app

Dockerfile

@@ -0,0 +1,14 @@
+
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN apt-get install poppler-utils
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY . .
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]
+

app.py

@@ -0,0 +1,40 @@
+import os
+import subprocess as sp
+import tempfile
+from pathlib import Path
+from fastapi import FastAPI
+from fastapi import FastAPI, File, UploadFile
+import aiofiles
+import shutil
+
+
+app = FastAPI()
+
+
+def extract_text(pdf_file):
+    """
+    Generate a text rendering of a PDF file in the form of a list of lines.
+    """
+    args = ['pdftotext', '-layout', pdf_file, '-']
+    cp = sp.run(
+      args, stdout=sp.PIPE, stderr=sp.DEVNULL,
+      check=True, text=True
+    )
+    return cp.stdout
+
+
+def save_and_export(pdf_file: UploadFile):
+    with tempfile.NamedTemporaryFile() as tmp_file:
+        shutil.copyfileobj(pdf_file.file, tmp_file)
+        resulting_text = extract_text(tmp_file.name)
+    return resulting_text
+
+
+@app.post('/extract_text')
+async def app_extract_text(pdf_file: UploadFile) -> str:
+    return save_and_export(pdf_file)
+
+
+@app.get("/")
+def read_root():
+    return {"Hello": "World"}

requirements.txt

@@ -0,0 +1,2 @@
+fastapi
+aiofiles