Extract tables from pdf

Question

I am trying to get data from tables in this pdf . I tried pdfminer and pypdf with little luck, but I can not get the data from the tables.

Here is what one of the tables looks like:

As you can see, some columns are marked with an "x". I am trying to use this table in a list of objects.

This is the code so far, now I am using pdfminer.

# pdfminer test
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice, TagExtractor
from pdfminer.pdfpage import PDFPage, PDFTextExtractionNotAllowed
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter, PDFPageAggregator
from pdfminer.cmapdb import CMapDB
from pdfminer.layout import LAParams, LTTextBox, LTTextLine, LTFigure, LTImage
from pdfminer.image import ImageWriter
from cStringIO import StringIO
import sys
import os


def pdfToText(path):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    fp = file(path, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ''
    maxpages = 0
    caching = True
    pagenos = set()

    records = []
    i = 1
    for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,
                                  caching=caching, check_extractable=True):
        # process page
        interpreter.process_page(page)

        # only select lines from the line containing 'Tool' to the line containing "1 The 'All'"
        lines = retstr.getvalue().splitlines()

        idx = containsSubString(lines, 'Tool')
        lines = lines[idx+1:]
        idx = containsSubString(lines, "1 The 'All'")
        lines = lines[:idx]

        for line in lines:
            records.append(line)
        i += 1

    fp.close()
    device.close()
    retstr.close()

    return records


def containsSubString(list, substring):
    # find a substring in a list item
    for i, s in enumerate(list):
        if substring in s:
            return i
    return -1


# process pdf
fn = '../test1.pdf'
ft = 'test.txt'

text = pdfToText(fn)
outFile = open(ft, 'w')
for i in range(0, len(text)):
    outFile.write(text[i])
outFile.close()

This creates a text file and it receives all the text, but x does not save the interval. The result is as follows:

x only one-part in a text document

, , - html- . OCR, . # , , .

: PDF , , . pdf ( ).

Answer 1

, . , , png pdf, opencv python.

Answer 2

Tabula, , tabula - ( ) .