upload to telegram
Browse files- App/Transcription/TranscriptionRoutes.py +23 -13
- App/app.py +1 -1
App/Transcription/TranscriptionRoutes.py
CHANGED
@@ -9,6 +9,7 @@ from .Schemas import (
|
|
9 |
)
|
10 |
from App import bot
|
11 |
import aiofiles, os, re
|
|
|
12 |
import tempfile
|
13 |
from celery.result import AsyncResult
|
14 |
from App.Worker import transcription_task, downloadfile
|
@@ -27,6 +28,10 @@ from App.Embedding.utils.Initialize import delete_documents
|
|
27 |
|
28 |
transcription_router = APIRouter(tags=["Transcription"])
|
29 |
|
|
|
|
|
|
|
|
|
30 |
|
31 |
@transcription_router.get("/download-audio")
|
32 |
async def download_audio(
|
@@ -38,14 +43,17 @@ async def download_audio(
|
|
38 |
),
|
39 |
user: UserSchema = Depends(get_token_owner),
|
40 |
):
|
41 |
-
|
|
|
42 |
parsed_url = urlparse(youtube_url)
|
43 |
|
44 |
# Get the query parameters
|
45 |
query_parameters = parse_qs(parsed_url.query)
|
46 |
|
47 |
# Get the value of the 'v' parameter
|
48 |
-
v_param_value =
|
|
|
|
|
49 |
url = f"https://www.youtube.com/watch?v={v_param_value}"
|
50 |
if user == None:
|
51 |
return {"code": 400, "message": "doesn't exist", "payload": None}
|
@@ -57,9 +65,9 @@ async def download_audio(
|
|
57 |
with yt_dlp.YoutubeDL(ydl_opts_info) as ydl:
|
58 |
info_dict = ydl.extract_info(url, download=False)
|
59 |
video_title = info_dict.get("title", None)
|
60 |
-
|
61 |
sanitized_title = re.sub(
|
62 |
-
r"(?u)[^-\w.]", "",
|
63 |
) # Ensure the title is file-friendly
|
64 |
filename = f"{sanitized_title}.mp3"
|
65 |
file_path = os.path.join("./", "Downloads", filename)
|
@@ -70,7 +78,7 @@ async def download_audio(
|
|
70 |
}
|
71 |
|
72 |
task = downloadfile.delay(url=url, ydl_opts=ydl_opts, model_size=model)
|
73 |
-
response = {"task_id": task.id, "file_name":
|
74 |
transcription_enrty = await Transcriptions.objects.create(
|
75 |
user=user, youtubeLink=url, **response
|
76 |
)
|
@@ -124,10 +132,12 @@ async def create_file(
|
|
124 |
),
|
125 |
user: UserSchema = Depends(get_token_owner),
|
126 |
):
|
|
|
|
|
127 |
# Write the file to disk asynchronously
|
128 |
Upload_dir = ""
|
129 |
try:
|
130 |
-
async with aiofiles.open(
|
131 |
while contents := await file.read(1024 * 1):
|
132 |
await f.write(contents)
|
133 |
|
@@ -139,11 +149,11 @@ async def create_file(
|
|
139 |
await file.close()
|
140 |
|
141 |
# celery task
|
142 |
-
task = transcription_task.delay(
|
143 |
|
144 |
# create a transcription entry
|
145 |
transcription_enrty = await Transcriptions.objects.create(
|
146 |
-
task_id=task.id, user=user, file_name=
|
147 |
)
|
148 |
background_tasks.add_task(perform_background_task, file=file, task_id=task.id)
|
149 |
return {
|
@@ -162,7 +172,7 @@ async def get_status(task_id):
|
|
162 |
result = BaseTranscription(**entry.__dict__)
|
163 |
|
164 |
if result.status == "SUCCESS":
|
165 |
-
result.percentage=
|
166 |
return result
|
167 |
task_result = AsyncResult(task_id)
|
168 |
# print(task_result.result)
|
@@ -175,17 +185,17 @@ async def get_status(task_id):
|
|
175 |
|
176 |
if task_result.status == "SUCCESS":
|
177 |
trans = TranscriptionMetadata(**task_result.result)
|
178 |
-
percentage=
|
179 |
await entry.update(**trans.dict())
|
180 |
else:
|
181 |
try:
|
182 |
_trans = TranscriptionMetadata(**task_result.result)
|
183 |
-
percentage=_trans.percentage
|
184 |
except Exception as e:
|
185 |
print(e)
|
186 |
return {"payload": None, "message": "Nothing found", "code": 200}
|
187 |
await entry.update(**_trans.dict())
|
188 |
|
189 |
result = BaseTranscription(**entry.__dict__)
|
190 |
-
result.percentage=percentage
|
191 |
-
return result
|
|
|
9 |
)
|
10 |
from App import bot
|
11 |
import aiofiles, os, re
|
12 |
+
import uuid
|
13 |
import tempfile
|
14 |
from celery.result import AsyncResult
|
15 |
from App.Worker import transcription_task, downloadfile
