Last active
December 11, 2015 19:28
-
-
Save mapyo/4648606 to your computer and use it in GitHub Desktop.
まともサイトの画像&リンクをとって来て、htmlファイルにまとめてしまうやつ。
This file contains 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
<?php | |
//URLは画像とリンクを取得したいURLを入れてください。 | |
$url="http://matome.naver.jp/odai/2127242472660703301"; | |
$res=@file_get_contents($url); | |
while($res){ | |
$data=getData($res); | |
for($i=0; $i<count($data["span"]); $i++){ | |
echo "<a href='" . $data["span"][$i]->a["href"] . "'>\n"; | |
echo "<img src='".$data["image"][$i]["src"]."'>\n"; | |
echo "</a>\n"; | |
} | |
/* | |
foreach($data["image"] as $image){ | |
echo "<img src='".$image["src"]."'>\n"; | |
} | |
*/ | |
if($data["nextPage"]){ | |
$res=@file_get_contents($url."?page=".$data["nextPage"]); | |
sleep(1); //サーバへの負荷対策 | |
}else{ | |
break; | |
} | |
} | |
function getData($html){ | |
$dom=@DOMDocument::loadHTML($html); | |
$xml=simplexml_import_dom($dom); | |
$result["image"]=$xml->xpath("//img[@class='MTMItemThumb']"); | |
//var_dump($result["image"][0]["src"]); | |
$result["span"]=$xml->xpath("//span[@class='mdMTMWidget01ItemCite01Value']"); | |
//var_dump($result["span"][0]->a["href"]); | |
$pager=$xml->xpath("//div[@class='MdPagination03']"); | |
$current_page=$pager[0]->strong; //太字ページ番号の値 | |
$last_anchor=$pager[0]->a[count($pager[0]->a)-1]; //実際の | |
if($last_anchor + 1 != $current_page){ //太字のページ番号が最後のページをさしていなければ。。。 | |
$result["nextPage"]=$current_page + 1; | |
}else{ | |
$result["nextPage"]=null; | |
} | |
return $result; | |
} | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment