概要
PHPSimpleHtmlDomParserを用いたニコニコ生放送公式ランキングのスクレイピング
コード
OfficialRankingScraper.class.php
<?php
require_once("./simple_html_dom.php");
class OfficialRankingScraper
{
const OFFICIAL_RANKING_URL = "http://live.nicovideo.jp/ranking";
private $user,$official;
public function __construct(){
}
public function getUser(){
$this->makeUser();
return $this->user;
}
public function getOfficial(){
$this->makeOfficial();
return $this->official;
}
private function makeUser(){
$html = file_get_html(self::OFFICIAL_RANKING_URL);
$stream_array = array();
foreach($html->find('div[class=user clearfix spriteIcon ranking_video]') as $i => $element) {
$rank = ($i + 1);
$community = $element->find('span[class=comName]',0);
$community_name = $community->plaintext;
$community_url = $community->find('a',0)->href;
$tmp = explode('/',$community_url);
$community_id = $tmp[4];
$user = $element->find('span[class=name]',0);
$user_name = $user->plaintext;
$user_url = $user->find('a',0)->href;
$viewer = $element->find('li[class="audience spriteIcon"]',0)->plaintext;
$comment = $element->find('li[class="coment spriteIcon"]',0)->plaintext;
$title = $element->find('span[class="video_title"]',0)->plaintext;
$thumbnail = $element->find('div[class="info"]',0)->find('img',0)->src;
$stream_url = $element->find('div[class="info"]',0)->find('a',0)->href;
$stream_url = "http://live.nicovideo.jp/".$stream_url;
$active = $element->find('span[class="score"]',0)->plaintext;
$stream_array[] = array(
'rank' => $rank,
'community_id' => $community_id,
'community_url' => $community_url,
'community_name' => $community_name,
'user_name' => $user_name,
'user_url' => $user_url,
'viewer' => $viewer,
'comment' => $comment,
'title' => $title,
'thumbnail' => $thumbnail,
'stream_url' => $stream_url,
'active' => $active
);
}
$this->user = $stream_array;
}
private function makeOfficial(){
$html = file_get_html(self::OFFICIAL_RANKING_URL);
$stream_array = array();
foreach($html->find('ul[class="active clearfix"] li') as $i => $element) {
$rank = ($i + 1);
$viewer = $element->find('div[class="audience spriteIcon"]',0)->plaintext;
$comment = $element->find('div[class="coment spriteIcon"]',0)->plaintext;
$title = $element->find('p a',0)->plaintext;
$thumbnail = $element->find('div[class="rankNumber"]',0)->find('img',0)->src;
$stream_url = $element->find('div[class="rankNumber"]',0)->find('a',0)->href;
$stream_url = "http://live.nicovideo.jp/".$stream_url;
$stream_id = $this->makeStreamId($stream_url);
$stream_array[] = array(
'rank' => $rank,
'viewer' => $viewer,
'comment' => $comment,
'title' => $title,
'thumbnail' => $thumbnail,
'stream_url' => $stream_url,
'stream_id' => $stream_id
);
}
$this->official = $stream_array;
}
private function makeStreamId($stream_url){
$stream_id = "";
$slash = explode("/", $stream_url);
$hatena = explode("?",$slash[4]);
$stream_id = $hatena[0];
return $stream_id;
}
}
?>
サンプルコード
sample.php
<?php
require_once("OfficialRankingScraper.class.php");
$scraper = new OfficialRankingScraper();
print_r($scraper->getOfficial());
print_r($scraper->getUser());
?>
結果
result
Array
(
[0] => Array
(
[rank] => 1
[viewer] => 77,592
[comment] => 64,730
[title] => 【衆議院 国会生中継】 ～平成25年3月18日 予算委員会～
[thumbnail] => http://nl.simg.jp/img/a2/4539.198de4.jpg
[stream_url] => http://live.nicovideo.jp/watch/lv130208276?ref=rnk_active&zroute=ranking&provider_type=official_and_channel
[stream_id] => lv130208276
)
[1] => Array
(
[rank] => 2
[viewer] => 41,713
[comment] => 17,362
[title] => 向谷実のニコニコ生レコーディング配信Vol.03（1日目）
[thumbnail] => http://nl.simg.jp/img/a55/164883.9cec79.jpg
[stream_url] => http://live.nicovideo.jp/watch/lv129102517?ref=rnk_active&zroute=ranking&provider_type=official_and_channel
[stream_id] => lv129102517
)
[2] => Array
(
[rank] => 3
[viewer] => 9,189
[comment] => 1,684
[title] => 《暴力問題と助成金不正使用問題で会見》全日本柔道連盟理事会後記者会見
[thumbnail] => http://nl.simg.jp/img/a56/165855.ba88d9.jpg
[stream_url] => http://live.nicovideo.jp/watch/lv130578293?ref=rnk_active&zroute=ranking&provider_type=official_and_channel
[stream_id] => lv130578293
)
...
)
Array
(
[0] => Array
(
[rank] => 1
[community_id] => co1406335
[community_url] => http://com.nicovideo.jp/community/co1406335
[community_name] => モロちゃんねる(´・ω・｀)
[user_name] => モロ
[user_url] => http://www.nicovideo.jp/user/4770536
[viewer] => 6,855
[comment] => 21,927
[title] => JKが全力で雑談∠( ∵ )／
[thumbnail] => http://icon.nimg.jp/community/s/140/co1406335.jpg?1362519204
[stream_url] => http://live.nicovideo.jp/watch/lv130537400?&zroute=ranking&provider_type=community
[active] => 138
)
[1] => Array
(
[rank] => 2
[community_id] => co1893195
[community_url] => http://com.nicovideo.jp/community/co1893195
[community_name] => 金バエリローデッド
[user_name] => まこと
[user_url] => http://www.nicovideo.jp/user/31151811
[viewer] => 3,988
[comment] => 2,250
[title] => 大雨だからロケは中止して雑談
[thumbnail] => http://icon.nimg.jp/community/s/189/co1893195.jpg?1363460057
[stream_url] => http://live.nicovideo.jp/watch/lv130593299?&zroute=ranking&provider_type=community
[active] => 61
)
[2] => Array
(
[rank] => 3
[community_id] => co1705340
[community_url] => http://com.nicovideo.jp/community/co1705340
[community_name] => 哲学とは哲学であるm9・｀ω・)ﾋﾞｼｯ!!【命の章】
[user_name] => ティロ・フィナーレ加川 放送用
[user_url] => http://www.nicovideo.jp/user/28450199
[viewer] => 12,717
[comment] => 2,521
[title] => 初めてのFX
[thumbnail] => http://icon.nimg.jp/community/s/170/co1705340.jpg?1363370871
[stream_url] => http://live.nicovideo.jp/watch/lv130583371?&zroute=ranking&provider_type=community
[active] => 60
)
...
)