function scrape_related($url)
{
$exists = scraperwiki::select("* from pages where url = '{$url}'");
if (count($exists)) {
print_r($exists);
return;
}
global $counter;
$counter++;
scraperwiki::save_sqlite(array('url'), array('count' => $counter, 'url' => $url), 'pages');
$html_content = scraperwiki::scrape($url);
$html = str_get_html($html_content);
foreach ($html->find('div.related a') as $related) {
scrape_related('http://tunein.com' . $related->href);
}
}
}
}
return null;
}
# Check for pages with no usable data
function fourOhFour($html)
{
if (strpos($html, 'Home not available', 1200) !== false) {
return true;
}
return false;
}
$blacklist = array();
# get an array of the cottage data to scrape
scraperwiki::attach("hoseasons_summary");
$cottData = scraperwiki::select(" COTTAGE_ID, COTTAGE_URL, SLEEPS, BEDROOMS, PETS,COTTAGE_NAME, PRICE_LOW, PRICE_HIGH from 'hoseasons_summary'.SWDATA order by COTTAGE_URL");
$placeholder = scraperwiki::get_var("cottURL");
if ($placeholder != "") {
$index = searchForId($placeholder, $cottData);
$cottData = array_splice($cottData, $index);
}
require 'scraperwiki/simple_html_dom.php';
$dom = new simple_html_dom();
foreach ($cottData as $value) {
$highPrice = "";
$lowPrice = "";
$found = 0;
$count = 0;
scraperwiki::save_var("cottURL", $value['COTTAGE_URL']);
// check the cottage url against the blacklist
foreach ($blacklist as $blItem) {
$routemap = array();
foreach ($routes as $route) {
$routemap[$route['route']]['route'] = $route['route'];
@($routemap[$route['route']]['coords'] .= $route['latitude'] . ',' . $route['longitude'] . ',2357' . "\n");
}
$theroutes = array();
$count = 0;
foreach ($routemap as $a_route) {
$count++;
$r = $a_route['route'];
$c = $a_route['coords'];
$theroutes[] = array('id' => $count, 'route' => $r, 'coords' => $c);
}
scraperwiki::save_sqlite(array("id"), $theroutes);
//Whoops, seems that doing 600 queries in under 80 seconds isn't a smart idea. This scraper attempts to aggregate coordinates into something usable.
scraperwiki::attach("tfl_bus_routes_scraper", "src");
$routes = scraperwiki::select("route, stop_name, latitude, longitude from src.tfl_buses where run = 1 order by sequence asc");
$routemap = array();
foreach ($routes as $route) {
$routemap[$route['route']]['route'] = $route['route'];
@($routemap[$route['route']]['coords'] .= $route['latitude'] . ',' . $route['longitude'] . ',2357' . "\n");
}
$theroutes = array();
$count = 0;
foreach ($routemap as $a_route) {
$count++;
$r = $a_route['route'];
$c = $a_route['coords'];
$theroutes[] = array('id' => $count, 'route' => $r, 'coords' => $c);
}
scraperwiki::save_sqlite(array("id"), $theroutes);
$callback = $_GET['callback'];
if ($callback) {
header("Content-Type: text/javascript; charset=utf8");
echo $callback . "(" . json_encode($alltrips) . ");";
} else {
header("Content-type: application/json");
echo json_encode($alltrips);
}
// {label} {id} {type} {day} {date} {year} {time} {startdate} {latlng} {arasnotaras} {details} {place} {act} {issue} {constitutional} {destf} {address} {days} {destination}
?>
<?php
//$sourcescraper = 'irish_president_engagementstest';
//$s = scraperwiki::scrape($sourcescraper, $limit=250);
// = scraperwiki::attach($sourcescraper, $limit=250);
scraperwiki::attach('irish_president_engagementsjson');
$trips = scraperwiki::select("* from irish_president_engagementsjson.swdata where date > date('now','-7 day');");
$alltrips = array();
foreach ($trips as $trip) {
$tripinfo = $trip["info"];
$triplabel = $trip["label"];
$tripinfo = str_replace('(', '', $tripinfo);
$tripinfo = str_replace(')', ',', $tripinfo);
$triplabel = str_replace('(', '', $triplabel);
$triplabel = str_replace(')', ',', $triplabel);
//print $triplabel;
$trip["info"] = $tripinfo;
$trip["label"] = $triplabel;
$alltrips[] = $trip;
}
//header('Content-type: application/json');
scraperwiki::httpresponseheader('Content-Type', 'application/json', 'charset=utf8');
if ($sort == "" || $sort == "category") {
$pCategory = "";
$data = scraperwiki::select("* from repos order by category,name");
foreach ($data as $d) {
$name = $d["name"];
$link = $d["link"];
$category = $d["category"];
if ($category != $pCategory) {
print "<li data-role=\"list-divider\">{$category}</li>";
}
$pCategory = $category;
print "<li><a href=\"?action=detail&link={$link}\" data-rel=\"dialog\">{$name}</a></li>";
}
}
if ($sort == "alphabet") {
$data = scraperwiki::select("* from repos order by name");
foreach ($data as $d) {
$name = $d["name"];
$link = $d["link"];
print "<li><a href=\"?action=detail&link={$link}\" data-rel=\"dialog\">{$name}</a></li>";
}
}
?>
</ul>
</div><!-- /content -->
<div data-role="footer">
<h4>ofxAddons.com</h4>
</div><!-- /footer -->
</div><!-- /page -->
return $txt;
}
function searchForId($id, $array)
{
foreach ($array as $key => $val) {
if ($val['COTTAGE_URL'] === $id) {
return $key;
}
}
return null;
}
$blacklist = array();
$url = "http://www.coastandcountry.co.uk/cottage-details/";
scraperwiki::attach("coastandcountrycouk");
# get an array of the cottage data to scrape
$cottData = scraperwiki::select("COTTAGE_URL, PRICE_HIGH, PRICE_LOW from 'coastandcountrycouk'.SWDATA order by COTTAGE_URL");
$placeholder = scraperwiki::get_var("cottID");
if ($placeholder != "") {
$index = searchForId($placeholder, $cottData);
$cottData = array_splice($cottData, $index);
}
require 'scraperwiki/simple_html_dom.php';
$dom = new simple_html_dom();
foreach ($cottData as $value) {
scraperwiki::save_var("cottID", $value['COTTAGE_URL']);
// check the cottage url against the blacklist
foreach ($blacklist as $blItem) {
if ($value['COTTAGE_URL'] == $blItem) {
continue 2;
}
}
// </a>
// <a href="webdata/resources/files/DAS-2015-42 12-09.pdf" onmouseover="self.status='';return true;" target="_blank">164 Roslyn Avenue, Blackmans Bay - Representation expiry date is 25 September 2015</a>
// <br>
// <span style="padding-left:25px;">Subdivision of one lot and balance</span>
//</p>
$record = array();
$addressDateAnchor = $thispara->find('a', 1);
$addressDateText = $addressDateAnchor->plaintext;
$parts = explode(' - Representation expiry date is', $addressDateText);
$record['address'] = htmlspecialchars_decode($parts[0] . ', TAS');
$expiry = $parts[1];
$record['on_notice_to'] = date('Y-m-d', strtotime($expiry));
// Set more_info to the DA page because unfortunately the council takes the PDFs down
// $record['info_url'] = $kcbase . $addressDateAnchor->href;
$record['info_url'] = $dapage;
//there's probably a clever way to do this
$record['council_reference'] = explode(' ', trim(strrchr($kcbase . $addressDateAnchor->href, '/'), '/'))[0];
$descriptionspan = $thispara->find('span', 0);
$record['description'] = htmlspecialchars_decode($descriptionspan->plaintext);
$record['date_scraped'] = date('Y-m-d');
$record['comment_url'] = 'mailto:kc@kingborough.tas.gov.au';
// var_dump($record);
$existingRecords = scraperwiki::select("* from data where `council_reference`='" . $record['council_reference'] . "'");
if (count($existingRecords) == 0) {
print "Saving record " . $record['council_reference'] . "\n";
//print_r ($record);
scraperwiki::save(array('council_reference'), $record);
} else {
print "Skipping already saved record " . $record['council_reference'] . "\n";
}
}
}
####################################################################################################################
####################################################################################################################
####################################################################################################################
####################################################################################################################
$originalPrice = "";
$discountedPrice = "";
$calcPercentage = "";
$discountAmount = "";
$percentage = "";
$i = 0;
$blacklist = array();
$url = "http://www.coastandcountry.co.uk/cottage-details/";
scraperwiki::attach("special_offers_coast_and_country_summary_delete");
# get an array of the cottage data to scrape
$cottData = scraperwiki::select("COTTAGE_URL from 'special_offers_coast_and_country_summary_delete'.SWDATA order by COTTAGE_URL");
$placeholder = scraperwiki::get_var("cottID");
if ($placeholder != "") {
$index = searchForId($placeholder, $cottData);
$cottData = array_splice($cottData, $index);
}
require 'scraperwiki/simple_html_dom.php';
$dom = new simple_html_dom();
foreach ($cottData as $value) {
scraperwiki::save_var("cottID", $value['COTTAGE_URL']);
// check the cottage url against the blacklist
foreach ($blacklist as $blItem) {
if ($value['COTTAGE_URL'] == $blItem) {
continue 2;
}
}
scraperwiki::attach("lichfield_cathedral_events", "cathedral");
$cathedral = scraperwiki::select("* from cathedral.swdata");
foreach (scraperwiki::select("* from cathedral.swdata") as $record) {
var_dump($record);
die;
}
/*
$insert_ical = array();
$insert_ical['link'] = $insert['link'];
$insert_ical['DTSTART'] = $strt;
$insert_ical['DTEND'] = $strt+86399;
$insert_ical['FREQ'] = "DAILY";
$insert_ical['BYDAY'] = "";
$insert_ical['WKST'] = "MO";
$insert_ical['COUNT'] = round(($nd-$strt)/86400);
$insert_event = array();
$insert_event['name'] = "";
$insert_event['link'] = "";
$insert_venue = array();
$insert_venue['name'] = "";
$insert_venue['postcode'] = "";
$insert_venue['lat'] = "";
$insert_venue['lng'] = "";
$insert_venue['picture'] = "";
*/
scraperwiki::attach("lichfield_cathedral_events", "cathedral");
$cathedral = scraperwiki::select("* from cathedral.swdata");
foreach (scraperwiki::select("* from cathedral.swdata") as $record) {
var_dump($record);
die;
}
<?php
//scraperwiki::sqliteexecute('create table create_test(a text,b text)');
//$val2="insert into create_test values('$name','$id')";
//scraperwiki::sqliteexecute($val2);
$result = scraperwiki::select('* from tagtable');
//$data=$result[0];
//$data['rank']='2';
print count($result);
//scraperwiki::sqliteexecute('create table create_test(a text,b text)');
//$val2="insert into create_test values('$name','$id')";
//scraperwiki::sqliteexecute($val2);
$result = scraperwiki::select('* from tagtable');
//$data=$result[0];
//$data['rank']='2';
print count($result);
}
print '</outline>';
}
?>
</body>
</opml>
<?php
# Blank PHP
$sourcescraper = 'sr_p3_poddar';
scraperwiki::attach("sr_p3_poddar");
$programs = scraperwiki::select("distinct progId from sr_p3_poddar.swdata");
print '<?xml version="1.0" encoding="UTF-8"?>';
?>
<opml version="1.1">
<head>
<title>Podsändningar i P3</title>
</head>
<body>
<?php
foreach ($programs as $program) {
print '<outline text="' . $program['progId'] . '">';
$pods = scraperwiki::select("* from sr_p3_poddar.swdata where progId=" . $program['progId'] . " limit 5");
foreach ($pods as $pod) {
print '<outline text="' . $pod['description'] . '" URL="' . $pod['url'] . '" type="audio" />';
}
print '</outline>';
}
?>
</body>
</opml>
<?php
# Blank PHP
/*
// för varje aktie
// för varje mäklare
// för varje rek, starta en månad tillbaka
// jämför rek med kurs när nästa rek inträffar (endast vid ändring av rek), eller nuvarande kurs om endast en rek
*/
require 'scraperwiki/simple_html_dom.php';
$stocks = array("AAK - AarhusKarlshamn" => "SSE36273", "ABB - ABB Ltd" => "SSE3966", "ABB U - ABB Ltd U" => "SSE81849", "ACAN B - Acando B" => "SSE981", "ACAP A - ACAP Invest A" => "SSE20016", "ACAP B - ACAP Invest B" => "SSE20017", "ACOM - A-Com" => "SSE4287", "ACTI - Active Biotech" => "SSE877", "ANOD B - Addnode B" => "SSE3887", "ADDT B - Addtech B" => "SSE14336", "AERO B - Aerocrine B" => "SSE41047", "ALFA - Alfa Laval" => "SSE18634", "ALNX - Allenex" => "SSE37656", "AOIL SDB - Alliance Oil Company SDB" => "SSE40583", "ATEL - AllTele" => "SSE66668", "ANOT - Anoto Group" => "SSE5110", "AWP - Arise Windpower" => "SSE74570", "ARTI B - Artimplant B" => "SSE953", "ASP - Aspiro" => "SSE13291", "ASSA B - ASSA ABLOY B" => "SSE402", "AZN - AstraZeneca" => "SSE3524", "ATCO A - Atlas Copco A" => "SSE45", "ATCO B - Atlas Copco B" => "SSE46", "LJGR B - Atrium Ljungberg B" => "SSE1011", "ALIV SDB - Autoliv SDB" => "SSE47", "AZA - Avanza Bank Holding" => "SSE988", "AVEG B - Avega Group B" => "SSE43396", "AXFO - Axfood" => "SSE4590", "AXIS - Axis" => "SSE5150", "BBTO B - B&B TOOLS B" => "SSE793", "BEGR - BE Group" => "SSE37309", "BEIA B - Beijer Alma B" => "SSE875", "BEIJ B - Beijer B" => "SSE792", "BELE - Beijer Electronics" => "SSE5081", "BRG B - Bergs Timber B" => "SSE891", "BETS B - Betsson B" => "SSE5121", "BILI A - Bilia A" => "SSE794", "BILL - Billerud" => "SSE14922", "BIOG B - BioGaia B" => "SSE959", "BINV - BioInvent International" => "SSE13348", "BIOT - Biotage" => "SSE5209", "BORG - Björn Borg" => "SSE40286", "BEF SDB - Black Earth Farming SDB" => "SSE66922", "BOL - Boliden" => "SSE15285", "BONG - Bong" => "SSE892", "BOUL - Boule Diagnostics" => "SSE82889", "BRIN B - Brinova Fastigheter B" => "SSE22922", "BTS B - BTS Group B" => "SSE13288", "BURE - Bure Equity" => "SSE800", "BMAX - Byggmax Group" => "SSE75712", "CAST - Castellum" => "SSE966", "CATE - Catena" => "SSE34362", "CCC - Cavotec" => "SSE84962", "CDON - CDON Group" => "SSE79303", "CEVI - CellaVision" => "SSE40679", "CSN - Cision" => "SSE1056", "CLAS B - Clas Ohlson B" => "SSE4145", "CLA B - Cloetta B" => "SSE63225", "COA - Coastal Contacts" => "SSE70690", "COIC - Concentric" => "SSE82656", "CCOR B - Concordia Maritime B" => "SSE971", "CNTA - Connecta" => "SSE29954", "CONS B - Consilium B" => "SSE803", "CORE - Corem Property Group" => "SSE66929", "CORE PREF - Corem Property Group Pref" => "SSE74282", "CTT - CTT Systems" => "SSE3081", "CYBE - Cybercom Group" => "SSE4345", "DAG - Dagon" => "SSE19210", "DEDI - Dedicare B" => "SSE81878", "DGC - DGC One" => "SSE56154", "DIAM B - Diamyd Medical B" => "SSE18765", "DIOS - Diös Fastigheter" => "SSE34271", "DORO - DORO" => "SSE896", "DUNI - Duni" => "SSE49775", "DURC B - Duroc B" => "SSE4005", "ECEX - East Capital Explorer" => "SSE49615", "ELAN B - Elanders B" => "SSE897", "ELEC - Electra Gruppen" => "SSE66436", "ELUX A - Electrolux A" => "SSE80", "ELUX B - Electrolux B" => "SSE81", "EKTA B - Elekta B" => "SSE806", "ELOS B - Elos B" => "SSE947", "ENEA - Enea" => "SSE1149", "ENRO - Eniro" => "SSE11046", "ENQ - EnQuest PLC" => "SSE75073", "EPCT - EpiCept" => "SSE32838", "ERIC A - Ericsson A" => "SSE100", "ERIC B - Ericsson B" => "SSE101", "ETX - Etrion" => "SSE78547", "EWRK - eWork Scandinavia" => "SSE72798", "FABG - Fabege" => "SSE861", "F*G - Fagerhult" => "SSE903", "FPAR - Fast Partner" => "SSE980", "BALD B - Fast. Balder B" => "SSE4212", "BALD PREF - Fast. Balder pref" => "SSE82823", "FEEL - Feelgood Svenska" => "SSE5053", "FIX B - Fenix Outdoor B" => "SSE905", "FING B - Fingerprint Cards B" => "SSE4870", "FBAB - FinnvedenBulten" => "SSE82239", "FPIP - FormPipe Software" => "SSE72565", "GETI B - Getinge B" => "SSE812", "GVKO B - Geveko B" => "SSE813", "GHP - Global Health Partner" => "SSE59064", "GUNN - Gunnebo" => "SSE816", "HAKN - Hakon Invest" => "SSE32443", "HLDX - Haldex" => "SSE817", "HAV B - Havsfrun Investment B" => "SSE990", "HEBA B - HEBA B" => "SSE991", "HEMX - Hemtex" => "SSE31293", "HM B - Hennes & Mauritz B" => "SSE992", "HEXA B - Hexagon B" => "SSE819", "HPOL B - HEXPOL B" => "SSE55907", "HIQ - HiQ International" => "SSE3540", "HMS - HMS Networks" => "SSE43302", "HOLM A - Holmen A" => "SSE221", "HOLM B - Holmen B" => "SSE222", "HUFV A - Hufvudstaden A" => "SSE820", "HUFV C - Hufvudstaden C" => "SSE821", "HUSQ A - Husqvarna A" => "SSE34913", "HUSQ B - Husqvarna B" => "SSE34915", "HOGA B - Höganäs B" => "SSE824", "IAR B - I.A.R Systems Group" => "SSE2346", "IS - Image Systems" => "SSE3571", "IFS A - Industrial & Financial Syst. A" => "SSE994", "IFS B - Industrial & Financial Syst. B" => "SSE995", "INDU A - Industrivärden A" => "SSE142", "INDU C - Industrivärden C" => "SSE143", "INDT - Indutrade" => "SSE31308", "ICTA B - Intellecta B" => "SSE941", "IJ - Intrum Justitia" => "SSE18962", "INVE A - Investor A" => "SSE160", "INVE B - Investor B" => "SSE161", "ITAB B - ITAB Shop Concept B" => "SSE56940", "JEEV - Jeeves Information Systems" => "SSE3555", "JM - JM" => "SSE13217", "KABE B - KABE B" => "SSE912", "KAHL - KappAhl" => "SSE33359", "KARO - Karo Bio" => "SSE3927", "KDEV - Karolinska Development B" => "SSE81547", "KINV A - Kinnevik A" => "SSE998", "KINV B - Kinnevik B" => "SSE999", "KLOV - Klövern" => "SSE19459", "KLOV PREF - Klövern pref" => "SSE86345", "KNOW - Know IT" => "SSE3219", "KLED - Kungsleden" => "SSE3546", "LAGR B - Lagercrantz Group B" => "SSE14335", "LAMM B - Lammhults Design Group B" => "SSE1049", "LATO B - Latour B" => "SSE914", "LIAB - Lindab International" => "SSE37400", "LOOM B - Loomis B" => "SSE61536", "LUND B - Lundbergföretagen B" => "SSE1012", "LUMI SDB - Lundin Mining Corporation SDB" => "SSE27709", "LUPE - Lundin Petroleum" => "SSE22335", "LUXO SDB - Luxonen SDB" => "SSE1014", "MEAB B - Malmbergs Elektriska B" => "SSE3223", "MEDA A - Meda A" => "SSE917", "MVIR B - Medivir B" => "SSE1020", "MEKO - Mekonomen" => "SSE4986", "MELK - Melker Schörling" => "SSE37472", "MTRO SDB A - Metro International SDB A" => "SSE12429", "MTRO SDB B - Metro International SDB B" => "SSE12430", "MSAB B - Micro Systemation B" => "SSE85846", "MICR - Micronic Mydata AB" => "SSE4714", "MSON A - Midsona A" => "SSE3921", "MSON B - Midsona B" => "SSE3922", "MIDW A - Midway A" => "SSE834", "MIDW B - Midway B" => "SSE835", "MIC SDB - Millicom Int. Cellular SDB" => "SSE24507", "MOB - Moberg Derma" => "SSE79252", "MTG A - Modern Times Group A" => "SSE3598", "MTG B - Modern Times Group B" => "SSE3599", "MORP B - Morphic Technologies B" => "SSE53228", "MQ - MQ Holding" => "SSE76085", "MSC B - MSC Konsult B" => "SSE1023", "MULQ - MultiQ International" => "SSE4359", "NAXS - NAXS Nordic Access Buyout Fund" => "SSE40342", "NCC A - NCC A" => "SSE837", "NCC B - NCC B" => "SSE838", "NMAN - Nederman Holding" => "SSE40347", "NET B - Net Entertainment NE B" => "SSE62494", "NETI B - Net Insight B" => "SSE3871", "NEWA B - New Wave B" => "SSE920", "NIBE B - NIBE Industrier B" => "SSE921", "NOBI - Nobia" => "SSE19095", "NOLA B - Nolato B" => "SSE923", "NDA SEK - Nordea Bank" => "SSE220", "NOMI - Nordic Mines" => "SSE57018", "NSP B - Nordic Service Partn. Holdings" => "SSE51621", "NN B - Nordnet B" => "SSE4872", "NOTE - NOTE" => "SSE25319", "NOVE - Novestra" => "SSE5116", "NTEK B - NOVOTEK B" => "SSE4000", "OASM - Oasmia Pharmaceutical" => "SSE76461", "ODD - Odd Molly International" => "SSE40936", "OEM B - OEM International B" => "SSE927", "OPCO - Opcon" => "SSE2282", "ORX - Orexo" => "SSE31885", "ORI SDB - Oriflame, SDB" => "SSE24227", "ORTI A - Ortivus A" => "SSE1031", "ORTI B - Ortivus B" => "SSE1032", "PAR - PA Resources" => "SSE34961", "PART - PartnerTech" => "SSE1036", "PEAB B - Peab B" => "SSE928", "PHON - Phonera" => "SSE5000", "POOL B - Poolia B" => "SSE3974", "PREC - Precise Biometrics" => "SSE10751", "PREV B - Prevas B" => "SSE1039", "PRIC B - Pricer B" => "SSE1040", "PACT - Proact IT Group" => "SSE4003", "PROB - Probi" => "SSE27701", "PROE B - Proffice B" => "SSE4208", "PROF B - Profilgruppen B" => "SSE929", "RATO A - Ratos A" => "SSE1044", "RATO B - Ratos B" => "SSE1045", "RAY B - RaySearch Laboratories B" => "SSE1063", "RSOF B - ReadSoft B" => "SSE3967", "RABT B - Rederi AB Transatlantic" => "SSE964", "REJL B - Rejlerkoncernen" => "SSE37758", "REZT - Rezidor Hotel Group" => "SSE37352", "RNBS - RNB RETAIL AND BRANDS" => "SSE13467", "RROS - Rottneros" => "SSE930", "RTIM B - Rörvik Timber B" => "SSE1050", "SAAB B - SAAB B" => "SSE1051", "SAGA - Sagax" => "SSE43045", "SAGA PREF - Sagax pref" => "SSE43046", "SAND - Sandvik" => "SSE4928", "SAS - SAS" => "SSE13557", "SCA A - SCA A" => "SSE322", "SCA B - SCA B" => "SSE323", "SCV A - SCANIA A" => "SSE260", "SCV B - SCANIA B" => "SSE261", "SEB A - SEB A" => "SSE281", "SEB C - SEB C" => "SSE282", "SECT B - SECTRA B" => "SSE3083", "SECU B - Securitas B" => "SSE401", "SMF - Semafo" => "SSE84981", "SEMC - Semcon" => "SSE1054", "SENS - Sensys Traffic" => "SSE12241", "SIGM B - Sigma B" => "SSE14531", "SINT - SinterCast" => "SSE1058", "SKA B - Skanska B" => "SSE283", "SKF A - SKF A" => "SSE284", "SKF B - SKF B" => "SSE285", "SKIS B - SkiStar B" => "SSE939", "SOF B - Softronic B" => "SSE1546", "SSAB A - SSAB A" => "SSE300", "SSAB B - SSAB B" => "SSE301", "STFY - StjärnaFyrkant AB" => "SSE1007", "STE A - Stora Enso A" => "SSE2169", "STE R - Stora Enso R" => "SSE2170", "SVIK - Studsvik" => "SSE13094", "SHB A - Sv. Handelsbanken A" => "SSE340", "SHB B - Sv. Handelsbanken B" => "SSE341", "SWEC A - SWECO A" => "SSE1061", "SWEC B - SWECO B" => "SSE1062", "SWED A - Swedbank A" => "SSE120", "SWED PREF - Swedbank pref" => "SSE61365", "SVED B - Svedbergs B" => "SSE935", "SWMA - Swedish Match" => "SSE361", "SOBI - Swedish Orphan Biovitrum" => "SSE36316", "SWOL B - Swedol B" => "SSE55913", "SVOL A - Svolder A" => "SSE936", "SVOL B - Svolder B" => "SSE937", "SYSR - Systemair" => "SSE43007", "TEL2 A - Tele2 A" => "SSE1026", "TEL2 B - Tele2 B" => "SSE1027", "TLSN - TeliaSonera" => "SSE5095", "TIEN - Tieto Oyj" => "SSE4025", "TRAC B - Traction B" => "SSE4963", "TRAD - TradeDoubler" => "SSE31884", "TWW SDB A - Transcom WorldWide SDB A" => "SSE14353", "TWW SDB B - Transcom WorldWide SDB B" => "SSE14354", "TRMO - Transmode Holding" => "SSE82457", "TREL B - Trelleborg B" => "SSE364", "TAGR - Trigon Agri" => "SSE40543", "UNIB SDB - Unibet Group" => "SSE36950", "UFLX B - Uniflex B" => "SSE36986", "WALL B - Wallenstam B" => "SSE945", "VBG B - VBG GROUP B" => "SSE942", "VRG B - Venue Retail Group B" => "SSE946", "WIHL - Wihlborgs Fastigheter" => "SSE29759", "VIT B - Vitec Software Group B" => "SSE5177", "VITR - Vitrolife" => "SSE13469", "VOLV A - Volvo A" => "SSE365", "VOLV B - Volvo B" => "SSE366", "VNIL SDB - Vostok Nafta Investment, SDB" => "SSE41044", "XANO B - XANO Industri B" => "SSE1074", "AF B - ÅF B" => "SSE862", "ORES - Öresund" => "SSE863");
//exit(0);
$sourcescraper = 'aktietips';
scraperwiki::attach($sourcescraper);
$data = scraperwiki::select("stock, by, `to`, date, rec\nfrom `swdata` \nwhere date > '2011-01-01' and date < '2012-05-01' and stock = 'Volvo'\norder by date asc");
$search_maklare = array();
for ($i = 0; $i < count($data); $i++) {
$maklare = $data[$i]["by"];
if (array_key_exists($maklare, $search_maklare) || $maklare == null || $maklare == "") {
continue;
}
$stock = $data[$i]["stock"];
