Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from fastapi import FastAPI, HTTPException
|
| 2 |
+
from langchain.document_loaders import YoutubeLoader, UnstructuredPDFLoader, WebBaseLoader
|
| 3 |
+
|
| 4 |
+
app = FastAPI()
|
| 5 |
+
|
| 6 |
+
@app.post("/extract_text", tags=["Text Extraction"])
|
| 7 |
+
def extract_text(url: str, language: str = "ja", length: int = 150000):
|
| 8 |
+
try:
|
| 9 |
+
if "youtube.com" in url or "youtu.be" in url:
|
| 10 |
+
# YouTubeの場合
|
| 11 |
+
loader = YoutubeLoader.from_youtube_url(
|
| 12 |
+
youtube_url=url,
|
| 13 |
+
add_video_info=True,
|
| 14 |
+
language=[language],
|
| 15 |
+
)
|
| 16 |
+
docs = loader.load()
|
| 17 |
+
text_content = str(docs)
|
| 18 |
+
elif url.endswith(".pdf"):
|
| 19 |
+
# PDFの場合
|
| 20 |
+
loader = UnstructuredPDFLoader(url)
|
| 21 |
+
docs = loader.load()
|
| 22 |
+
text_content = docs[0].page_content
|
| 23 |
+
else:
|
| 24 |
+
# それ以外の場合
|
| 25 |
+
loader = WebBaseLoader(url)
|
| 26 |
+
docs = loader.load()
|
| 27 |
+
text_content = docs[0].page_content
|
| 28 |
+
|
| 29 |
+
if len(text_content) < length:
|
| 30 |
+
return {"text_content": text_content}
|
| 31 |
+
else:
|
| 32 |
+
return {
|
| 33 |
+
"text_content": text_content[: int(length / 2)]
|
| 34 |
+
+ text_content[len(text_content) - int(length / 2) :]
|
| 35 |
+
}
|
| 36 |
+
except Exception as e:
|
| 37 |
+
error_msg = str(e)
|
| 38 |
+
return {"message": error_msg}
|