ttps://www.tokyo-tc.com/h_list_kouma.html からとる

tosara_get_from_html.pl

#!perl

# 読み飛ばす
while (<>) {
  last if /<div class="horseList">/;
}

# テーブルをばらす
while (<>) {
  if (/<h4 class="name">/) {
    s/<.+?>//g;
    s/\s//g;
    $name = $_;
  } elsif (m|<p class="seiseki">年齢：1　性別：(.+)　毛色：(.+)毛|) {
    $sex = $1;
    $keiro = $2;
  } elsif (m|>父</span>(.+?)</p>|) {
    $sire = $1;
  } elsif (m|>母</span>(.+?)</p>|) {
    $mare = $1;
  } elsif (m|>母父</span>(.+?)</p>|) {
    $bms = $1;
  } elsif (m|>所属</span>(.+?)</p>|) {
    $area = $1;
  } elsif (m|>厩舎</span>(.+?)</p>|) {
    $stable = $1;
  } elsif (m|>育成牧場</span>.+>(.+)</span>|) {
    $farm = $1
  } elsif (m|一口出資額</span><strong class="red2">(\d+),000</|) {
    $price = int($1) * 1000;
    # ここで表示
    $line = join("\t", ($name, $sex, $price, $sire, $mare, $bms, $area, $stable, $farm, $keiro)) . "\n";
    $line =~ s/&#039;/'/g;
    print $line;
  }
}