$mrows = getReksFromMaklare($stock, $maklare, $data);
print_r("<b>" . $stock . " av " . $maklare . "</b><br />");
$search_maklare[$maklare] = true;
$kurs1 = -1;
$rek1 = null;
$points = 0;
foreach ($mrows as $row) {
print_r($row["by"] . " (" . $row["date"] . "), rek: " . $row["rec"] . ", riktkurs: " . $row["to"] . "<br />");
<ev:enddate><?php
echo $enddate;
?>
</ev:enddate>
<ev:location>Lichfield Cathedral</ev:location>
<georss:point>52.685556 -1.830556</georss:point>
</item>
<?php
}
?>
</rdf:RDF><?php
// Attach the data
scraperwiki::attach("hhhlich-lichfield-arts-events");
// Get the data
$data = scraperwiki::select("* from swdata limit 10");
//print_r($data);
echo '<?xml version="1.0" encoding="utf-8"?>';
?>
<rdf:RDF
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
xmlns:ev="http://purl.org/rss/1.0/modules/event/"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:georss="http://www.georss.org/georss"
xmlns:creativeCommons="http://backend.userland.com/creativeCommonsRssModule"
xmlns="http://purl.org/rss/1.0/">
<rdf:Description rdf:about="http://lichfieldlive.co.uk/">
<dc:title>Lichfield What's On Importer</dc:title>
<dc:source rdf:resource="http://www.lichfield-cathedral.org/"/>
<dc:creator>Lichfield Community Media</dc:creator>
}
}
return null;
}
# Check for pages with no usable data
function fourOhFour($html)
{
if (strpos($html, 'Home not available', 1200) !== false) {
return true;
}
return false;
}
$blacklist = array();
# get an array of the cottage data to scrape
scraperwiki::attach("bluechip_summary");
$cottData = scraperwiki::select(" COTTAGE_ID, COTTAGE_URL, SLEEPS, BEDROOMS, FEATURES,COTTAGE_NAME, PRICE_LOW from 'bluechip_summary'.SWDATA order by COTTAGE_URL");
$placeholder = scraperwiki::get_var("cottURL");
if ($placeholder != "") {
$index = searchForId($placeholder, $cottData);
$cottData = array_splice($cottData, $index);
}
require 'scraperwiki/simple_html_dom.php';
$dom = new simple_html_dom();
foreach ($cottData as $value) {
$highPrice = "";
$lowPrice = "";
$found = 0;
$count = 0;
scraperwiki::save_var("cottURL", $value['COTTAGE_URL']);
// check the cottage url against the blacklist
foreach ($blacklist as $blItem) {
)</li>
<?php
$orgs[$organization] += 1;
}
print "</ul>";
print "<h2>Organizations contacted</h2><ul>";
foreach ($orgs as $o => $k) {
?>
<li><?php
echo $o;
?>
(<?php
echo $k;
?>
)</li><?php
}
print '</ul>';
$data = scraperwiki::select("count(*) AS c, subject AS s FROM contact INNER JOIN contact_subject ON contact_subject.contact_id=contact.contact_id WHERE behalf='{$w}' GROUP BY subject ORDER BY subject DESC");
print "<h2>Subjects covered</h2><ul>";
foreach ($data as $row) {
extract($row);
?>
<li><?php
echo $s;
?>
(<?php
echo $c;
?>
)</li><?php
}
print "</ul>";
function validateEntry($id)
{
$result = false;
// Set total number of rows
try {
$recordSet = scraperwiki::select("* from data where id ='" . $id . "'");
if (!empty($recordSet[0]['id'])) {
if ($recordSet[0]['surname'] != "") {
$result = true;
}
if ($recordSet[0]['firstname'] != "") {
$result = true;
}
if ($recordSet[0]['fathername'] != "") {
$result = true;
}
}
} catch (Exception $e) {
}
return $result;
}
print_r("start");
scraperwiki::attach("appcelerator_devlink");
// Bootstrap variables
if (!scraperwiki::table_info($name = "swvariables")) {
scraperwiki::save_var('last_page', 0);
}
$lastPage = scraperwiki::get_var('last_page');
if ($lastPage > 0) {
$offset = " OFFSET " . $lastPage;
$counter = $lastPage;
} else {
$offset = "";
$counter = 0;
}
print_r($offset);
$data = scraperwiki::select("* from appcelerator_devlink.swdata LIMIT 1500" . $offset);
foreach ($data as $row) {
$OBJ = array('id' => $row['id'], 'name' => $row['name'], 'company' => $row['company'], 'location' => $row['location'], 'date' => $row['date'], 'url' => $row["url"], 'profile' => $row["profile"], 'twitter' => '', 'klout' => '', 'linkedIn' => '', 'certifications' => '');
// Clean Links
$links = json_decode($row['links']);
foreach ($links as $link) {
if ($link->label == 'Twitter:') {
// Twitter
$twitter = str_replace("@", "", $link->data);
$twitter = preg_replace("/\\s+/", "", $twitter);
$twitter = str_replace("Twitter:", "", $twitter);
$OBJ['twitter'] = $twitter;
// Klout (based on Twitter)
$klout = scraperWiki::scrape('http://api.klout.com/v2/identity.json/twitter?screenName=' . $twitter . '&key=v23b2ddvdf8n5fvap95kk56r');
$klout = json_decode($klout);
$klout = scraperWiki::scrape('http://api.klout.com/v2/user.json/' . $klout->id . '?key=v23b2ddvdf8n5fvap95kk56r');
