def get_all_documents(doccano_client: DoccanoClient, project_id):
documents = doccano_client.get_document_list(project_id, {
'limit': [doccano_client.get_project_statistics(project_id)['total']],
'offset': [0],
})['results']
for doc in documents:
doc['meta'] = json.loads(doc['meta'])
return documents
# imports
import json
import os
import psycopg2
import pandas as pd
from doccano_api_client import DoccanoClient
#client for receiving API DATA
doccano_client = DoccanoClient('http://15.207.89.34', 'admin', 'spinnaker')
total_doc = doccano_client.get_project_statistics(1)[
'total'] # 1 is for project_id
remaining_doc = doccano_client.get_project_statistics(1)[
'remaining'] # 1 is for project_id
documnet_iter_start = doccano_client.get_document_list(1)['results'][0]['id']
try:
connection = psycopg2.connect(user="******",
password="******",
host="127.0.0.1",
port="5432",
database="sahib")
cursor = connection.cursor()
postgres_insert_query = """ INSERT INTO output_data (ID, info) VALUES (%s,%s)"""
for i in range(documnet_iter_start, documnet_iter_start + total_doc):
s = doccano_client.get_document_detail(1, i)
doc_id = s['id']
doc_text = s['text'].replace("'", "")
doc_ann = s['annotations']
temp = {"text": doc_text, "annotations": doc_ann}
cursor.execute(