From abd4dd16c9dad194e447d018ec14a3dc271007a6 Mon Sep 17 00:00:00 2001
From: rimu <3310831+rimu@users.noreply.github.com>
Date: Tue, 16 Apr 2024 16:35:12 +1200
Subject: [PATCH] embed video and generate still thumbnail
---
app/activitypub/util.py | 165 +++++++++++++++---------
app/community/util.py | 42 +++---
app/main/routes.py | 3 +-
app/static/structure.css | 5 +
app/static/structure.scss | 5 +
app/templates/post/_post_full.html | 9 ++
app/utils.py | 43 +++++-
docs/project_management/contributing.md | 5 +-
requirements.txt | 1 +
9 files changed, 193 insertions(+), 85 deletions(-)
diff --git a/app/activitypub/util.py b/app/activitypub/util.py
index 1a463a79..277641bb 100644
--- a/app/activitypub/util.py
+++ b/app/activitypub/util.py
@@ -27,7 +27,7 @@ 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, markdown_to_text, head_request, post_ranking, \
shorten_string, reply_already_exists, reply_is_just_link_to_gif_reaction, confidence, remove_tracking_from_link, \
- blocked_phrases, microblog_content_to_title
+ blocked_phrases, microblog_content_to_title, generate_image_from_video_url
def public_key():
@@ -738,78 +738,117 @@ def make_image_sizes(file_id, thumbnail_width=50, medium_width=120, directory='p
def make_image_sizes_async(file_id, thumbnail_width, medium_width, directory):
file = File.query.get(file_id)
if file and file.source_url:
- try:
- source_image_response = get_request(file.source_url)
- except:
- pass
+ # Videos
+ 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')
+
+ generate_image_from_video_url(file.source_url, 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
+
+ db.session.commit()
+
+ # Images
else:
- if source_image_response.status_code == 200:
- content_type = source_image_response.headers.get('content-type')
- if content_type and content_type.startswith('image'):
- source_image = source_image_response.content
- source_image_response.close()
+ try:
+ source_image_response = get_request(file.source_url)
+ except:
+ pass
+ else:
+ if source_image_response.status_code == 200:
+ content_type = source_image_response.headers.get('content-type')
+ if content_type and content_type.startswith('image'):
+ source_image = source_image_response.content
+ source_image_response.close()
- file_ext = os.path.splitext(file.source_url)[1]
- # fall back to parsing the http content type if the url does not contain a file extension
- if file_ext == '':
- content_type_parts = content_type.split('/')
- if content_type_parts:
- file_ext = '.' + content_type_parts[-1]
- else:
- if '?' in file_ext:
- file_ext = file_ext.split('?')[0]
+ file_ext = os.path.splitext(file.source_url)[1]
+ # fall back to parsing the http content type if the url does not contain a file extension
+ if file_ext == '':
+ content_type_parts = content_type.split('/')
+ if content_type_parts:
+ file_ext = '.' + content_type_parts[-1]
+ else:
+ if '?' in file_ext:
+ file_ext = file_ext.split('?')[0]
- new_filename = gibberish(15)
+ 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)
+ # 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 + file_ext)
- final_place_thumbnail = os.path.join(directory, new_filename + '_thumbnail.webp')
+ # file path and names to store the resized images on disk
+ final_place = os.path.join(directory, new_filename + file_ext)
+ final_place_thumbnail = os.path.join(directory, new_filename + '_thumbnail.webp')
- # Load image data into Pillow
- Image.MAX_IMAGE_PIXELS = 89478485
- image = Image.open(BytesIO(source_image))
- image = ImageOps.exif_transpose(image)
- img_width = image.width
- img_height = image.height
+ # Load image data into Pillow
+ Image.MAX_IMAGE_PIXELS = 89478485
+ image = Image.open(BytesIO(source_image))
+ image = ImageOps.exif_transpose(image)
+ img_width = image.width
+ img_height = image.height
- # 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 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
+ # 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
- db.session.commit()
+ db.session.commit()
- # Alert regarding fascist meme content
- if img_width < 2000: # images > 2000px tend to be real photos instead of 4chan screenshots.
- try:
- image_text = pytesseract.image_to_string(Image.open(BytesIO(source_image)).convert('L'), timeout=30)
- except FileNotFoundError as e:
- image_text = ''
- if 'Anonymous' in image_text and ('No.' in image_text or ' N0' in image_text): # chan posts usually contain the text 'Anonymous' and ' No.12345'
- post = Post.query.filter_by(image_id=file.id).first()
- notification = Notification(title='Review this',
- user_id=1,
- author_id=post.user_id,
- url=url_for('activitypub.post_ap', post_id=post.id))
- db.session.add(notification)
- db.session.commit()
+ # Alert regarding fascist meme content
+ if img_width < 2000: # images > 2000px tend to be real photos instead of 4chan screenshots.