<style type="text/css">
body {
margin: 0;
padding: 0;
font:0.8em/1.5em "Lucida Grande", "Lucida Sans Unicode", Helvetica, Arial, sans-serif;
}
</style>
</head>
<body>
<div id="map_canvas" style="width: 100%; height: 100%;"></div>
</body>
</html>
<?php
scraperwiki::attach("walsall_warwickshire_food_safety_inspections");
$data = scraperwiki::select("* from walsall_warwickshire_food_safety_inspections.swdata");
foreach ($data as $data) {
if (strlen($data['latlng_lng']) > 0) {
$markers[] = "['<h3>" . addslashes(trim($data['name'])) . "</h3><p>" . $data['rating'] . " stars</p>'," . $data['latlng_lat'] . "," . $data['latlng_lng'] . "]";
}
}
$markers = implode(",", $markers);
?>
<html>
<head>
<script type="text/javascript" src="http://maps.google.com/maps/api/js?sensor=false"></script>
<script src="http://ajax.googleapis.com/ajax/libs/jquery/1.5.2/jquery.min.js" type="text/javascript"></script>
<script type="text/javascript">
jQuery.noConflict();
jQuery(document).ready(function($){
<?php
# Blank PHP
//scraperwiki::sqliteexecute("DROP TABLE last_update");
scraperwiki::sqliteexecute("CREATE TABLE IF NOT EXISTS ll (\n id INTEGER PRIMARY KEY ASC,\n HITs_available int,\n jobs int\n )");
scraperwiki::sqliteexecute("CREATE TABLE IF NOT EXISTS ll (\n id INTEGER PRIMARY KEY ASC,\n HITs_available int,\n jobs int\n )");
//scraperwiki::sqliteexecute('update ll set jobs = 100 AND (set jobs = 200)');
scraperwiki::sqliteexecute('INSERT INTO ll (jobs) VALUES (100), (200), (300)');
scraperwiki::sqlitecommit();
//
$res = scraperwiki::select('* FROM ll');
print_r($res[0]);
//print_r(scraperwiki::show_tables());
//print_r(scraperwiki::table_info($name="last_update"));
# Blank PHP
//scraperwiki::sqliteexecute("DROP TABLE last_update");
scraperwiki::sqliteexecute("CREATE TABLE IF NOT EXISTS ll (\n id INTEGER PRIMARY KEY ASC,\n HITs_available int,\n jobs int\n )");
scraperwiki::sqliteexecute("CREATE TABLE IF NOT EXISTS ll (\n id INTEGER PRIMARY KEY ASC,\n HITs_available int,\n jobs int\n )");
//scraperwiki::sqliteexecute('update ll set jobs = 100 AND (set jobs = 200)');
scraperwiki::sqliteexecute('INSERT INTO ll (jobs) VALUES (100), (200), (300)');
scraperwiki::sqlitecommit();
//
$res = scraperwiki::select('* FROM ll');
print_r($res[0]);
//print_r(scraperwiki::show_tables());
//print_r(scraperwiki::table_info($name="last_update"));
$results["twitter_url"] = $url;
} else {
$results["website_url"] = $url;
}
}
// There are max 3 urls we are interested in
if (sizeof($results) === 4) {
break;
}
}
scraperwiki::save_sqlite(array("id"), $results, "eparlimen_social_links");
}
require 'scraperwiki/simple_html_dom.php';
scraperwiki::sqliteexecute("DELETE FROM eparlimen_social_links");
scraperwiki::attach("eparlimen-constituencies", "urls");
$urls = scraperwiki::select("* FROM urls.eparlimen_constituencies_links");
foreach ($urls as $url) {
$url = str_replace(",%20", "", $url["url"]);
// A hack for a known bad link. This should be in the link scraper, but it's xmas and I have better things to do :)
$html = scraperwiki::scrape($url);
$dom = new simple_html_dom();
$dom->load($html);
$node = $dom->find("ul.wrap_senarai li", 2);
if (is_object($node)) {
$code = $node->children(1)->plaintext;
} else {
echo "Unable to parse {$url}\n";
continue;
}
$results = array("id" => $code);
foreach ($dom->find("div.detail div a") as $data) {
# Blank PHP
$sourceScraper = 'testi-scraper_1';
scraperwiki::attach($sourceScraper);
$data = scraperwiki::select("SELECT * FROM swdata WHERE (Minutes_late > 0)");
print_r($data);
print "<table>";
print "<tr><th>Country</th><th>Years in school</th>";
foreach ($data as $d) {
print "<tr>";
print "<td>" . $d["Primary_code"] . "</td>";
print "<td>" . $d["Actual_time"] . "</td>";
print "</tr>";
}
print "</table>";
print "This is a <em>fragment</em> of HTML.";
# Blank PHP
$sourceScraper = 'testi-scraper_1';
scraperwiki::attach($sourceScraper);
$data = scraperwiki::select("SELECT * FROM swdata WHERE (Minutes_late > 0)");
print_r($data);
print "<table>";
print "<tr><th>Country</th><th>Years in school</th>";
foreach ($data as $d) {
print "<tr>";
print "<td>" . $d["Primary_code"] . "</td>";
print "<td>" . $d["Actual_time"] . "</td>";
print "</tr>";
}
print "</table>";
print "This is a <em>fragment</em> of HTML.";
//scraperwiki::save_var('last_id',55626); //55150
/*scraperwiki::sqliteexecute("delete from info where id>55652");
scraperwiki::sqlitecommit();
die();*/
//get last id
//scraperwiki::save_var('last_id',0);
