$res = $ua->request(HTTP::Request->new("GET", "$uri"));
if(open CACHE, ">:utf8", $cname) {
- print CACHE $res->content;
+ print CACHE $res->decoded_content;
close CACHE;
}
return undef unless $res->is_success;
- return $res->content;
+ return $res->decoded_content;
}
sub getlist
($name) = @_;
$name = ($name =~ /^(the\s+)?(.*)$/i)[1];
- $il = uc(($name =~ /^(.)/)[0]);
+ $il = uc(($name =~ /^\W*(.)/)[0]);
$il = "9" if (!($il =~ /[A-Z]/));
if(!($html = _get "http://www.animenewsnetwork.com/encyclopedia/anime.php?list=$il")) {
return undef;
# The only way to recognize entries that seems sure is to look
# after the "HOVERLINE" class.
- while($html =~ /<A\s.*CLASS=HOVERLINE\s.*HREF=\"([^\"]+)\".*>(\<small\>.*\<\/small\>)?([^<]+)<\//ig) {
- if((substr "" . lc $3 , 0, length $name) eq lc $name) {
- push @ret, $3;
+ while($html =~ /<A\s+CLASS="HOVERLINE"\s+HREF="([^"]+)"[^>]*>(<FONT[^>]*>)?(<small>[^<]*<\/small>)?\s*([^<]+)<\//ig) {
+ if((substr "" . lc $4 , 0, length $name) eq lc $name) {
+ push @ret, $4;
}
}
# push @ret, $1 while $html =~ /<A\s.*CLASS=HOVERLINE\s.*>.*<FONT.*>([^<>]*$name[^<>]*)<\/FONT/ig;
($name) = @_;
$name = ($name =~ /^(the\s+)?(.*)$/i)[1];
- $il = uc(($name =~ /^(.)/)[0]);
+ $il = uc(($name =~ /^\W*(.)/)[0]);
$il = "9" if (!($il =~ /[A-Z]/));
if(!($html = _get "http://www.animenewsnetwork.com/encyclopedia/anime.php?list=$il")) {
return undef;
# The only way to recognize entries that seems sure is to look
# after the "HOVERLINE" class.
- while($html =~ /<A\s.*CLASS=HOVERLINE\s.*HREF=\"([^\"]+)\".*>(\<small\>.*\<\/small\>)?([^<]+)<\//ig) {
- if((substr "" . lc $3 , 0, length $name) eq lc $name) {
+ while($html =~ /<A\s+CLASS="HOVERLINE"\s+HREF="([^"]+)"[^>]*>(<FONT[^>]*>)?(<small>[^<]*<\/small>)?\s*([^<]+)<\//ig) {
+ if((substr "" . lc $4 , 0, length $name) eq lc $name) {
return ($1 =~ /id=(\d+)$/)[0];
}
}
if($html =~ /$kind theme:<\/strong>\s*\n/igc) {
my(@parts, $ct, $buf);
- while($html =~ /\G\s*\<div\>(([^<>]|\<i\>|<\/i>)+)<\/div>/igc) {
+ while($html =~ /\G\s*\<div class=\"tab\"\>(([^<>]|\<i\>|<\/i>)+)(<span[^<>]*>[^<>]*<img[^<>]*>[^<>]*<\/span>)?<\/div>/igc) {
$buf = $1;
- # 0 1 2 3 4 5 6 7 8 9 10 11
- if(@parts = ($buf =~ /(\#(\d+):)?\s*\"([^\"\(]+\S)(\s*\((\<i\>(.*)<\/i>( - \s*)?)?([^<>]+)?\))?\"\s+by\s+([^\(]*[^\(\s])(\s*\(eps (\d+)-(\d+)?\))?/i)) {
+ # 0 1 2 3 4 5 6 7 8 9 10 1112
+ if(@parts = ($buf =~ /(\#(\d+):)?\s*\"([^\"\(]+\S)(\s*\((\<i\>(.*)<\/i>( - \s*)?)?([^<>]+)?\))?\"\s+by\s+([^\(]*[^\(\s])(\s*\(eps? (\d+)(-(\d+))?\))?/i)) {
$ct = {};
$ct->{"num"} = $parts[1] if defined $parts[1];
if(defined $parts[5]) {
$ct->{"ent"} = decode_entities($parts[7]) if defined $parts[7];
$ct->{"prf"} = decode_entities($parts[8]) if defined $parts[8];
$ct->{"fep"} = $parts[10] if defined $parts[10];
- $ct->{"lep"} = $parts[11] if defined $parts[11];
+ $ct->{"lep"} = $parts[12] if defined $parts[12];
push @ret, $ct;
}
}
}
$ret{"url"} = geturl $id;
- ($buf) = ($html =~ /\<TITLE\>Anime News Network - ([^<]*)<\/TITLE>/);
+ ($buf) = ($html =~ /\<title\>([^<]*) - Anime News Network<\/title>/);
if($buf =~ /\([^\)]+\)$/) {
($ret{"name"}, $ret{"type"}) = ($buf =~ /^(.*[^\s])\s*\(([^\)]+)\)$/);
} else {