Spaces:
Runtime error
Runtime error
File size: 3,824 Bytes
a93b356 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 |
# To read the PDF
import PyPDF2
# To analyze the PDF layout and extract text
from pdfminer.high_level import extract_pages, extract_text
from pdfminer.layout import LTTextContainer, LTChar, LTRect, LTFigure
# To extract text from tables in PDF
import pdfplumber
import os
# Create a function to extract text
def text_extraction(element):
# Extracting the text from the in-line text element
line_text = element.get_text()
# Find the formats of the text
# Initialize the list with all the formats that appeared in the line of text
line_formats = []
for text_line in element:
if isinstance(text_line, LTTextContainer):
# Iterating through each character in the line of text
for character in text_line:
if isinstance(character, LTChar):
# Append the font name of the character
line_formats.append(character.fontname)
# Append the font size of the character
line_formats.append(character.size)
# Find the unique font sizes and names in the line
format_per_line = list(set(line_formats))
# Return a tuple with the text in each line along with its format
return (line_text, format_per_line)
def read_pdf(pdf_path):
# create a PDF file object
pdfFileObj = open(pdf_path, 'rb')
# create a PDF reader object
pdfReaded = PyPDF2.PdfReader(pdfFileObj)
# Create the dictionary to extract text from each image
text_per_page = {}
# We extract the pages from the PDF
for pagenum, page in enumerate(extract_pages(pdfFileObj)):
print("Elaborating Page_" +str(pagenum))
# Initialize the variables needed for the text extraction from the page
pageObj = pdfReaded.pages[pagenum]
page_text = []
line_format = []
text_from_images = []
text_from_tables = []
page_content = []
# Initialize the number of the examined tables
table_num = 0
first_element= True
table_extraction_flag= False
# Open the pdf file
pdf = pdfplumber.open(pdfFileObj)
# Find the examined page
page_tables = pdf.pages[pagenum]
# Find the number of tables on the page
tables = page_tables.find_tables()
# Find all the elements
page_elements = [(element.y1, element) for element in page._objs]
# Sort all the elements as they appear in the page
page_elements.sort(key=lambda a: a[0], reverse=True)
# Find the elements that composed a page
for i,component in enumerate(page_elements):
# Extract the position of the top side of the element in the PDF
pos= component[0]
# Extract the element of the page layout
element = component[1]
# Check if the element is a text element
if isinstance(element, LTTextContainer):
# Check if the text appeared in a table
if table_extraction_flag == False:
# Use the function to extract the text and format for each text element
(line_text, format_per_line) = text_extraction(element)
# Append the text of each line to the page text
page_text.append(line_text)
# Append the format for each line containing text
line_format.append(format_per_line)
page_content.append(line_text)
else:
# Omit the text that appeared in a table
pass
# Create the key of the dictionary
dctkey = 'Page_'+str(pagenum)
# Add the list of list as the value of the page key
text_per_page[dctkey]= [page_text, line_format, text_from_images,text_from_tables, page_content]
# Closing the pdf file object
pdfFileObj.close()
return text_per_page |