+ try:
+ image_text = pytesseract.image_to_string(Image.open(BytesIO(source_image)).convert('L'), timeout=30)
+ except FileNotFoundError as e:
+ image_text = ''
+ if 'Anonymous' in image_text and ('No.' in image_text or ' N0' in image_text): # chan posts usually contain the text 'Anonymous' and ' No.12345'
+ post = Post.query.filter_by(image_id=file.id).first()
+ notification = Notification(title='Review this',
+ user_id=1,
+ author_id=post.user_id,
+ url=url_for('activitypub.post_ap', post_id=post.id))
+ db.session.add(notification)
+ db.session.commit()
# create a summary from markdown if present, otherwise use html if available
diff --git a/app/community/util.py b/app/community/util.py
index c58dcad9..7b438594 100644
--- a/app/community/util.py
+++ b/app/community/util.py
@@ -112,7 +112,8 @@ def retrieve_mods_and_backfill(community_id: int):
post.ranking = post_ranking(post.score, post.posted_at)
if post.url:
other_posts = Post.query.filter(Post.id != post.id, Post.url == post.url,
- Post.posted_at > post.posted_at - timedelta(days=3), Post.posted_at < post.posted_at + timedelta(days=3)).all()
+ Post.posted_at > post.posted_at - timedelta(days=3),
+ Post.posted_at < post.posted_at + timedelta(days=3)).all()
for op in other_posts:
if op.cross_posts is None:
op.cross_posts = [post.id]
@@ -223,26 +224,31 @@ def save_post(form, post: Post, type: str):
remove_old_file(post.image_id)
post.image_id = None
- unused, file_extension = os.path.splitext(form.link_url.data)
- # this url is a link to an image - turn it into a image post
- if file_extension.lower() in allowed_extensions:
- file = File(source_url=form.link_url.data)
+ if post.url.endswith('.mp4') or post.url.endswith('.webm'):
+ file = File(source_url=form.link_url.data) # make_image_sizes() will take care of turning this into a still image
post.image = file
db.session.add(file)
- post.type = POST_TYPE_IMAGE
else:
- # check opengraph tags on the page and make a thumbnail if an image is available in the og:image meta tag
- opengraph = opengraph_parse(form.link_url.data)
- if opengraph and (opengraph.get('og:image', '') != '' or opengraph.get('og:image:url', '') != ''):
- filename = opengraph.get('og:image') or opengraph.get('og:image:url')
- filename_for_extension = filename.split('?')[0] if '?' in filename else filename
- unused, file_extension = os.path.splitext(filename_for_extension)
- if file_extension.lower() in allowed_extensions and not filename.startswith('/'):
- file = url_to_thumbnail_file(filename)
- if file:
- file.alt_text = shorten_string(opengraph.get('og:title'), 295)
- post.image = file
- db.session.add(file)
+ unused, file_extension = os.path.splitext(form.link_url.data)
+ # this url is a link to an image - turn it into a image post
+ if file_extension.lower() in allowed_extensions:
+ file = File(source_url=form.link_url.data)
+ post.image = file
+ db.session.add(file)
+ post.type = POST_TYPE_IMAGE
+ else:
+ # check opengraph tags on the page and make a thumbnail if an image is available in the og:image meta tag
+ opengraph = opengraph_parse(form.link_url.data)
+ if opengraph and (opengraph.get('og:image', '') != '' or opengraph.get('og:image:url', '') != ''):
+ filename = opengraph.get('og:image') or opengraph.get('og:image:url')
+ filename_for_extension = filename.split('?')[0] if '?' in filename else filename
+ unused, file_extension = os.path.splitext(filename_for_extension)
+ if file_extension.lower() in allowed_extensions and not filename.startswith('/'):
+ file = url_to_thumbnail_file(filename)
+ if file:
+ file.alt_text = shorten_string(opengraph.get('og:title'), 295)
+ post.image = file
+ db.session.add(file)
elif type == 'image':
post.title = form.image_title.data
diff --git a/app/main/routes.py b/app/main/routes.py
index d90f55d3..74bf30d7 100644
--- a/app/main/routes.py
+++ b/app/main/routes.py
@@ -25,7 +25,8 @@ from sqlalchemy_searchable import search
from app.utils import render_template, get_setting, gibberish, request_etag_matches, return_304, blocked_domains, \
ap_datetime, ip_address, retrieve_block_list, shorten_string, markdown_to_text, user_filters_home, \
