remove moviepy and ffmpeg dependency

Dockerfile

@@ -4,7 +4,7 @@ FROM --platform=$BUILDPLATFORM python:3-alpine AS builder
 
 RUN apk update
 RUN apk add pkgconfig
-RUN apk add --virtual build-deps gcc python3-dev musl-dev tesseract-ocr tesseract-ocr-data-eng ffmpeg
+RUN apk add --virtual build-deps gcc python3-dev musl-dev tesseract-ocr tesseract-ocr-data-eng
 
 WORKDIR /app
 COPY . /app

app/activitypub/util.py

@@ -10,7 +10,6 @@ import httpx
 import redis
 from flask import current_app, request, g, url_for, json
 from flask_babel import _
-from requests import JSONDecodeError
 from sqlalchemy import text, func, desc
 from sqlalchemy.exc import IntegrityError
 
@@ -29,7 +28,7 @@ import pytesseract
 from app.utils import get_request, allowlist_html, get_setting, ap_datetime, markdown_to_html, \
     is_image_url, domain_from_url, gibberish, ensure_directory_exists, head_request, \
     shorten_string, remove_tracking_from_link, \
-    microblog_content_to_title, generate_image_from_video_url, is_video_url, \
+    microblog_content_to_title, is_video_url, \
     notification_subscribers, communities_banned_from, actor_contains_blocked_words, \
     html_to_text, add_to_modlog_activitypub, joined_communities, \
     moderating_communities, get_task_session, is_video_hosting_site, opengraph_parse
@@ -1009,48 +1008,6 @@ def make_image_sizes_async(file_id, thumbnail_width, medium_width, directory, to
     session = get_task_session()
     file: File = session.query(File).get(file_id)
     if file and file.source_url:
-        # Videos (old code. not invoked because file.source_url won't end .mp4 or .webm)
-        if file.source_url.endswith('.mp4') or file.source_url.endswith('.webm'):
-            new_filename = gibberish(15)
-
-            # set up the storage directory
-            directory = f'app/static/media/{directory}/' + new_filename[0:2] + '/' + new_filename[2:4]
-            ensure_directory_exists(directory)
-
-            # file path and names to store the resized images on disk
-            final_place = os.path.join(directory, new_filename + '.jpg')
-            final_place_thumbnail = os.path.join(directory, new_filename + '_thumbnail.webp')
-            try:
-                generate_image_from_video_url(file.source_url, final_place)
-            except Exception as e:
-                return
-
-            if final_place:
-                image = Image.open(final_place)
-                img_width = image.width
-
-                # Resize the image to medium
-                if medium_width:
-                    if img_width > medium_width:
-                        image.thumbnail((medium_width, medium_width))
-                    image.save(final_place)
-                    file.file_path = final_place
-                    file.width = image.width
-                    file.height = image.height
-
-                # Resize the image to a thumbnail (webp)
-                if thumbnail_width:
-                    if img_width > thumbnail_width:
-                        image.thumbnail((thumbnail_width, thumbnail_width))
-                    image.save(final_place_thumbnail, format="WebP", quality=93)
-                    file.thumbnail_path = final_place_thumbnail
-                    file.thumbnail_width = image.width
-                    file.thumbnail_height = image.height
-
-                session.commit()
-
-        # Images
-        else:
         try:
             source_image_response = get_request(file.source_url)
         except:

app/models.py

@@ -1364,7 +1364,7 @@ class Post(db.Model):
                     i += 1
                 db.session.commit()
 
-            if post.image_id:
+            if post.image_id and not post.type == constants.POST_TYPE_VIDEO:
                 make_image_sizes(post.image_id, 170, 512, 'posts',
                                  community.low_quality)  # the 512 sized image is for masonry view
 

app/utils.py

@@ -4,7 +4,6 @@ import bisect
 import hashlib
 import mimetypes
 import random
-import tempfile
 import urllib
 from collections import defaultdict
 from datetime import datetime, timedelta, date
@@ -13,11 +12,9 @@ from typing import List, Literal, Union
 
 import httpx
 import markdown2
-import math
 from urllib.parse import urlparse, parse_qs, urlencode
 from functools import wraps
 import flask
-import requests
 from bs4 import BeautifulSoup, MarkupResemblesLocatorWarning
 import warnings
 import jwt
@@ -34,7 +31,6 @@ from wtforms.fields  import SelectField, SelectMultipleField
 from wtforms.widgets import Select, html_params, ListWidget, CheckboxInput
 from app import db, cache, httpx_client
 import re
-from moviepy.editor import VideoFileClip
 from PIL import Image, ImageOps
 
 from app.models import Settings, Domain, Instance, BannedInstances, User, Community, DomainBlock, ActivityPubLog, IpBan, \
@@ -1109,49 +1105,6 @@ def in_sorted_list(arr, target):
     return index < len(arr) and arr[index] == target
 
 
-# Makes a still image from a video url, without downloading the whole video file
-def generate_image_from_video_url(video_url, output_path, length=2):
-
-    response = requests.get(video_url, stream=True, timeout=5,
-                            headers={'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:127.0) Gecko/20100101 Firefox/127.0'})  # Imgur requires a user agent
-    content_type = response.headers.get('Content-Type')
-    if content_type:
-        if 'video/mp4' in content_type:
-            temp_file_extension = '.mp4'
-        elif 'video/webm' in content_type:
-            temp_file_extension = '.webm'
-        else:
-            raise ValueError("Unsupported video format")
-    else:
-        raise ValueError("Content-Type not found in response headers")
-
-    # Generate a random temporary file name
-    temp_file_name = gibberish(15) + temp_file_extension
-    temp_file_path = os.path.join(tempfile.gettempdir(), temp_file_name)
-
-    # Write the downloaded data to a temporary file
-    with open(temp_file_path, 'wb') as f:
-        for chunk in response.iter_content(chunk_size=4096):
-            f.write(chunk)
-            if os.path.getsize(temp_file_path) >= length * 1024 * 1024:
-                break
-
-    # Generate thumbnail from the temporary file
-    try:
-        clip = VideoFileClip(temp_file_path)
-    except Exception as e:
-        os.unlink(temp_file_path)
-        raise e
-    thumbnail = clip.get_frame(0)
-    clip.close()
-
-    # Save the image
-    thumbnail_image = Image.fromarray(thumbnail)
-    thumbnail_image.save(output_path)
-
-    os.remove(temp_file_path)
-
-
 @cache.memoize(timeout=600)
 def recently_upvoted_posts(user_id) -> List[int]:
     post_ids = db.session.execute(text('SELECT post_id FROM "post_vote" WHERE user_id = :user_id AND effect > 0 ORDER BY id DESC LIMIT 1000'),

requirements.txt

@@ -32,4 +32,3 @@ Werkzeug==2.3.3
 pytesseract==0.3.10
 sentry-sdk==1.40.6
 python-slugify==8.0.4
-moviepy==1.0.3