|
|
|
28 |
|
29 |
transcription_router = APIRouter(tags=["Transcription"])
|
30 |
|
31 |
+
def genUUID():
|
32 |
+
uuid_value = uuid.uuid4()
|
33 |
+
short_uuid = str(uuid_value)[:6]
|
34 |
+
return short_uuid
|
35 |
|
36 |
@transcription_router.get("/download-audio")
|
37 |
async def download_audio(
|
|
|
43 |
),
|
44 |
user: UserSchema = Depends(get_token_owner),
|
45 |
):
|
46 |
+
|
47 |
+
youtube_url = url
|
48 |
parsed_url = urlparse(youtube_url)
|
49 |
|
50 |
# Get the query parameters
|
51 |
query_parameters = parse_qs(parsed_url.query)
|
52 |
|
53 |
# Get the value of the 'v' parameter
|
54 |
+
v_param_value = (
|
55 |
+
query_parameters.get("v", [])[0] if "v" in query_parameters else None
|
56 |
+
)
|
57 |
url = f"https://www.youtube.com/watch?v={v_param_value}"
|
58 |
if user == None:
|
59 |
return {"code": 400, "message": "doesn't exist", "payload": None}
|
|
|
65 |
with yt_dlp.YoutubeDL(ydl_opts_info) as ydl:
|
66 |
info_dict = ydl.extract_info(url, download=False)
|
67 |
video_title = info_dict.get("title", None)
|
68 |
+
short_uuid = genUUID()
|
69 |
sanitized_title = re.sub(
|
70 |
+
r"(?u)[^-\w.]", "", short_uuid
|
71 |
) # Ensure the title is file-friendly
|
72 |
filename = f"{sanitized_title}.mp3"
|
73 |
file_path = os.path.join("./", "Downloads", filename)
|
|
|
78 |
}
|
79 |
|
80 |
task = downloadfile.delay(url=url, ydl_opts=ydl_opts, model_size=model)
|
81 |
+
response = {"task_id": task.id, "file_name": video_title }
|
82 |
transcription_enrty = await Transcriptions.objects.create(
|
83 |
user=user, youtubeLink=url, **response
|
84 |
)
|
|
|
132 |
),
|
133 |
user: UserSchema = Depends(get_token_owner),
|
134 |
):
|
135 |
+
extension = file.filename.split('.')[-1]
|
136 |
+
file_name = f'{genUUID()}.{extension}'
|
137 |
# Write the file to disk asynchronously
|
138 |
Upload_dir = ""
|
139 |
try:
|
140 |
+
async with aiofiles.open(file_name, "wb") as f:
|
141 |
while contents := await file.read(1024 * 1):
|
142 |
await f.write(contents)
|
143 |
|
|
|
149 |
await file.close()
|
150 |
|
151 |
# celery task
|
152 |
+
task = transcription_task.delay(file_name, model)
|
153 |
|
154 |
# create a transcription entry
|
155 |
transcription_enrty = await Transcriptions.objects.create(
|
156 |
+
task_id=task.id, user=user, file_name=file_name
|
157 |
)
|
158 |
background_tasks.add_task(perform_background_task, file=file, task_id=task.id)
|
159 |
return {
|
|
|
172 |
result = BaseTranscription(**entry.__dict__)
|
173 |
|
174 |
if result.status == "SUCCESS":
|
175 |
+
result.percentage = "100"
|
176 |
return result
|
177 |
task_result = AsyncResult(task_id)
|
178 |
# print(task_result.result)
|
|
|
185 |
|
186 |
if task_result.status == "SUCCESS":
|
187 |
trans = TranscriptionMetadata(**task_result.result)
|
188 |
+
percentage = "100"
|
189 |
await entry.update(**trans.dict())
|
190 |
else:
|
191 |
try:
|
192 |
_trans = TranscriptionMetadata(**task_result.result)
|
193 |
+
percentage = _trans.percentage
|
194 |
except Exception as e:
|
195 |
print(e)
|
196 |
return {"payload": None, "message": "Nothing found", "code": 200}
|
197 |
await entry.update(**_trans.dict())
|
198 |
|
199 |
result = BaseTranscription(**entry.__dict__)
|
200 |
+
result.percentage = percentage
|
201 |
+
return result
|
App/app.py
CHANGED
@@ -47,7 +47,7 @@ def authjwt_exception_handler(request: Request, exc: AuthJWTException):
|
|
47 |
|
48 |
@app.on_event("startup")
|
49 |
async def startup_event():
|
50 |
-
|
51 |
# await upload_bot.start()
|
52 |
# await models.create_all()
|
53 |
# models.metadata.create_all()
|
|
|
47 |
|
48 |
@app.on_event("startup")
|
49 |
async def startup_event():
|
50 |
+
await bot.start(bot_token="6183919505:AAEhHFt4mI18bQeAf2Lj7AePXFRPVLrOFM8")
|
51 |
# await upload_bot.start()
|
52 |
# await models.create_all()
|
53 |
# models.metadata.create_all()
|