joined_communities, moderating_communities, parse_page, theme_list, get_request, markdown_to_html, allowlist_html, \
- blocked_instances, communities_banned_from, topic_tree, recently_upvoted_posts, recently_downvoted_posts
+ blocked_instances, communities_banned_from, topic_tree, recently_upvoted_posts, recently_downvoted_posts, \
+ generate_image_from_video_url
from app.models import Community, CommunityMember, Post, Site, User, utcnow, Domain, Topic, File, Instance, \
InstanceRole, Notification
from PIL import Image
diff --git a/app/static/structure.css b/app/static/structure.css
index 64cbe713..b66f05f9 100644
--- a/app/static/structure.css
+++ b/app/static/structure.css
@@ -1384,4 +1384,9 @@ h1 .warning_badge {
max-width: 100%;
}
+.responsive-video {
+ max-width: 100%;
+ max-height: 90vh;
+}
+
/*# sourceMappingURL=structure.css.map */
diff --git a/app/static/structure.scss b/app/static/structure.scss
index 8152ec92..79019d4f 100644
--- a/app/static/structure.scss
+++ b/app/static/structure.scss
@@ -1057,4 +1057,9 @@ h1 .warning_badge {
line-height: initial;
max-width: 100%;
}
+}
+
+.responsive-video {
+ max-width: 100%;
+ max-height: 90vh;
}
\ No newline at end of file
diff --git a/app/templates/post/_post_full.html b/app/templates/post/_post_full.html
index b0d1c618..891700f3 100644
--- a/app/templates/post/_post_full.html
+++ b/app/templates/post/_post_full.html
@@ -83,6 +83,15 @@
+ {% elif post.url.endswith('.mp4') or post.url.endswith('.webm') %}
+
+
+ {% if post.url.endswith('.mp4') %}
+
{% endif %}
{% if 'youtube.com' in post.url %}
{{ _('Watch on piped.video') }}
diff --git a/app/utils.py b/app/utils.py
index f7d427cf..c354b085 100644
--- a/app/utils.py
+++ b/app/utils.py
@@ -4,6 +4,7 @@ import bisect
import hashlib
import mimetypes
import random
+import tempfile
import urllib
from collections import defaultdict
from datetime import datetime, timedelta, date
@@ -14,7 +15,7 @@ import math
from urllib.parse import urlparse, parse_qs, urlencode
from functools import wraps
import flask
-from bs4 import BeautifulSoup, NavigableString, MarkupResemblesLocatorWarning
+from bs4 import BeautifulSoup, MarkupResemblesLocatorWarning
import warnings
warnings.filterwarnings("ignore", category=MarkupResemblesLocatorWarning)
import requests
@@ -26,6 +27,8 @@ from wtforms.fields import SelectField, SelectMultipleField
from wtforms.widgets import Select, html_params, ListWidget, CheckboxInput
from app import db, cache
import re
+from moviepy.editor import VideoFileClip
+from PIL import Image
from app.email import send_welcome_email
from app.models import Settings, Domain, Instance, BannedInstances, User, Community, DomainBlock, ActivityPubLog, IpBan, \
@@ -881,6 +884,44 @@ 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)
+ 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
+ clip = VideoFileClip(temp_file_path)
+ 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'),
diff --git a/docs/project_management/contributing.md b/docs/project_management/contributing.md
index f09ea3d3..92bfeff1 100644
--- a/docs/project_management/contributing.md
+++ b/docs/project_management/contributing.md
@@ -34,9 +34,10 @@ time of things.
# Coding Standards / Guidelines
**[PEP 8](https://peps.python.org/pep-0008/)** covers the basics. PyCharm encourages this by default -
-VS Code coders are encouraged to try the free community edition of PyCharm but it is by no means required.
+VS Code coders may like to try the free community edition of PyCharm but it is by no means required.
-Use PEP 8 conventions for line length, naming, indentation. Use descriptive commit messages.
+Use PEP 8 conventions for naming, indentation. Use descriptive commit messages. Try to limit lines of code
+to a length of roughly 120 characters.
Database model classes are singular. As in "Car", not "Cars".
diff --git a/requirements.txt b/requirements.txt
index fad9be58..338bdd49 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -32,3 +32,4 @@ Werkzeug==2.3.3
pytesseract==0.3.10
sentry-sdk==1.40.6
python-slugify==8.0.4
+moviepy==1.0.3