55.                                         raise

  56. 

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

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

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

  60. 

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

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

  63.             else:

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

  65. 

  66.             if "videoDetails" in initplay.keys():

  67.                 if "channelId" in initplay["videoDetails"].keys():

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

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

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

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

  72.                 try:

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

  74.                         #auto is like the others

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

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

  77. 

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

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

  80.                             try:

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

  82.                             except KeyError as e:

  83.                                 try:

  84.                                     recchans.add(recmd["compactVideoRenderer"]["longBylineText"]["runs"][0]["navigationEndpoint"]["browseEndpoint"]["browseId"])

  85.                                 except KeyError as e:

  86.                                     print("Channel extract error")

  87.                                 #raise

  88.                                 #print("Unable to extract channel:")

  89.                                 #print(recmd["compactVideoRenderer"])

  90. 

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

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

  93.                             if "navigationEndpoint" in recmd["compactPlaylistRenderer"].keys():

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

  95.                             if "navigationEndpoint" in recmd["compactPlaylistRenderer"]["shortBylineText"].keys():

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

  97. 

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

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

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

  101.                 except:

  102.                     print("Exception in discovery, continuing anyway")

  103. 

  104.             creditdata = {}

  105.             try:

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

  107.                 for item in mdinfo:

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

  109.                         try:

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

  111.                         except KeyError as e:

  112.                             #print(e)

  113.                             print("Language code conversion error, using language name")

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

  115.                         creditdata[desl] = []

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

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

  118. 

  119.             except KeyError as e:

  120.                 #print("Video does not have credits")

  121.                 pass

  122.                 #raise

  123.                 #print(e)

  124.         

  125.         if initplay and initdata:

  126.             break

  127. 

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

  129. 

  130. if __name__ == "__main__":

  131.     from sys import argv

  132.     vidl = argv

  133.     vidl.pop(0)

  134.     for video in vidl:

  135.         print(getmetadata(video))