@@ -2,22 +2,32 @@ from time import sleep | |||
from typing import Dict | |||
from json import loads | |||
from switchable_request import get | |||
backend = "http3" | |||
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"} | |||
def getmetadata(mysession, vid): | |||
def getmetadata(mysession, vid, allheaders): | |||
global backend | |||
params = ( | |||
("v", vid), | |||
) | |||
while True: | |||
wpage = mysession.get("https://www.youtube.com/watch", params=params) | |||
wpage = get("https://www.youtube.com/watch", params=params, mysession=mysession, backend=backend, http3headers=allheaders) | |||
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> | |||
<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: | |||
break | |||
else: | |||
print("Captcha detected, waiting 30 seconds") | |||
sleep(30) | |||
if backend == "requests": | |||
backend = "http3" | |||
print("Captcha detected, switching discovery to HTTP3/QUIC") | |||
else: | |||
print("Captcha detected, waiting 30 seconds") | |||
sleep(30) | |||
wptext = wpage.text | |||
@@ -38,6 +38,10 @@ from time import sleep | |||
# https://docs.python.org/3/library/html.parser.html | |||
from html.parser import HTMLParser | |||
backend = "http3" | |||
from switchable_request import get | |||
class MyHTMLParser(HTMLParser): | |||
def __init__(self): | |||
HTMLParser.__init__(self) | |||
@@ -79,7 +83,8 @@ class MyHTMLParser(HTMLParser): | |||
elif self.get_starttag_text() and self.get_starttag_text().startswith('<div id="original-video-title"'): | |||
self.inittitle += data | |||
def subprrun(mysession, langcode, vid, mode, needforcemetadata, needforcecaptions): | |||
def subprrun(mysession, langcode, vid, mode, needforcemetadata, needforcecaptions, allheaders): | |||
global backend | |||
if mode == "forceedit-metadata": | |||
while needforcemetadata[langcode] == None: #extra logic | |||
print("Awaiting forcemetadata") | |||
@@ -114,7 +119,7 @@ def subprrun(mysession, langcode, vid, mode, needforcemetadata, needforcecaption | |||
("o", "U") | |||
) | |||
page = mysession.get("https://www.youtube.com/timedtext_editor", params=pparams) | |||
page = get("https://www.youtube.com/timedtext_editor", params=pparams, mysession=mysession, backend=backend, http3headers=allheaders) | |||
elif mode == "forceedit-metadata": | |||
pparams = ( | |||
("v", vid), | |||
@@ -124,7 +129,7 @@ def subprrun(mysession, langcode, vid, mode, needforcemetadata, needforcecaption | |||
('tab', 'metadata') | |||
) | |||
page = mysession.get("https://www.youtube.com/timedtext_editor", params=pparams) | |||
page = get("https://www.youtube.com/timedtext_editor", params=pparams, mysession=mysession, backend=backend, http3headers=allheaders) | |||
elif mode == "forceedit-captions": | |||
pparams = ( | |||
("v", vid), | |||
@@ -137,13 +142,17 @@ def subprrun(mysession, langcode, vid, mode, needforcemetadata, needforcecaption | |||
("o", "U") | |||
) | |||
page = mysession.get("https://www.youtube.com/timedtext_editor", params=pparams) | |||
page = get("https://www.youtube.com/timedtext_editor", params=pparams, mysession=mysession, backend=backend, http3headers=allheaders) | |||
if not "accounts.google.com" in page.url and page.status_code != 429 and 'Subtitles/CC' in page.text and 'Title & description' in page.text: | |||
break | |||
else: | |||
print("[Retrying in 30 seconds for rate limit or login failure] Please supply authentication cookie information in config.json or environment variables. See README.md for more information.") | |||
sleep(30) | |||
if backend == "requests": | |||
backend = "http3" | |||
print("Rate limit or login failure, switching export to HTTP3/QUIC...") | |||
else: | |||
print("[Retrying in 30 seconds for rate limit or login failure] Please supply authentication cookie information in config.json or environment variables. See README.md for more information.") | |||
sleep(30) | |||
except: | |||
print("Error in request, retrying in 5 seconds...") | |||
sleep(5) | |||
@@ -0,0 +1,54 @@ | |||
import asyncio | |||
from typing import cast | |||
from urllib.parse import urlparse | |||
from aioquic.h3.connection import H3_ALPN | |||
from aioquic.asyncio.client import connect | |||
from aioquic.quic.configuration import QuicConfiguration | |||
from http3_base import HttpClient, prepare_response, perform_http_request | |||
class HTTP3Response: | |||
def __init__(self, input) -> None: | |||
headers, content = input | |||
self.content = content | |||
try: | |||
