def Pptx_To_Png(pptx_input):
# Configure API key authorization: Apikey
configuration = cloudmersive_convert_api_client.Configuration()
configuration.api_key['Apikey'] = 'f0a69dc5-3973-4ab9-9ce8-6a28eda5f67a'
# Uncomment below to setup prefix (e.g. Bearer) for API key, if needed
# configuration.api_key_prefix['Apikey'] = 'Bearer'
# create an instance of the API class
api_instance = cloudmersive_convert_api_client.ConvertDocumentApi(
cloudmersive_convert_api_client.ApiClient(configuration))
input_file = pptx_input # file | Input file to perform the operation on.
try:
# Convert PowerPoint PPTX to PNG image array
api_response = api_instance.convert_document_pptx_to_png(input_file)
url = api_response.png_result_pages[0].url
return url
except ApiException as e:
print(
"Exception when calling ConvertDocumentApi->convert_document_pptx_to_png: %s\n"
% e)
def uploaded_file(filename, s, e):
import fitz
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files (x86)\Tesseract-OCR\tesseract.exe"
pdffile = filename
doc = fitz.open('static' + '/' + filename)
for i in range(int(s) - 1, int(e)):
page = doc.loadPage(i) # number of page
pix = page.getPixmap()
output = "outfile" + str(i) + ".png"
pix.writePNG(output)
x = ''
for i in range(int(s) - 1, int(e)):
x += pytesseract.image_to_string(f'outfile{str(i)}.png')
from PyDictionary import PyDictionary
from summa import keywords
from summa.summarizer import summarize
import nltk
from nltk.tokenize import sent_tokenize
from docx import Document
f = x
b = str(filename.replace('.pdf', ''))
a = x
a = keywords.keywords(a)
dictionary = PyDictionary()
a = a.split('\n')
a1 = []
for i in a:
x = i.split(' ')
for j in x:
a1.append(j)
a1.sort(key=lambda s: len(s))
a1.reverse()
try:
a1 = a1[:20]
except:
pass
a = set(a1)
a = tuple(a1)
a1 = []
for i in range(10):
try:
a1.append(a[i])
except:
pass
from nltk.stem import WordNetLemmatizer
lemmatizer = WordNetLemmatizer()
a = a1
a1 = []
for i in a:
a1.append(lemmatizer.lemmatize(i))
a = list(set(a1))
a1 = a
a = [dictionary.meaning(i) for i in a1]
z = sent_tokenize(summarize(f, ratio=0.25))
doc = Document()
doc.add_heading('Notes for ' + b, 0)
for i in z:
doc.add_paragraph(i)
doc.add_heading('Vocab Words from ' + b, 0)
for i in range(len(a)):
c = doc.add_paragraph(str(i + 1) + ') ')
c.add_run(a1[i]).bold = True
c.add_run(': ')
d = str(list(a[i].values()))
d = d.replace('[', '')
d = d.replace(']', '')
c.add_run(d)
g = doc.add_paragraph('')
g.add_run('Synonyms for ')
g.add_run(a1[i].upper() + ': ').bold = True
from datamuse import datamuse
api = datamuse.Datamuse()
s = api.words(ml=a1[i], max=10)
s1 = []
for i in s:
for j in i:
if j == 'word':
s1.append(i[j])
g.add_run(str(s1).replace('[',
'').replace(']',
'').replace("'",
'')).italic = True
whitelist = set('abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ')
fileName = b.replace(' ', '')
fileName = ''.join(filter(whitelist.__contains__, fileName))
fileName += '.docx'
doc.save(fileName)
import cloudmersive_convert_api_client
from cloudmersive_convert_api_client.rest import ApiException
configuration = cloudmersive_convert_api_client.Configuration()
configuration.api_key['Apikey'] = 'f0c513bc-8c00-4491-830e-3e83b015feb6'
api_instance = cloudmersive_convert_api_client.ConvertDocumentApi(
cloudmersive_convert_api_client.ApiClient(configuration))
try:
# Convert Word DOCX Document to PDF
api_response = api_instance.convert_document_docx_to_pdf(fileName)
file = open('static/' + fileName.replace('.docx', '.pdf'), 'wb')
file.write(api_response)
file.close()
except ApiException as e:
print(
"Exception when calling ConvertDocumentApi->convert_document_docx_to_pdf: %s\n"
% e)
myFile = fileName.replace('.docx', '.pdf')
myFile2 = myFile
note = Note(noteFile=str(myFile2), creator=current_user)
db.session.add(note)
db.session.commit()
myFile = url_for('.static', filename=myFile)
return render_template('notes.html', myFile=myFile)
#pdfdoc
# pip install cloudmersive-convert-api-client
from __future__ import print_function
import time
import cloudmersive_convert_api_client
from cloudmersive_convert_api_client.rest import ApiException
from pprint import pprint
# Configure API key authorization: Apikey
configuration = cloudmersive_convert_api_client.Configuration()
configuration.api_key['Apikey'] = 'YOUR_API_KEY'
# Uncomment below to setup prefix (e.g. Bearer) for API key, if needed
# configuration.api_key_prefix['Apikey'] = 'Bearer'
# create an instance of the API class
api_instance = cloudmersive_convert_api_client.ConvertDocumentApi(
cloudmersive_convert_api_client.ApiClient(configuration))
input_file = 'ALL.pdf' # file | Input file to perform the operation on.
try:
# Convert PDF to Word DOCX Document
api_response = api_instance.convert_document_pdf_to_docx(input_file)
pprint(api_response)
except ApiException as e:
print(
"Exception when calling ConvertDocumentApi->convert_document_pdf_to_docx: %s\n"
% e)
def notes():
from PyDictionary import PyDictionary
from summa import keywords
from summa.summarizer import summarize
import nltk
from nltk.tokenize import sent_tokenize
from newspaper import Article
from docx import Document
url = str(request.form['link'])
a = Article(url)
a.download()
a.parse()
f = a.text
b = a.title
a = a.text
a = keywords.keywords(a)
dictionary = PyDictionary()
a = a.split('\n')
a1 = []
for i in a:
x = i.split(' ')
for j in x:
a1.append(j)
a1.sort(key=lambda s: len(s))
a1.reverse()
try:
a1 = a1[:20]
except:
pass
a = set(a1)
a = tuple(a1)
a1 = []
for i in range(10):
try:
a1.append(a[i])
except:
pass
from nltk.stem import WordNetLemmatizer
lemmatizer = WordNetLemmatizer()
a = a1
a1 = []
for i in a:
a1.append(lemmatizer.lemmatize(i))
a = list(set(a1))
a1 = a
a = [dictionary.meaning(i) for i in a1]
z = sent_tokenize(summarize(f, ratio=0.25))
doc = Document()
doc.add_heading('Notes for ' + b, 0)
for i in z:
doc.add_paragraph(i)
doc.add_heading('Vocab Words from ' + b, 0)
for i in range(len(a)):
c = doc.add_paragraph(str(i + 1) + ') ')
c.add_run(a1[i]).bold = True
c.add_run(': ')
d = str(list(a[i].values()))
d = d.replace('[', '')
d = d.replace(']', '')
c.add_run(d)
g = doc.add_paragraph('')
g.add_run('Synonyms for ')
g.add_run(a1[i].upper() + ': ').bold = True
from datamuse import datamuse
api = datamuse.Datamuse()
s = api.words(ml=a1[i], max=10)
s1 = []
for i in s:
for j in i:
if j == 'word':
s1.append(i[j])
g.add_run(str(s1).replace('[',
'').replace(']',
'').replace("'",
'')).italic = True
whitelist = set('abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ')
fileName = b.replace(' ', '')
fileName = ''.join(filter(whitelist.__contains__, fileName))
fileName += '.docx'
doc.save(fileName)
import cloudmersive_convert_api_client
from cloudmersive_convert_api_client.rest import ApiException
configuration = cloudmersive_convert_api_client.Configuration()
configuration.api_key['Apikey'] = 'f0c513bc-8c00-4491-830e-3e83b015feb6'
api_instance = cloudmersive_convert_api_client.ConvertDocumentApi(
cloudmersive_convert_api_client.ApiClient(configuration))
try:
# Convert Word DOCX Document to PDF
api_response = api_instance.convert_document_docx_to_pdf(fileName)
file = open('static/' + fileName.replace('.docx', '.pdf'), 'wb')
file.write(api_response)
file.close()
except ApiException as e:
print(
"Exception when calling ConvertDocumentApi->convert_document_docx_to_pdf: %s\n"
% e)
myFile = fileName.replace('.docx', '.pdf')
myFile2 = myFile
note = Note(noteFile=str(myFile2), creator=current_user)
db.session.add(note)
db.session.commit()
myFile = url_for('.static', filename=myFile)
return render_template('notes.html', myFile=myFile)