Created
July 9, 2011 15:35
-
-
Save toritori0318/1073673 to your computer and use it in GitHub Desktop.
はてぶのトップからperlタグをたどってエントリのリンク先からテキストのみ抽出
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
use strict; | |
use Scrappy; | |
my $s = Scrappy->new; | |
# 1秒間隔でクロール | |
$s->pause(1); | |
# ファイルにログを保存 | |
$s->logger->file('scrappy.log'); | |
# クロール実行 | |
$s->crawl('http://b.hatena.ne.jp/', | |
# 1. root | |
'/' => { | |
# 「タグ一覧」へのリンク | |
'//a[ @href="/t" ]' => sub { | |
my ($self, $item) = @_; | |
$self->queue->add($item->{href}); | |
} | |
}, | |
# 2. タグ一覧 | |
'/t' => { | |
# 2.1. 「perl」タグを見つけてキューにpush | |
'//a[ @href="/t/perl" ]' => sub { | |
my ($self, $item) = @_; | |
$self->queue->add($item->{href}); | |
} | |
}, | |
# 3. タグ(perl) | |
'/t/:tag' => { | |
# 3.1. エントリのリンクをたどって、リンク先のテキスト部分のみを標準出力 | |
'body' => sub { | |
my ($self, $item, $args) = @_; | |
# エントリのリンクを抜き出すxpath | |
my $entries = $self->select('//div[@class="entry-body"]/h3/a'); | |
for my $entry (@{$entries->data}) { | |
$s->log('info', "found entry: " . $entry->{title}); | |
# 別サイトの場合はインスタンス作る | |
my $sd = Scrappy->new; | |
$sd->get($entry->{href}); | |
print $sd->page_text, "\n"; | |
} | |
}, | |
# 3.2. 「次へ」リンクをキューにpush | |
'//a[ @class="pager-next" ]' => sub { | |
my ($self, $item) = @_; | |
print "goto next page... \n"; | |
$self->queue->add($item->{href}); | |
}, | |
}, | |
); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment