lap_time_parser.py

import re
import PyPDF2
from collections import defaultdict
import matplotlib.pyplot as plt
import warnings
import seaborn as sns

sns.set()

warnings.filterwarnings('ignore')


riders = [
    'MARQUEZ', 'ROSSI', 'DOVIZIOSO', 'BRADL', 'MORBIDEL', 
    'ESPARGARO', 'PETRUCCI', 'ESPARGARO', 'PIRRO', 'BAGNAI', 
    'RINS', 'NAKAGAMI', 'MILLER', 'MIR', 'RABAT', 'ZARCO', 
    'LORENZO', 'IANNONE', 'ABRAHAM', 'SMITH', 'FOLGER', 'QUARTARARO', 
    'SYAHRIN', 'OLIVEIRA', 'VIÑALES'
]

file = open('laps.pdf', 'rb')
fileReader = PyPDF2.PdfFileReader(file)

laps = defaultdict(list)
lap_time_pattern = "1'[2,3][0-9]\.[0-9]{3}"

for i in range(fileReader.numPages):
    lines = fileReader.getPage(i).extractText().split('\n')
    skip_next = False
    for line in lines:
        for token in line.split(' '):
            if token in riders and line != ', 2018Maverick VIÑALES':
                rider = laps[token]
            if line == ', 2018Maverick VIÑALES':
                skip_next = True
            match = re.match(lap_time_pattern, token)
            
            funky_match = re.match('dT4' + lap_time_pattern, line)
            if funky_match:
                rider.append(funky_match.group(0).replace('dT4', ''))
                
            if match:
                if skip_next:
                    skip_next = False
                else:
                    rider.append(match.group(0))
                    

fig, ax = plt.subplots(figsize=(13, 9))

cnt = 0 
max_riders = 9
max_laps_per_rider = 45
for rider in laps.keys():
    if rider == 'ESPARGARO': continue;
    if cnt == max_riders: break;
    times = sorted([round(float(lap[2:]) + 60, 3) for lap in laps[rider]])[:max_laps_per_rider]
    plt.plot(times, label=rider)
    cnt += 1

ax.set_xlabel('laps')
ax.set_ylabel('lap time')
plt.legend()

plt.savefig('lap_times_11.20.2018.png')