class ConvertDoc():
document_conversion = DocumentConversionV1(
url='https://gateway.watsonplatform.net/document-conversion/api',
username='******',
password='******',
version='2016-02-10')
config = {
'conversion_target': 'NORMALIZED_TEXT',
# Use a custom configuration.
#http://www.ibm.com/watson/developercloud/doc/document-conversion/customizing.shtml
'word': {
'heading': {
'fonts': [{
'level': 1,
'min_size': 24
}, {
'level': 2,
'min_size': 16,
'max_size': 24
}]
}
}
}
with open('uploads/guide.pdf', 'r') as document:
response = document_conversion.convert_document(document=document,
config=config)
print response.text
#To pass to next page?
#def convert_doc()
# return response.text
#finding the time and parsing with chrono time/date parser needs to be done
#https://github.com/wanasit/chrono-python
import json
from os.path import join, dirname
from watson_developer_cloud import DocumentConversionV1
document_conversion = DocumentConversionV1(
username='******',
password='******',
version='2016-02-09')
path = input('please enter the path name: ')
name = input('please enter the name of your new file with appending .json: ')
# Example with JSON
o = open(name, 'w')
f = open(path, 'r+')
config = {
'conversion_target' : DocumentConversionV1.ANSWER_UNITS
}
json.dump(document_conversion.convert_document(document=f, config=config), o, indent= 2)
f.close()
o.flush()
o.close()
__author__ = 'rcj1492'
__created__ = '2017.04'
__license__ = '©2017 Collective Acuity'
from labpack.records.settings import load_settings
from watson_developer_cloud import DocumentConversionV1
if __name__ == '__main__':
file_path = '../../media/test-pdf-4.pdf'
save_path = '../../media/test-pdf-4.json'
watson_config = load_settings('../../cred/watson.yaml')
username = watson_config['watson_conversion_username']
password = watson_config['watson_conversion_password']
document_conversion = DocumentConversionV1(username=username,
password=password,
version='2015-12-15')
convert_config = {'conversion_target': 'ANSWER_UNITS'}
file_data = open(file_path, "rb")
response = document_conversion.convert_document(document=file_data,
config=convert_config)
print(response.status_code)
with open(save_path, 'wt', encoding='utf-8', errors='ignore') as save_file:
import json
save_file.write(json.dumps(response.json(), indent=2))
save_file.close()
from ibm_cloud_env import IBMCloudEnv
from watson_developer_cloud import DocumentConversionV1
document_conversion = DocumentConversionV1(
username=IBMCloudEnv.getString('watson_document_conversion_username'),
password=IBMCloudEnv.getString('watson_document_conversion_password'),
version='2016-02-10')
def getService(app):
return 'watson-document-conversion', document_conversion
# coding=utf-8
import json
from os.path import join, dirname
from watson_developer_cloud import DocumentConversionV1 as DocumentConversion
document_conversion = DocumentConversion(username='******',
password='******')
with open(join(dirname(__file__), '../resources/sample-docx.docx'), 'rb') as document:
config = {'conversion_target': DocumentConversion.ANSWER_UNITS}
print(json.dumps(document_conversion.convert_document(document=document, config=config), indent=2))
# coding=utf-8
import json
from os.path import join, dirname
from io import open
from watson_developer_cloud import DocumentConversionV1
document_conversion = DocumentConversionV1(username='******',
password='******',
version='2016-02-09')
# Example of retrieving html or plain text
with open(join(dirname(__file__), '../resources/example.html'),
encoding='utf8') as document:
config = {'conversion_target': DocumentConversionV1.NORMALIZED_HTML}
print(
document_conversion.convert_document(document=document,
config=config,
media_type='text/html').content)
# Example with JSON
with open(join(dirname(__file__), '../resources/example.html'),
encoding='utf8') as document:
config['conversion_target'] = DocumentConversionV1.ANSWER_UNITS
print(
json.dumps(document_conversion.convert_document(document=document,
config=config),
indent=2))
# Examples of index_document API
print("########## Example of a dry run of index_document with only a document "
"##########")
import pprint
from os.path import join, dirname
import os
from watson_developer_cloud import DocumentConversionV1
from watson_developer_cloud import NaturalLanguageUnderstandingV1
from flask import Flask, render_template, request
from werkzeug import secure_filename
import requests
from requests.auth import HTTPBasicAuth
from json2html import *
app = Flask(__name__)
# Doc conversion
document_conversion = DocumentConversionV1(
username='******',
password='******',
version='2015-12-15')
#Natural language understanding
cred = {'user': '******', 'pass': '******'}
NLU_url = 'https://gateway.watsonplatform.net/natural-language-understanding/api/v1'
@app.route('/', methods=['GET', 'POST'])
def serve_page():
if request.method == 'POST':
model_id = request.values.get('model_id')
resp = requests.delete(NLU_url + '/models/' + model_id,
auth=HTTPBasicAuth(cred['user'], cred['pass']))
return render_template('index.htm', model_id="model deleted")
else:
'''
Created on Jun 2, 2016
@author: Jerome Boyer - IBM
'''
import json
from os.path import join, dirname
from watson_developer_cloud import DocumentConversionV1
document_conversion = DocumentConversionV1(
username='******',
password='******',
version='2016-02-09')
def convertBattryDocToAnswerUnit():
with open(('./data/Battery.docx'), 'rb') as document:
config = {'conversion_target': DocumentConversionV1.ANSWER_UNITS}
return document_conversion.convert_document(document=document,
config=config)
if __name__ == '__main__':
#print(json.dumps(buildAnswerUnits(), indent=2))
print(json.dumps(convertBattryDocToAnswerUnit(), indent=2))
# print(buildNormalizedHtml())
# coding=utf-8
import json
from os.path import join, dirname
from watson_developer_cloud import DocumentConversionV1 as DocumentConversion
document_conversion = DocumentConversion(username='******',
password='******',
version='2016-02-09')
with open(join(dirname(__file__), '../resources/example.html'),
'r') as document:
config = {'conversion_target': DocumentConversion.ANSWER_UNITS}
print(
json.dumps(document_conversion.convert_document(
document=document, config=config, media_type='text/html'),
indent=2))
# coding=utf-8
import json
from os.path import join, dirname
from watson_developer_cloud import DocumentConversionV1 as DocumentConversion
document_conversion = DocumentConversion(username='******',
password='******')
# print(json.dumps(document_conversion.get_jobs(), indent=2))
with open(join(dirname(__file__), '../resources/sample-docx.docx'),
'rb') as document:
config = {'conversion_target': DocumentConversion.ANSWER_UNITS}
print(
json.dumps(document_conversion.convert_document(document=document,
config=config),
indent=2))
# coding=utf-8
import json
from os.path import join, dirname
from io import open
from watson_developer_cloud import DocumentConversionV1
'''
{
"url" : "https://gateway.aibril-watson.kr/document-conversion/api",
"username" : "61d34a43-4105-42a0-9ec8-01774c3ce1a6",
"password" : "ydCaaRag3Um5"
}
'''
document_conversion = DocumentConversionV1(
username='******',
password='******',
version='2016-02-09')
# Example of retrieving html or plain text
# with open(join(dirname(__file__), '../resources/thesis/sample.pdf'),
# encoding='ascii') as document:
# config = {'conversion_target': DocumentConversionV1.NORMALIZED_HTML}
# print(document_conversion.convert_document(
# document=document, config=config, media_type='text/html').content)
# Example with JSON
with open(join(dirname(__file__), '../resources/thesis/medical.pdf'),
'rb') as document:
config = {'conversion_target': DocumentConversionV1.NORMALIZED_TEXT}
config['conversion_target'] = DocumentConversionV1.ANSWER_UNITS
print(
json.dumps(document_conversion.convert_document(document=document,
# coding=utf-8
import json
from os.path import join, dirname
from watson_developer_cloud import DocumentConversionV1 as DocumentConversion
document_conversion = DocumentConversion(username='******',
password='******',
version='2016-02-09')
with open(join(dirname(__file__), '../resources/example.html'), 'r') as document:
config = {'conversion_target': DocumentConversion.ANSWER_UNITS}
print(json.dumps(document_conversion.convert_document(document=document, config=config, media_type='text/html'),
indent=2))
