tech234a
/
ytcc-archive
mirror of https://github.com/Data-Horde/ytcc-archive
1
0
Fork 0
Code Issues 0 Releases 0 Wiki Activity
archiving community contributions on YouTube: unpublished captions, title and description translations and caption credits
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
130 Commits
7 Branches
182 KiB
 
 
Branch: halt-discovery
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'halt-discovery'
${ noResults }
ytcc-archive/discovery.py

163 lines
14 KiB
Raw Permalink Blame History 

  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, ccenabledonly=False):

  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 and 'window["ytInitialPlayerResponse"] = ' in wpage.text and 'window["ytInitialData"] = ' in wpage.text:

  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 not ccenabledonly:

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

  41.                     print(vid, "unavailable")

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

  43.                 

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

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

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

  47. 

  48.                             if type(el) == Dict:

  49.                                 elint = el["endscreenElementRenderer"]

  50. 

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

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

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

  54. 

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

  56.                                         try:

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

  58.                                         except:

  59.                                             print("Channel endscreen error")

  60.                                             raise

  61. 

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

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

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

  65. 

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

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

  68.             else:

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

  70. 

  71.             if not ccenabledonly:

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

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

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

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

  76.             if not ccenabledonly:

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

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

  79.                     try:

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

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

  82.                                 #auto is like the others

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

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

  85. 

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

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

  88.                                     try:

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

  90.                                     except KeyError as e:

  91.                                         try:

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

  93.                                         except KeyError as e:

  94.                                             print("Channel extract error")

  95.                                         #raise

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

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

  98. 

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

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

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

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

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

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

  105. 

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

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

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

  109.                     except BaseException as e:

  110.                         print(e)

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

  112. 

  113.             creditdata = {}

  114. 

  115.             if not ccenabledonly:

  116.                 try:

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

  118.                     for item in mdinfo:

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

  120.                             try:

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

  122.                             except KeyError as e:

  123.                                 #print(e)

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

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

  126.                             creditdata[desl] = []

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

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

  129. 

  130.                 except KeyError as e:

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

  132.                     pass

  133.                     #raise

  134.                     #print(e)

  135.         

  136.         if initplay and (initdata or ccenabledonly):

  137.             break

  138. 

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

  140. 

  141. if __name__ == "__main__":

  142.     from sys import argv

  143.     from requests import session

  144.     from os.path import isfile

  145.     from os import environ

  146.     mysession = session()

  147.     #HSID, SSID, SID cookies required

  148.     if "HSID" in environ.keys() and "SSID" in environ.keys() and "SID" in environ.keys():

  149.         cookies = {"HSID": environ["HSID"], "SSID": environ["SSID"], "SID": environ["SID"]}

  150.     elif isfile("config.json"):

  151.         cookies = loads(open("config.json").read())

  152.     else:

  153.         print("HSID, SSID, and SID cookies from youtube.com are required. Specify in config.json or as environment variables.")

  154.         assert False

  155.     if not (cookies["HSID"] and cookies["SSID"] and cookies["SID"]):

  156.         print("HSID, SSID, and SID cookies from youtube.com are required. Specify in config.json or as environment variables.")

  157.         assert False

  158. 

  159.     mysession.headers.update({"cookie": "HSID="+cookies["HSID"]+"; SSID="+cookies["SSID"]+"; SID="+cookies["SID"], "Accept-Language": "en-US",})

  160.     vidl = argv

  161.     vidl.pop(0)

  162.     for video in vidl:

  163.         print(getmetadata(mysession, video))