michael/pyfedi
1
0
Fork 0
mirror of https://codeberg.org/rimu/pyfedi synced 2025-01-23 19:36:56 -08:00
Code Issues Projects Releases Packages Wiki Activity Actions

better source for pytesseract will result in more reliable ocr

Browse source
This commit is contained in:
rimu 2024-01-17 16:12:19 +13:00
parent 321731a5f0
commit ea224e291b
1 changed files with 17 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
app/activitypub/util.py
View file

@ -554,7 +554,7 @@ def make_image_sizes_async(file_id, thumbnail_width, medium_width, directory):
# Alert regarding fascist meme content
try:
image_text = pytesseract.image_to_string(Image.open(final_place).convert('L'))
image_text = pytesseract.image_to_string(Image.open(BytesIO(source_image)).convert('L'))
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'
@ -1164,6 +1164,22 @@ def undo_vote(activity_log, comment, post, target_ap_id, user):
return post
# given an activitypub id for a post or comment, retrieve it and all it's parent objects
def backfill_from_ap_id(ap_id: str):
if ap_id.startswith(f"https://{current_app.config['SERVER_NAME']}"):
...
else:
try:
activity_data = get_request(ap_id, headers={'Accept': 'application/activity+json'})
except requests.exceptions.ReadTimeout:
time.sleep(randint(3, 10))
activity_data = get_request(ap_id, headers={'Accept': 'application/activity+json'})
if activity_data.status_code == 200:
actor_json = activity_data.json()
activity_data.close()
return actor_json_to_model(actor_json, address, server)
def lemmy_site_data():
site = g.site
data = {