if (preg_match("/[0-9]+\\.[0-9]+\\.[0-9]+/", $dam->href, $m)) {
$uidDam = $m[0];
$titDam = utf8_encode($dam->plaintext);
$urlInf = $urlBase . $dam->href;
$txtInf = utf8_encode(scraperWiki::scrape($urlInf));
preg_match_all("/((?:Sone :)|(?:.st :)|(?:Nord :)) <B>([^<]+)</u", $txtInf, $m, PREG_SET_ORDER);
foreach ($m as $kv) {
$pos[$kv[1]] = $kv[2];
}
$utmDam = sprintf("%sN %s %s", $pos["Sone :"], $pos["Nord :"], $pos["Øst :"]);
$urlDam = $urlBase . str_replace('index.html', 'basis.txt', $dam->href);
$txtDam = scraperWiki::scrape($urlDam);
$arrDam = explode("\n", $txtDam);
$lenArr = count($arrDam);
for ($i = 2; $i < $lenArr; $i++) {
$row = array();
$ln = $arrDam[$i];
foreach ($fmtSampleFixed as $col => $pos) {
$row[$col] = trim(substr($ln, $pos["offset"], $pos["length"]));
}
if (!is_numeric($row["level"])) {
continue;
}
$row["time"] = sprintf("%s-%s-%s %s:%s:00", substr($row["time"], 0, 2), substr($row["time"], 2, 2), substr($row["time"], 4, 4), substr($row["time"], 9, 2), substr($row["time"], 11, 2));
$row["id_dam"] = $uidDam;
$row["dam"] = $titDam;
$row["utm_pos"] = empty($utmDam) ? "NULL" : $utmDam;
scraperWiki::save(array('id_dam', 'time'), $row);
}
}
}
<?php
# Blank PHP
require 'scraperwiki/simple_html_dom.php';
$i = 1;
$html = scraperWiki::scrape("http://www.quora.com/Placerville-CA/What-is-nightlife-like-in-Placerville-CA");
scraperWiki::save(array('id' => $i), array('id' => $i, 'html' => $html->outertext));
# Blank PHP
require 'scraperwiki/simple_html_dom.php';
$i = 1;
$html = scraperWiki::scrape("http://www.quora.com/Placerville-CA/What-is-nightlife-like-in-Placerville-CA");
scraperWiki::save(array('id' => $i), array('id' => $i, 'html' => $html->outertext));
<?php
require 'scraperwiki/simple_html_dom.php';
$res = scraperWiki::scrape("http://www.onewaytextlink.com/links.php?type=free&pagenum=1");
$html = str_get_html($res);
$id = 0;
foreach ($html->find("a") as $data) {
$record = array('id' => $id, 'url' => $data->href);
scraperWiki::save(array('id'), $record);
$id++;
}
require 'scraperwiki/simple_html_dom.php';
$res = scraperWiki::scrape("http://www.onewaytextlink.com/links.php?type=free&pagenum=1");
$html = str_get_html($res);
$id = 0;
foreach ($html->find("a") as $data) {
$record = array('id' => $id, 'url' => $data->href);
scraperWiki::save(array('id'), $record);
$id++;
}
function grab12($url, $name)
{
$html = scraperWiki::scrape($url);
$html = preg_replace('/<span style="display:none">(\\d+)<\\/span>/', '', $html);
$html = preg_replace('/<span class="\\d+">(\\d+)<\\/span>/', '\\1', $html);
preg_match_all('/\\d+\\.\\d+\\.\\d+\\.\\d+/', $html, $ips);
foreach ($ips[0] as $ip) {
$record = array('ip' => $ip, 'name' => $name);
scraperWiki::save(array('ip'), $record);
}
}
scraperWiki::save(array("id"), $data);
# Fortsett med neste rad...
}
# Ferdig når det ikke er flere rader igjen i $rows.
# Sett inn ekstern fil med Simple HTML DOM-biblioteket:
require "scraperwiki/simple_html_dom.php";
# Hent HTML-koden fra nettstedet og lagre i $h:
$h = scraperWiki::scrape("http://car.espenandersen.no/?data=1");
# Konstruere et tomt HTML-tre og lagre objektet i $tree:
$tree = new simple_html_dom();
# Last HTML-koden fra nettstedet inn i HTML-treet:
$tree->load($h);
# La $tbody representere <tbody>, bruk stien:
$tbody = $tree->find("html body table tbody", 0);
# Dataradene er barn av <tbody>, kall metoden children():
$rows = $tbody->children();
# For hver rad blant dataradene...
foreach ($rows as $row) {
# Gjør klar tom array:
$data = array();
# Fyll arrayen med skrapede data, feltnavn som nøkler:
$data["id"] = $row->find("td", 0)->plaintext;
$data["skolenavn"] = $row->find("td", 1)->plaintext;
$data["kommunenr"] = $row->find("td", 2)->plaintext;
$data["kommune"] = $row->find("td", 3)->plaintext;
$data["inneklima"] = $row->find("td", 4)->plaintext;
# Lagre dataraden (arrayen) til databasen i ScraperWiki:
scraperWiki::save(array("id"), $data);
# Fortsett med neste rad...
}
# Ferdig når det ikke er flere rader igjen i $rows.
