oliver-batey

import parse_file as dp

#define paths to test files
txt_path = 'test_txt.txt'
docx_path = 'test_docx.docx'
pdf_path = 'test_pdf.pdf'
html_path = 'test_html.html'
pptx_path = 'test_pptx.pptx'

file_paths = [txt_path,docx_path,pdf_path,html_path,pptx_path]

oliver-batey

import os 
import io
from docx import Document

from pdfminer3.layout import LAParams, LTTextBox
from pdfminer3.pdfpage import PDFPage
from pdfminer3.pdfinterp import PDFResourceManager
from pdfminer3.pdfinterp import PDFPageInterpreter
from pdfminer3.converter import PDFPageAggregator
from pdfminer3.converter import TextConverter

oliver-batey

import os
from docx import Document

class DocParser:
    def parse(self,document):
        parser = get_format(document)
        return parser(document)

def get_format(document):
    format = os.path.splitext(document)[-1]

oliver-batey

def serialise_file(document,format):
    
    if format =='txt':
        with open(document, 'r') as file:
            string = file.read().replace('\n', ' ')
        return string 
        
    elif format == 'docx'
        #docx parsing code here
        

oliver-batey

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from textblob import TextBlob


def sentiment_polarity(string: str) -> float:
    polarity = TextBlob(string).sentiment[0]
    return polarity

oliver-batey

import numpy as np
import pandas as pd
from textacy import extract, make_spacy_doc

# Load the entire article text
with open("news_article.txt", "r") as file:
    data = file.read().replace("\n", "")
article = data.replace(u"\xa0", u" ")

# Create doc object

oliver-batey

from itertools import count

import matplotlib.pyplot as plt
import networkx as nx
import numpy as np
import pandas as pd
import textacy

with open("news_article.txt", "r") as file:
    data = file.read().replace("\n", "")

oliver-batey

from typing import List, Tuple

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from matplotlib.axes import Axes
from textacy import extract, make_spacy_doc


def decompose_keyterms(keyterm_list: List[str]) -> Tuple:

oliver-batey

#Scrape profile and get recent posts
natgeo = Profile('natgeo')
natgeo.scrape()
recents = natgeo.get_recent_posts()

#Filter list to separate images from videos
recent_photos = [post for post in recents if not post.is_video]

#Save photos in a loop
for i, post in enumerate(recent_photos):

oliver-batey

from instascrape import Hashtag
#Substitute 'ad' with the word you 
#want to search for (as a string)
hashtag = Hashtag('ad')
  
#Scrape the profile
hashtag.scrape()
  
#Get list of the recent posts
recents = hashtag.get_recent_posts()