ParserQuiénEstáDelanteDeTi - MECD Premio Nacional Fin de Carrera

fuck.py

import re
import PyPDF2

path_file = "..."

media_pond = 11.23
meritos = 0.9

file = open(path_file, "rb")
pdfReader = PyPDF2.PdfFileReader(file)
above = 0
fuck = 0
for i in range(5, 49):
    t = pdfReader.getPage(i).extractText().replace(" ", "").split("\n")
    cont = -1
    for s in t:
        if "INGENIERÍAY" == s:
            cont = 0
            prev = 0
            continue
        if cont == -1:
            continue
        try:
            f = float(re.sub(r'[A-Za-z]', '', s.replace(",", ".")))
            if (f < 15.) and (f > 0.0):
                cont += 1
        except:
            continue
        if cont == 4:
            if (prev + f > media_pond + meritos):
                fuck += 1
            cont = -1
        if cont == 3:
            if (f > media_pond):
                above += 1
                prev = f
            else:
                cont = -1
print("total = " + str(above))
print("total fucks = " + str(fuck))
  

This file is meant to parse this document [1]. The string result of parsing is not consistent through all rows, that is why I have a counter checking whether I have found in the same row 2 floats between 0 and 15 before.

[1] http://www.educacionyfp.gob.es/dam/jcr:33f0241f-f886-4c25-9186-6b45bdb181b4/resolucionprovisional.pdf