Extractor for http://m-p.sakura.ne.jp/Html/anime.html

moonphaseextractor.py

f = open('MOON PHASE - ANIME.html', 'r')
o = open('output.txt', 'w')

line = True
while line:
    line = f.readline().strip()
    if line == '<tr>':
        line = f.readline().strip()         # Date cell
        try:
            date = line.split('>', 2)[2].split('<', 1)[0]
            line = f.readline().strip()     # Title cell
            title = line.split('>', 3)[3].split('<', 1)[0]
            url = line.split('href="', 1)[1].split('"', 1)[0]
            output = date + ' ' + title + '\n' + url + '\n\n'
            o.write(output)
        except IndexError:     # Wrong format, can't split correctly
            pass
f.close()
o.close()