Spaces:
Sleeping
Sleeping
lanbogao
commited on
Commit
•
093a866
0
Parent(s):
Duplicate from lanbogao/docker_fastapi
Browse files- .gitattributes +34 -0
- Dockerfile +11 -0
- README.md +11 -0
- fetchYoutubeSubtitle.py +97 -0
- main.py +20 -0
- requirements.txt +7 -0
.gitattributes
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
Dockerfile
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
FROM python:3.9
|
2 |
+
|
3 |
+
WORKDIR /code
|
4 |
+
|
5 |
+
COPY ./requirements.txt /code/requirements.txt
|
6 |
+
|
7 |
+
RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
|
8 |
+
|
9 |
+
COPY . .
|
10 |
+
|
11 |
+
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
|
README.md
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
title: Docker Fastapi
|
3 |
+
emoji: 🐢
|
4 |
+
colorFrom: purple
|
5 |
+
colorTo: blue
|
6 |
+
sdk: docker
|
7 |
+
pinned: false
|
8 |
+
duplicated_from: lanbogao/docker_fastapi
|
9 |
+
---
|
10 |
+
|
11 |
+
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
fetchYoutubeSubtitle.py
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import json
|
2 |
+
import os
|
3 |
+
import requests
|
4 |
+
import logging
|
5 |
+
|
6 |
+
logger = logging.getLogger(__name__)
|
7 |
+
|
8 |
+
from typing import List, Dict
|
9 |
+
|
10 |
+
SUBTITLE_DOWNLOADER_URL = 'https://savesubs.com'
|
11 |
+
|
12 |
+
def fetchYoutubeSubtitleUrls(video_id):
|
13 |
+
headers = {
|
14 |
+
'accept': 'application/json, text/plain, */*',
|
15 |
+
'accept-language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
|
16 |
+
'cache-control': 'no-cache',
|
17 |
+
'Content-Type': 'application/json; charset=UTF-8',
|
18 |
+
'pragma': 'no-cache',
|
19 |
+
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36',
|
20 |
+
'x-auth-token': os.environ.get('SAVESUBS_X_AUTH_TOKEN', ''),
|
21 |
+
'x-requested-domain': 'savesubs.com',
|
22 |
+
'X-requested-with': 'xmlhttprequest',
|
23 |
+
'sec-ch-ua': '"Google Chrome";v="111", "Not(A:Brand";v="8", "Chromium";v="111"',
|
24 |
+
'sec-ch-ua-mobile': '?0',
|
25 |
+
'sec-ch-ua-platform': 'Linux',
|
26 |
+
'sec-fetch-dest': 'empty',
|
27 |
+
'sec-fetch-mode': 'cors',
|
28 |
+
'sec-fetch-site': 'same-origin',
|
29 |
+
'authority': 'savesubs.com',
|
30 |
+
'origin': 'https://savesubs.com',
|
31 |
+
'referer': f'https://savesubs.com/process?url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3D{video_id}'
|
32 |
+
}
|
33 |
+
data = {
|
34 |
+
'data': {'url': f'https://www.youtube.com/watch?v={video_id}'}
|
35 |
+
}
|
36 |
+
session = requests.Session()
|
37 |
+
|
38 |
+
proxy = os.environ.get('PROXY', None)
|
39 |
+
if proxy:
|
40 |
+
session.proxies = {
|
41 |
+
"http": proxy,
|
42 |
+
"https": proxy,
|
43 |
+
}
|
44 |
+
|
45 |
+
response = session.post(SUBTITLE_DOWNLOADER_URL + '/action/extract', json=data, headers=headers)
|
46 |
+
|
47 |
+
|
48 |
+
if response.status_code != 200:
|
49 |
+
logger.error("response.status_code: {}".format(response.status_code))
|
50 |
+
return {'title': None, 'subtitleList': None, 'error': response.reason}
|
51 |
+
else:
|
52 |
+
try:
|
53 |
+
json = response.json().get('response', {})
|
54 |
+
logger.info('subtitle url json: {}'.format(json))
|
55 |
+
return {'title': json.get('title'), 'subtitleList': json.get('formats')}
|
56 |
+
except Exception as error:
|
57 |
+
logger.error(error)
|
58 |
+
return {'title': None, 'subtitleList': None, 'error': str(error)}
|
59 |
+
|
60 |
+
|
61 |
+
async def find(subtitleList: List[Dict], args: Dict) -> Dict:
|
62 |
+
key = list(args.keys())[0]
|
63 |
+
return next((item for item in subtitleList if item.get(key, None) == args[key]), None)
|
64 |
+
|
65 |
+
async def fetchYoutubeSubtitle(videoId: str) -> Dict:
|
66 |
+
subtitle_url = ""
|
67 |
+
betterSubtitle = {}
|
68 |
+
subtitleList = []
|
69 |
+
title = ""
|
70 |
+
error = ""
|
71 |
+
|
72 |
+
result = fetchYoutubeSubtitleUrls(videoId)
|
73 |
+
title, subtitleList, error = result["title"], result["subtitleList"], result.get("error", None)
|
74 |
+
|
75 |
+
if not subtitleList or len(subtitleList) <= 0:
|
76 |
+
return {"title": title, "subtitle": None, "error": error}
|
77 |
+
|
78 |
+
betterSubtitle = (
|
79 |
+
await find(subtitleList, {"quality": "English"})
|
80 |
+
or await find(subtitleList, {"quality": "English (auto"})
|
81 |
+
or await find(subtitleList, {"quality": "zh-CN"})
|
82 |
+
or subtitleList[0]
|
83 |
+
)
|
84 |
+
|
85 |
+
subtitleUrl = f"{SUBTITLE_DOWNLOADER_URL}{betterSubtitle['url']}?ext=srt"
|
86 |
+
|
87 |
+
session = requests.Session()
|
88 |
+
|
89 |
+
proxy = os.environ.get('PROXY', None)
|
90 |
+
if proxy:
|
91 |
+
session.proxies = {
|
92 |
+
"http": proxy,
|
93 |
+
"https": proxy,
|
94 |
+
}
|
95 |
+
response = session.get(subtitleUrl)
|
96 |
+
|
97 |
+
return {"title": title, "subtitle": response.text}
|
main.py
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from fastapi import FastAPI
|
2 |
+
from fastapi.responses import JSONResponse
|
3 |
+
from fetchYoutubeSubtitle import fetchYoutubeSubtitle
|
4 |
+
|
5 |
+
app = FastAPI()
|
6 |
+
|
7 |
+
@app.get("/")
|
8 |
+
def read_root():
|
9 |
+
return {"Hello": "World!"}
|
10 |
+
|
11 |
+
|
12 |
+
@app.get("/json")
|
13 |
+
def read_json():
|
14 |
+
return JSONResponse(content={"Hello": "World!"})
|
15 |
+
|
16 |
+
|
17 |
+
@app.get("/subtitle/")
|
18 |
+
async def get_subtitle(vid: str):
|
19 |
+
subtitle = await fetchYoutubeSubtitle(vid)
|
20 |
+
return JSONResponse(content=subtitle)
|
requirements.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
fastapi==0.74.*
|
2 |
+
requests==2.27.*
|
3 |
+
sentencepiece==0.1.*
|
4 |
+
torch==1.11.*
|
5 |
+
transformers==4.*
|
6 |
+
uvicorn[standard]==0.17.*
|
7 |
+
langchain
|