mermelstein

from PIL import Image
import pytesseract
from pdf2image import convert_from_path

# Convert the PDF to a list of images
images = convert_from_path('path_to_pdf.pdf')

# Process each image with Tesseract
for i, img in enumerate(images):
    text = pytesseract.image_to_string(img, lang='eng')

mermelstein

FROM python:3.10

WORKDIR /app

COPY . /app

RUN pip install uv
RUN uv pip install --system --no-cache-dir -r requirements.txt

CMD python -u main.py

mermelstein

library(jsonlite)
library(brio)

# where is the archive directory
dir_path <- "~/Downloads/twitter-archive/data"

# file in /data with the tweets
filename <- "tweets.js"

# get full file path

mermelstein

library(jsonlite)
library(lubridate)

# specify local path to the downloaded JSON files
path <- "~/Downloads/Spotify Extended Streaming History/"

# get a list of all JSON files in the directory
json_files <- list.files(path, pattern = "*.json", full.names = TRUE)

# initialize an empty list to store the data