Skip to content

Required payload to get the best quality results with Python #8

Description

@Qeyf

import re
import requests

def ocr_space_file(filename, overlay=False, OCREngine=2, api_key='xxxxxxxxxxxxxxxxxxxxxxxx', language='eng', FileType='Auto', IsCreateSearchablePDF=False, isSearchablePdfHideTextLayer=True, detectOrientation=False, isTable=False, scale=True, detectCheckbox=False):
payload = {
'isOverlayRequired': overlay,
'apikey': api_key,
'language': language,
'FileType': FileType,
'IsCreateSearchablePDF': IsCreateSearchablePDF,
'isSearchablePdfHideTextLayer': isSearchablePdfHideTextLayer,
'detectOrientation': detectOrientation,
'detectOrientation': detectOrientation,
'scale': scale,
'OCREngine': OCREngine,
'detectCheckbox': detectCheckbox,
}
with open(filename, 'rb') as f:
response = requests.post('https://api.ocr.space/parse/image',
files={filename: f},
data=payload,
)
return response.json()

#you must write the rest of the code. This is just the code up to the payload part.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions