wow we suck

get-sources.py

__author__ = 'Matthew'

import re
import urllib


def parse_reportlist(filename):
    counter = 999
    urls = []
    with open(filename, 'r') as f:
        matches = re.findall('<a href="https://www.warcraftlogs.com/reports/([a-zA-Z0-9]+)">([^<]+)</a>', f.read())
        for match in matches:
            urls.append((str(counter) + '_' + match[0], 'https://www.warcraftlogs.com/reports/fights_and_participants/' + match[0] + '/0'))
            counter -= 1
    return urls


def download(url, dest):
    print 'Saving', url, 'to', dest,
    with open(dest, 'w+') as f:
        f.write(urllib.urlopen(url).read())
    print 'Done'


for (id, url) in parse_reportlist('reportlist.html'):
    download(url, 'reports/' + id + '.html')

parse-report.py

__author__ = 'Matthew'

import glob
import json


def parse_report(filename):
    data = json.loads(open(filename).read())
    for fight in data['fights']:
        if fight['boss'] == 0:
            continue
        if fight['difficulty'] != 5:
            continue
        yield {'name': fight['name'], 'length': (fight['end_time'] - fight['start_time']) / 1000, 'kill': fight['kill']}


for filename in glob.glob('reports/*.html'):
    for fight in parse_report(filename):
        if fight['name'] == 'Brackenspore':
            if fight['kill']:
                print '--------DONE---------'
            else:
                print fight['length']
                
# Results:  https://project-2501.net/gallery/wow/2015-0202%20brakenspore-attempt-length.png