self.text = content.decode() | |||
except: | |||
print("Text decoding error") | |||
self.text = "" | |||
self.headers = {} | |||
for k, v in headers.items(): | |||
self.headers[k.decode()] = v.decode() | |||
try: | |||
self.status_code = int(headers[b":status"]) | |||
except: | |||
print("Status code not included as header, defaulting to 200") | |||
self.status_code = 200 | |||
self.ok = self.status_code < 400 | |||
async def main(address, headers={}): | |||
parsed = urlparse(address) | |||
configuration = QuicConfiguration( | |||
is_client=True, alpn_protocols=H3_ALPN | |||
) | |||
async with connect(parsed.netloc, port=443, configuration=configuration, create_protocol=HttpClient) as client: | |||
client = cast(HttpClient, client) | |||
events = await perform_http_request(client=client, url=address, headers=headers) | |||
return HTTP3Response(prepare_response(events)) | |||
def get(url, headers={}, params={}): | |||
plist = [] | |||
for item in params: | |||
#print(item) | |||
k, v = item | |||
plist.append(str(k)+"="+str(v)) | |||
if plist: | |||
pstring = "?"+"&".join(plist) | |||
else: | |||
pstring = "" | |||
#print(url+pstring) | |||
loop = asyncio.new_event_loop() | |||
return loop.run_until_complete(main(url+pstring, headers=headers)) |
@@ -0,0 +1,158 @@ | |||
import asyncio | |||
import logging | |||
import time | |||
from collections import deque | |||
from typing import Deque, Dict, Optional | |||
from urllib.parse import urlparse | |||
import aioquic | |||
from aioquic.asyncio.protocol import QuicConnectionProtocol | |||
from aioquic.h3.connection import H3Connection | |||
from aioquic.h3.events import ( | |||
DataReceived, | |||
H3Event, | |||
HeadersReceived, | |||
PushPromiseReceived, | |||
) | |||
from aioquic.quic.events import QuicEvent | |||
logger = logging.getLogger("client") | |||
USER_AGENT = "aioquic/" + aioquic.__version__ | |||
class URL: | |||
def __init__(self, url: str) -> None: | |||
parsed = urlparse(url) | |||
self.authority = parsed.netloc | |||
self.full_path = parsed.path | |||
if parsed.query: | |||
self.full_path += "?" + parsed.query | |||
self.scheme = parsed.scheme | |||
class HttpRequest: | |||
def __init__( | |||
self, method: str, url: URL, content: bytes = b"", headers: Dict = {} | |||
) -> None: | |||
self.content = content | |||
self.headers = headers | |||
self.method = method | |||
self.url = url | |||
class HttpClient(QuicConnectionProtocol): | |||
def __init__(self, *args, **kwargs) -> None: | |||
super().__init__(*args, **kwargs) | |||
self.pushes: Dict[int, Deque[H3Event]] = {} | |||
self._request_events: Dict[int, Deque[H3Event]] = {} | |||
self._request_waiter: Dict[int, asyncio.Future[Deque[H3Event]]] = {} | |||
self._http = H3Connection(self._quic) | |||
async def get(self, url: str, headers: Dict = {}) -> Deque[H3Event]: | |||
""" | |||
Perform a GET request. | |||
""" | |||
return await self._request( | |||
HttpRequest(method="GET", url=URL(url), headers=headers) | |||
) | |||
async def post(self, url: str, data: bytes, headers: Dict = {}) -> Deque[H3Event]: | |||
""" | |||
Perform a POST request. | |||
""" | |||
return await self._request( | |||
HttpRequest(method="POST", url=URL(url), content=data, headers=headers) | |||
) | |||
def http_event_received(self, event: H3Event) -> None: | |||
if isinstance(event, (HeadersReceived, DataReceived)): | |||
stream_id = event.stream_id | |||
if stream_id in self._request_events: | |||
# http | |||
self._request_events[event.stream_id].append(event) | |||
if event.stream_ended: | |||
request_waiter = self._request_waiter.pop(stream_id) | |||
request_waiter.set_result(self._request_events.pop(stream_id)) | |||
elif event.push_id in self.pushes: | |||
# push | |||
self.pushes[event.push_id].append(event) | |||
elif isinstance(event, PushPromiseReceived): | |||
self.pushes[event.push_id] = deque() | |||
self.pushes[event.push_id].append(event) | |||
def quic_event_received(self, event: QuicEvent) -> None: | |||
# pass event to the HTTP layer | |||
if self._http is not None: | |||
for http_event in self._http.handle_event(event): | |||
self.http_event_received(http_event) | |||
async def _request(self, request: HttpRequest) -> Deque[H3Event]: | |||
stream_id = self._quic.get_next_available_stream_id() | |||
self._http.send_headers( | |||
stream_id=stream_id, | |||
headers=[ | |||
(b":method", request.method.encode()), | |||
(b":scheme", request.url.scheme.encode()), | |||
(b":authority", request.url.authority.encode()), | |||
