Skip to content

Commit

Permalink
Update scraper.php
Browse files Browse the repository at this point in the history
  • Loading branch information
csomakk committed Apr 17, 2016
1 parent 2ac6c0d commit 87c38bb
Showing 1 changed file with 9 additions and 7 deletions.
16 changes: 9 additions & 7 deletions scraper.php
Expand Up @@ -3,10 +3,11 @@
require 'scraperwiki/simple_html_dom.php';
$page_counter = 0;
$next_page = FALSE;

do {
$kovetkezo = "";
$page_counter++;
$pageurl = "http://www.hasznaltauto.hu/talalatilista/auto/T4R1C47G6M6KO453QWL61U465TH1433L37CE8R6FPALFLUZK9LOS29KWSTKGAGG1YDMOK293ARIFGK0Y542OAP4J12J924F733LZYMLZA2034LIC7POTK4JZD6QYQEC3M531E53JAQIZHCPGFDJRP807HPDQRAE8F7M8H1SPJW1A390GCJIWT8PHECIHZO3F6IPI9O/page{$page_counter}";
$pageurl = "http://www.hasznaltauto.hu/talalatilista/auto/0P5EDPTSFJF2GPQWMZ8FE4PFQ0AEPWW8WTD7U5FKC38K84H2R8G1OR2Z102S3SSE9LJG2ORW356KS2I9QPOG3CPYEOYROPKTWW8H9J8H3OIWP86DTCG02PYHLFM9M7DWJQWE7QWY3M6HADCSKLY5CUITACLM537UKTJUAE1CYZE3WRISDY6Z0UCA7D6AHGWKF6C6RG/page{$page_counter}";

$html_content = scraperWiki::scrape($pageurl);

Expand All @@ -20,25 +21,26 @@
foreach ($talalat->find("div.talalati_lista_vetelar strong") as $ar) {
$ar = str_replace(" ", " ", $ar->innertext);
}
foreach ($talalat->find("div.talalati_lista_infosor") as $info) {
foreach ($talalat->find("p.talalati_lista_infosor") as $info) {
$info = str_replace("–", ",", $info->innertext);
$info = str_replace(" ", " ", $info);
$info = str_replace("³", "3", $info);
$info = explode(",",$info);
}
///foreach ($talalat->find("div.felszereltseg") as $felszereltseg) {
// $felszereltseg = str_replace(" ", " ", $felszereltseg->innertext);
//}
foreach ($talalat->find("div.felszereltseg") as $felszereltseg) {
$felszereltseg = str_replace(" ", " ", $felszereltseg->innertext);
}

scraperwiki::save(
array('id'),
array(
'id' => $kod,
'id' => $kod * 100000000 + "-" + date("Y/m/d"),
'kod' => $kod,
'type' => $el->innertext,
'price' => $ar,
'info' => $info,
'url' => $url,
// 'felsz' => $felszereltseg,
'felsz' => $felszereltseg,
'crapedate' => date("Y/m/d"),
)
);
Expand Down

0 comments on commit 87c38bb

Please sign in to comment.