fix html files not being saved properly

.gitignore

@@ -4,4 +4,5 @@ crisis_events.db
 backend/storage/0/steve.zip
 backend/storage/2/steve.zip
 *.txt
-*.zip
+*.zip
\ No newline at end of file
+*.pyc

Dockerfile

+# Use the official Python 3.8 slim image as the base image
+FROM python:3.8-slim
+
+# Set the working directory within the container
+WORKDIR /api-flask
+
+# Copy the necessary files and directories into the container
+# COPY resources/ static/ util/ .env application.py requirements.txt /api-flask/
+# COPY resources/ /api-flask/resources/
+# COPY static/ /api-flask/static/
+# COPY util/ /api-flask/util/
+# COPY .env application.py requirements.txt  /api-flask/
+COPY ./requirements.txt /api-flask/
+COPY ./flask_backend.py /api-flask/
+
+# Upgrade pip and install Python dependencies
+RUN pip3 install --upgrade pip && pip install --no-cache-dir -r requirements.txt
+
+# Expose port 5000 for the Flask application
+EXPOSE 5000
+
+# Define the command to run the Flask application using Gunicorn
+CMD ["gunicorn", "application:app", "-b", "0.0.0.0:5000", "-w", "4"]
\ No newline at end of file

crisis_events_database_metadata.json

+{"Users": 2, "Collections": 1}
\ No newline at end of file

flask_backend.py

@@ -388,7 +388,8 @@ def v1_upload_raw_html():
                 with zip_ref.open(file_name) as file:
                     content = file.read()
                     text = scraper.scrape_html(content)
-                file_path = f'./backend/storage/{collection_id}/{file_name}'
+                new_file_name = file_name.split(".")[0]
+                file_path = f'./backend/storage/{collection_id}/{new_file_name}.txt'
                 with open(file_path, 'w', encoding='utf-8') as text_file:
                     text_file.write(text)