Duplicate from lanbogao/docker_fastapi

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY . .
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -0,0 +1,11 @@
+---
+title: Docker Fastapi
+emoji: 🐢
+colorFrom: purple
+colorTo: blue
+sdk: docker
+pinned: false
+duplicated_from: lanbogao/docker_fastapi
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

fetchYoutubeSubtitle.py

@@ -0,0 +1,97 @@
+import json
+import os
+import requests
+import logging
+
+logger = logging.getLogger(__name__)
+
+from typing import List, Dict
+
+SUBTITLE_DOWNLOADER_URL = 'https://savesubs.com'
+
+def fetchYoutubeSubtitleUrls(video_id):
+    headers = {
+        'accept': 'application/json, text/plain, */*',
+        'accept-language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
+        'cache-control': 'no-cache',
+        'Content-Type': 'application/json; charset=UTF-8',
+        'pragma': 'no-cache',
+        'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36',
+        'x-auth-token': os.environ.get('SAVESUBS_X_AUTH_TOKEN', ''),
+        'x-requested-domain': 'savesubs.com',
+        'X-requested-with': 'xmlhttprequest',
+        'sec-ch-ua': '"Google Chrome";v="111", "Not(A:Brand";v="8", "Chromium";v="111"',
+        'sec-ch-ua-mobile': '?0',
+        'sec-ch-ua-platform': 'Linux',
+        'sec-fetch-dest': 'empty',
+        'sec-fetch-mode': 'cors',
+        'sec-fetch-site': 'same-origin',
+        'authority': 'savesubs.com',
+        'origin': 'https://savesubs.com',
+        'referer': f'https://savesubs.com/process?url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3D{video_id}'
+    }
+    data = {
+        'data': {'url': f'https://www.youtube.com/watch?v={video_id}'}
+    }
+    session = requests.Session()
+
+    proxy = os.environ.get('PROXY', None)
+    if proxy:
+        session.proxies = {
+            "http": proxy,
+            "https": proxy,
+        }
+
+    response = session.post(SUBTITLE_DOWNLOADER_URL + '/action/extract', json=data, headers=headers)
+    
+    
+    if response.status_code != 200:
+        logger.error("response.status_code: {}".format(response.status_code))
+        return {'title': None, 'subtitleList': None, 'error': response.reason}
+    else:
+        try:
+            json = response.json().get('response', {})
+            logger.info('subtitle url json: {}'.format(json))
+            return {'title': json.get('title'), 'subtitleList': json.get('formats')}
+        except Exception as error:
+            logger.error(error)
+            return {'title': None, 'subtitleList': None, 'error': str(error)}
+
+
+async def find(subtitleList: List[Dict], args: Dict) -> Dict:
+    key = list(args.keys())[0]
+    return next((item for item in subtitleList if item.get(key, None) == args[key]), None)
+
+async def fetchYoutubeSubtitle(videoId: str) -> Dict:
+    subtitle_url = ""
+    betterSubtitle = {}
+    subtitleList = []
+    title = ""
+    error = ""
+
+    result = fetchYoutubeSubtitleUrls(videoId)
+    title, subtitleList, error = result["title"], result["subtitleList"], result.get("error", None)
+
+    if not subtitleList or len(subtitleList) <= 0:
+        return {"title": title, "subtitle": None, "error": error}
+
+    betterSubtitle = (
+        await find(subtitleList, {"quality": "English"})
+        or await find(subtitleList, {"quality": "English (auto"})
+        or await find(subtitleList, {"quality": "zh-CN"})
+        or subtitleList[0]
+    )
+
+    subtitleUrl = f"{SUBTITLE_DOWNLOADER_URL}{betterSubtitle['url']}?ext=srt"
+
+    session = requests.Session()
+
+    proxy = os.environ.get('PROXY', None)
+    if proxy:
+        session.proxies = {
+            "http": proxy,
+            "https": proxy,
+        }
+    response = session.get(subtitleUrl)
+    
+    return {"title": title, "subtitle": response.text}

main.py

@@ -0,0 +1,20 @@
+from fastapi import FastAPI
+from fastapi.responses import JSONResponse
+from fetchYoutubeSubtitle import fetchYoutubeSubtitle
+
+app = FastAPI()
+
+@app.get("/")
+def read_root():
+    return {"Hello": "World!"}
+
+
+@app.get("/json")
+def read_json():
+    return JSONResponse(content={"Hello": "World!"})
+
+
+@app.get("/subtitle/")
+async def get_subtitle(vid: str):
+    subtitle = await fetchYoutubeSubtitle(vid)
+    return JSONResponse(content=subtitle)

requirements.txt

@@ -0,0 +1,7 @@
+fastapi==0.74.*
+requests==2.27.*
+sentencepiece==0.1.*
+torch==1.11.*
+transformers==4.*
+uvicorn[standard]==0.17.*
+langchain