Created
May 31, 2015 10:01
-
-
Save jimyhuang/e94f9cd5a3fd651a99ed to your computer and use it in GitHub Desktop.
pet-hsz.php
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 | |
$page = 0; | |
$output = ''; | |
`echo '' > /tmp/animal`; | |
while(1) { | |
$url = 'http://animalprotection.hchg.gov.tw/sca/C/Animal.aspx?page='.$page; | |
$doc = new DOMDocument(); | |
$new = new DOMDocument(); | |
$html = @file_get_contents($url); | |
if($html){ | |
@$doc->loadHTML('<?xml encoding="utf-8" ?>'."\n".$html); | |
$xpath = new DOMXPath($doc); | |
$div = $xpath->query('//*[@class="animal_list"]'); | |
foreach ($div as $d){ | |
$cloned = $d->cloneNode(TRUE); | |
$new->appendChild($new->importNode($cloned,TRUE)); | |
} | |
$output = $new->saveHTML(); | |
$output = mb_convert_encoding($output, 'UTF-8', 'HTML-ENTITIES'); | |
file_put_contents("/tmp/animal", $output, FILE_APPEND); | |
} | |
else{ | |
break; | |
} | |
$page++; | |
sleep(3); | |
} | |
// prase to array | |
$c = file_get_contents("/tmp/animal"); | |
$c = str_replace('<div class="animal_list">', '---<div class="animal_list">', $c); | |
$array = explode('---', $c); | |
$header = array(); | |
$rows = array(); | |
$count = 0; | |
foreach($array as $a){ | |
$a = trim($a); | |
if(empty($a)){ | |
continue; | |
} | |
$count++; | |
preg_match('/AnimalsThumb\/(\d+)/i', $a, $matches); | |
$img = $matches[1] ? 'http://animalprotection.hchg.gov.tw/sca/Animals/'.$matches[1].'.JPG' : ''; | |
preg_match('/AnimalDetail\.aspx\?id=(\d+)/i', $a, $ids); | |
$url_detail = !empty($ids[0]) ? 'http://animalprotection.hchg.gov.tw/sca/C/'.$ids[0] : ''; | |
echo "Fetching ... ".$ids[1]."\n"; | |
$animal = file_get_contents($url_detail); | |
if($animal){ | |
$fields = array(); | |
if(!isset($header['id'])){ | |
$header['id'] = 'id'; | |
} | |
$fields['id'] = $ids[1]; | |
preg_match_all("/animal_detail_right_T'>([^<]+)<[^>]+>[^<]*<[^>]+class='animal_detail_right_C'>([^<]+)/i", $animal, $matches); | |
foreach($matches[1] as $k => $m){ | |
if(!empty($m)){ | |
$label = str_replace(":", '', $m); | |
if(!isset($header[$label])){ | |
$header[$label] = $label; | |
} | |
$value = trim(str_replace(' ', '', $matches[2][$k])); | |
$fields[$label] = $value; | |
} | |
} | |
if(!isset($header['圖片'])){ | |
$header['圖片'] = '圖片'; | |
} | |
$fields['圖片'] = $img; | |
$rows[] = $fields; | |
unset($fields); | |
} | |
sleep(3); | |
} | |
array_unshift($rows, $header); | |
/** | |
* Build csv | |
* Install: composer require league/csv | |
*/ | |
require 'vendor/autoload.php'; | |
use League\Csv\Writer; | |
$csv = Writer::createFromFileObject(new SplTempFileObject()); | |
$csv->setEnclosure('"'); | |
$csv->insertAll($rows); | |
$file = $csv->__toString(); | |
file_put_contents('pet-hsz.csv', $file); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment