Datos Caseros.

                                
    import PyPDF2
    pdf = path_data + '/' + file
    archivo_pdf = open(pdf, 'rb')
    pdf_reader = PyPDF2.PdfReader(archivo_pdf)
    contenido_pdf = []
    words = ['NO', 'TIME', 'P', '']
    
    words += ['TheF', 'FORMULA', 'logo,F', 'logo,FORMULA', ',FORMULAONE,F',
                ',FIAFORMULAONEWORLDCHAMPIONSHIP,GRANDPRIXandrelatedmarksaretrademarksofFormulaOneLicensingBV,a', 'Formula',
                'company.TheFIAlogoisatrademarkoftheFédérationInternationaledel', '’', 'Automobile.Allrightsreserved.',
                'Nopartoftheseresults/datamaybereproduced,storedinaretrievalsystemortransmittedinanyformorbyanymeanselectronic,mechanical,photocopying,recording,broadcastingorotherwisewithout',
                'priorpermissionofthecopyrightholderexceptforreproductioninlocal/national/internationaldailypressandregularprintedpublicationsonsaletothepublicwithin',
                '90', 'daysoftheeventtowhichthe',
                'results/datarelateandprovidedthatthecopyrightsymbolandnameofcopyrightownerappears.',
                '©2022FormulaOneWorldChampionshipLimited', 'Page3of3', 'FORMULA1GULFAIRBAHRAINGRANDPRIX2022-Sakhir',
                'FirstPracticeSessionLapTimes', 'LAP']
    pilots = ['Lewis Hamilton', 'Valtteri Bottas', 'Max Verstappen', 'Sergio Perez', 'Lando Norris', 'Oscar Piastri',
                'Charles Leclerc', 'Carlos Sainz', 'Pierre Gasly', 'Yuki Tsunoda', 'Fernando Alonso', 'Esteban Ocon',
                'Nyck DE VRIES', 'Lance Stroll', 'ZHOU Guanyu', 'Logan SARGEANT', 'Kevin MAGNUSSEN', 'Nico HULKENBERG',
                'George Russell', 'Alexander ALBON']
    lap_data = {}
    lap_id = []
    minimum_laps = []
    min_laps_order = []
    
    for i in range(len(pilots)):
        pilots[i] = pilots[i].replace(' ', '').upper()
    
    for pagina in range(len(pdf_reader.pages)):
        pagina_actual = pdf_reader.pages[pagina]
        contenido_pdf.append(pagina_actual.extract_text())
    
    pdf_data = []
    for page in contenido_pdf:
        line_list = page.split('\n')
        data = []
        for i in range(len(line_list)):
            line_list[i] = line_list[i].replace(' ', '')
    
        for line in line_list:
            if line not in words:
                data.append(line)
        pdf_data += data
    
    for i in range(len(pdf_data)):
        if pdf_data[i].upper() in pilots:
            lap_data[pdf_data[i]] = {}
            lap_id.append(i)
    
    for i in range(len(lap_id)):
        start = lap_id[i]
        if i < len(lap_id) - 1:
            end = lap_id[i + 1]
    
        else:
            end = len(pdf_data)
    
        for j in range(start + 1, end, 2):
            lap_num = pdf_data[j]
            if j < len(pdf_data) - 1:
    
                lap_time = pdf_data[j + 1]
                if ':' in lap_time:
                    lap_data[list(lap_data.keys())[i]][int(lap_num)] = lap_time
    
    
    for pilot_id in lap_data:
    
        new_laps = {}
        laps = lap_data[pilot_id]
        lap_order = sorted(list(laps.keys()))
        for l_id in lap_order:
            new_laps[l_id] = laps[l_id]
        lap_data[pilot_id] = new_laps
    
    
        stint = 0
    
        stint_id = 1
        all_laps = []
    
        for num_lap in range(len(lap_data[pilot_id].keys())+1):
            if num_lap == 0:
                continue
            time_str_sec = float(lap_data[pilot_id][num_lap].split(':')[1])
            time_str_min = int(lap_data[pilot_id][num_lap].split(':')[0])
            complete_time = time_str_min*60 + time_str_sec
            all_laps.append(complete_time)
            lap_data[pilot_id][num_lap] = {
                'min' : time_str_min,
                'sec' : time_str_sec,
                'complete' : complete_time
            }
    
    
            if time_str_min >= 2:
                stint += 1
                stint_name =  'E' + str(stint_id)
                stint_id +=1
    
            stint_name = 'E' + str(stint_id)
            stint_name = 'F' + str(stint_id)
            stint_id += 1
            lap_data[pilot_id][num_lap]['stint'] = stint
    
        if len(all_laps)>0:
            min_lap = sorted(all_laps)[0]
            minimum_laps.append([pilot_id,min_lap])
            min_laps_order.append(min_lap)
    
    
    i=0
    min_laps_order.sort()
    new_fast_laps = []
    for lap in min_laps_order:
        filtered = list(filter(lambda x: x[1] == lap, minimum_laps))
        new_fast_laps.append(filtered[0])
    csv = open('f1_data.csv', 'w')
    for pilot_id in lap_data:
        for num_lap in lap_data[pilot_id]:
            lap = lap_data[pilot_id][num_lap]
            line = gp + ';' + session + ';' + pilot_id + ';' + str(num_lap) + ';' +  str(lap['complete'])  + ';' + str(lap['stint']) + '\n'
            csv_data.append(line)
    csv.writelines(csv_data)
    csv.close()