(b":path", request.url.full_path.encode()), | |||
(b"user-agent", USER_AGENT.encode()), | |||
] | |||
+ [(k.lower().encode(), v.encode()) for (k, v) in request.headers.items()], | |||
) | |||
self._http.send_data(stream_id=stream_id, data=request.content, end_stream=True) | |||
waiter = self._loop.create_future() | |||
self._request_events[stream_id] = deque() | |||
self._request_waiter[stream_id] = waiter | |||
self.transmit() | |||
return await asyncio.shield(waiter) | |||
async def perform_http_request( | |||
client: HttpClient, | |||
url: str, | |||
headers: Optional[dict] | |||
) -> Dict[int, Deque[H3Event]] : | |||
# perform request | |||
start = time.time() | |||
if headers: | |||
http_events = await client.get(url, headers=headers) | |||
else: | |||
http_events = await client.get(url) | |||
method = "GET" | |||
elapsed = time.time() - start | |||
# print speed | |||
octets = 0 | |||
for http_event in http_events: | |||
if isinstance(http_event, DataReceived): | |||
octets += len(http_event.data) | |||
logger.info( | |||
"Response received for %s %s : %d bytes in %.1f s (%.3f Mbps)" | |||
% (method, urlparse(url).path, octets, elapsed, octets * 8 / elapsed / 1000000) | |||
) | |||
return http_events | |||
def prepare_response( | |||
http_events: Deque[H3Event] | |||
) -> str: | |||
byteslist = [] | |||
headers = {} | |||
for http_event in http_events: | |||
if isinstance(http_event, HeadersReceived): | |||
headers.update(http_event.headers) | |||
elif isinstance(http_event, DataReceived): | |||
byteslist.append(http_event.data) | |||
return headers, b''.join(byteslist) |
@@ -1,4 +1,5 @@ | |||
requests | |||
beautifulsoup4 | |||
html5lib | |||
youtube_dl | |||
youtube_dl | |||
aioquic |
@@ -0,0 +1,7 @@ | |||
import http3 | |||
def get(url: str, params: tuple = (), backend="requests", mysession=None, http3headers: dict ={}): | |||
if backend == "requests": | |||
return mysession.get(url, params) | |||
elif backend == "http3": | |||
#print(http3headers) | |||
return http3.get(url, headers=http3headers, params=params) |
@@ -9,7 +9,7 @@ from os.path import isfile | |||
from json import loads | |||
# https://github.com/ArchiveTeam/tencent-weibo-grab/blob/9bae5f9747e014db9227821a9c11557267967023/pipeline.py | |||
VERSION = "20200924.07" | |||
VERSION = "20200924.10" | |||
TRACKER_ID = "ext-yt-communitycontribs" | |||
TRACKER_HOST = "trackerproxy.meo.ws" | |||
@@ -64,6 +64,7 @@ if not (cookies["HSID"] and cookies["SSID"] and cookies["SID"]): | |||
assert False | |||
mysession = requests.session() | |||
allheaders = {"cookie": "HSID="+cookies["HSID"]+"; SSID="+cookies["SSID"]+"; SID="+cookies["SID"], "Accept-Language": "en-US",} | |||
mysession.headers.update({"cookie": "HSID="+cookies["HSID"]+"; SSID="+cookies["SSID"]+"; SID="+cookies["SID"], "Accept-Language": "en-US",}) | |||
validationtest = mysession.get("https://www.youtube.com/timedtext_editor?action_mde_edit_form=1&v=1iNTtHUwvq4&lang=en&bl=vmp&ui=hd&ref=player&tab=captions&o=U") | |||
@@ -109,11 +110,12 @@ def threadrunner(): | |||
elif task == "discovery": | |||
while True: | |||
try: | |||
info = getmetadata(mysession, str(vid).strip()) | |||
info = getmetadata(mysession, str(vid).strip(), allheaders) | |||
break | |||
except BaseException as e: | |||
print(e) | |||
print("Error in retrieving information, waiting 30 seconds and trying again") | |||
#raise | |||
sleep(30) | |||
if info[0] or info[1]: # ccenabled or creditdata | |||
if not isdir("out/"+str(vid).strip()): | |||
@@ -143,11 +145,11 @@ def threadrunner(): | |||
jobs.put(("submitdiscovery", playldisc, tracker.ItemType.Playlist)) | |||
elif task == "subtitles": | |||
subprrun(mysession, args, vid, "default", needforcemetadata, needforcecaptions) | |||
subprrun(mysession, args, vid, "default", needforcemetadata, needforcecaptions, allheaders) | |||
elif task == "subtitles-forceedit-captions": | |||
subprrun(mysession, args, vid, "forceedit-captions", needforcemetadata, needforcecaptions) | |||
subprrun(mysession, args, vid, "forceedit-captions", needforcemetadata, needforcecaptions, allheaders) | |||
elif task == "subtitles-forceedit-metadata": | |||
subprrun(mysession, args, vid, "forceedit-metadata", needforcemetadata, needforcecaptions) | |||
subprrun(mysession, args, vid, "forceedit-metadata", needforcemetadata, needforcecaptions, allheaders) | |||
elif task == "channel": | |||
try: | |||
y = ydl.extract_info("https://www.youtube.com/channel/"+desit.split(":", 1)[1], download=False) | |||