Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Create candidates_to_json.py #26

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 23 additions & 0 deletions candidates_to_json.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
from utils import config
import extract_candidates
import re
import json
import os
from dateparser.search import search_dates
import generate_tesseract_results

candidates_folder=str(config.CANDIDATE_DIR)+'/'
images_folder=str(config.IMAGE_DIR)+'/'



if __name__ == '__main__':
print("main")
for image in os.listdir(images_folder):
print(image)
path=images_folder+image
ocr_data=generate_tesseract_results.get_tesseract_results(path)
candidates=extract_candidates.get_candidates(ocr_data)
with open(candidates_folder+image.replace('.jpg','.json'),'w') as f:
json.dump(candidates,f)