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archiving community contributions on YouTube: unpublished captions, title and description translations and caption credits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.
111 Commits
7 Branches
243 KiB
 
 
Tag: afcdd991fa
Branches Tags
${ item.name }
Criar branch ${ searchTerm }
de afcdd991fa
${ noResults }
ytcc-archive/discovery.py

141 linhas
12 KiB
Original Anotar Histórico 

  1. from time import sleep

  2. from typing import Dict

  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(mysession, vid):

  8.     params = (

  9.         ("v", vid),

  10.     )

  11. 

  12.     while True:

  13.         wpage = mysession.get("https://www.youtube.com/watch", params=params)

  14.         if not """</div><div id="content" class="  content-alignment" role="main"><p class='largeText'>Sorry for the interruption. We have been receiving a large volume of requests from your network.</p>

  15. 

  16. <p>To continue with your YouTube experience, please fill out the form below.</p>""" in wpage.text and not wpage.status_code == 429:

  17.             break

  18.         else:

  19.             print("Captcha detected, waiting 30 seconds")

  20.             sleep(30)

  21. 

  22.     wptext = wpage.text

  23. 

  24.     initplay = None

  25.     initdata = None

  26. 

  27.     recvids  = set()

  28.     recchans = set()

  29.     recmixes = set()

  30.     recplayl = set()

  31. 

  32.     ccenabled = False #default values

  33.     creditdata = {}

  34. 

  35.     for line in wptext.splitlines():

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

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

  38. 

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

  40.                 print(vid, "unavailable")

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

  42.             

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

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

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

  46. 

  47.                         if type(el) == Dict:

  48.                             elint = el["endscreenElementRenderer"]

  49. 

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

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

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

  53. 

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

  55.                                     try:

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

  57.                                     except:

  58.                                         print("Channel endscreen error")

  59.                                         raise

  60. 

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

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

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

  64. 

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

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

  67.             else:

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

  69. 

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

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

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

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

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

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

  76.                 try:

  77.                     if "results" in initdata["contents"]["twoColumnWatchNextResults"]["secondaryResults"]["secondaryResults"].keys():

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

  79.                             #auto is like the others

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

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

  82. 

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

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

  85.                                 try:

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

  87.                                 except KeyError as e:

  88.                                     try:

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

  90.                                     except KeyError as e:

  91.                                         print("Channel extract error")

  92.                                     #raise

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

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

  95. 

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

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

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

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

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

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

  102. 

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

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

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

  106.                 except BaseException as e:

  107.                     print(e)

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

  109. 

  110.             creditdata = {}

  111.             try:

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

  113.                 for item in mdinfo:

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

  115.                         try:

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

  117.                         except KeyError as e:

  118.                             #print(e)

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

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

  121.                         creditdata[desl] = []

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

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

  124. 

  125.             except KeyError as e:

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

  127.                 pass

  128.                 #raise

  129.                 #print(e)

  130.         

  131.         if initplay and initdata:

  132.             break

  133. 

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

  135. 

  136. if __name__ == "__main__":

  137.     from sys import argv

  138.     vidl = argv

  139.     vidl.pop(0)

  140.     for video in vidl:

  141.         print(getmetadata(video))