$last_id = scraperwiki::get_var('last_id', 0);
echo $last_id;
//read the saved tables
scraperwiki::attach("cz_senate_voting_records_downloader_2", "src");
$rows = scraperwiki::select("id from src.swdata where id>{$last_id} order by id");
if (!empty($rows)) {
foreach ($rows as $html) {
//get dom
$dom = new simple_html_dom();
$html2 = scraperwiki::select("* from src.swdata where id={$html['id']}");
$dom->load(str_replace(" ", " ", $html2[0]['html']));
//common part
$div = $dom->find("div[class=wysiwyg]", 0);
//info
$h1 = $div->find('h1', 0);
preg_match('/([0-9]{1,}). schůze/', $h1->innertext, $matches);
$schuze = $matches[1];
preg_match('/([0-9]{1,}). hlasování/', $h1->innertext, $matches);
$hlasovani = $matches[1];
preg_match('/([0-9]{2}).([0-9]{2}).([0-9]{4})/', $h1->innertext, $matches);
$date = implode('-', array($matches[3], $matches[2], $matches[1]));
$p = $div->find('p[class=openingText]', 0);
$p_ar = explode('<br />', $p->innertext);
$name = $p_ar[0];
if (isset($p_ar[1])) {
if (mb_strlen($noidung) > 1000) {
$j++;
@scraperwiki::save_sqlite(array('id'), array('id' => $j . '-' . $src[0]['url'], 'title' => $src[0]['title'], 'url' => $src[0]['url'], 'content' => base64_encode($noidung), 'order' => $j, 'num' => $src[0]['num'], 'reply' => $src[0]['reply']));
}
}
$html->clear();
unset($html);
scraperwiki::save_var('last_id', $i);
}
require 'scraperwiki/simple_html_dom.php';
scraperwiki::attach("s-in-s", "src");
//scraperwiki::save_var('last_id', 1);
//exit();
$id = scraperwiki::get_var('last_id');
for ($i = $id; $i < 1900; $i++) {
$src = scraperwiki::select("* from src.swdata limit {$i},1");
$url = $src[0]['link'];
$url = 'http://sexinsex.net/bbs/' . $url;
$html_content = scraperwiki::scrape($url);
$html = str_get_html($html_content);
$data = array();
$tr = $html->find("div.postmessage div.t_msgfont");
$j = 0;
foreach ($tr as $trr) {
$noidung = $trr->find('div', 0)->innertext;
//$noidung = utf8_encode($noidung);
if (mb_strlen($noidung) > 1000) {
$j++;
@scraperwiki::save_sqlite(array('id'), array('id' => $j . '-' . $src[0]['url'], 'title' => $src[0]['title'], 'url' => $src[0]['url'], 'content' => base64_encode($noidung), 'order' => $j, 'num' => $src[0]['num'], 'reply' => $src[0]['reply']));
}
}
<?php
require 'scraperwiki.php';
require 'scraperwiki/simple_html_dom.php';
$startProductId = scraperwiki::get_var("currentId", -1);
if ($startProductId == -1) {
print "No previous saved position found. Starting from scratch.";
} else {
print "Resuming from product id {$startProductId}\n";
}
scraperwiki::attach("hobbyking_batteryidlist");
$batteries = scraperwiki::select("id from hobbyking_batteryidlist.data where id > {$startProductId} order by id asc");
$remainingCount = count($batteries);
print "Found {$remainingCount} batteries left to be scraped.";
$maxPerRun = 100;
$loopCount = 0;
foreach ($batteries as $bat) {
if ($loopCount > $maxPerRun) {
print "Ending run after {$maxPerRun} iterations.";
break;
}
$productId = $bat['id'];
print "Retrieving " . $productId . "\n";
$html = scraperWiki::scrape("http://www.hobbyking.com/hobbyking/store/uh_viewItem.asp?idProduct={$productId}");
//print $html . "\n";
$dom = new simple_html_dom();
$dom->load($html);
// Get the product data (located in a span tag). Should only be one product data area!
$productDataAreasDom = $dom->find("SPAN[id=prodDataArea]");
$productDataDom = $productDataAreasDom[0];
//print $productData . "\n";
$price = intval(preg_replace('[\\D]', '', $eg));
// scrape price as integer
$mileage = $el->find("span.mileage", 0)->innertext;
$mileage = intval(preg_replace('[\\D]', '', $mileage));
// scrape milage as integer
$distance = $el->find("span.distanceAmount", 0)->innertext;
$distance = intval(preg_replace('[\\D]', '', $distance));
// scrape distance as integer
$url = $el->find("h2 a", 0)->href;
// scrape url
//$url = $el->find("div.vehicleTitle a",0 ); // scrape url ->href;
$advertType = $el->find("span.advertType", 0)->innertext;
$advertcount = scraperwiki::select("count(*) as count from swdata where guid=" . $advertReference);
if ($advertcount[0]['count'] == 1) {
print 'existing record';
$createarray = scraperwiki::select("created as created from swdata where guid=" . $advertReference);
$created = $createarray[0]['created'];
} else {
print 'new record';
$created = date("Ymd");
}
$record_counter++;
$description = $el->find("div.searchResultMainText", 0)->innertext;
// if (strpos($description,"Leather")==0 ) break ;
print $record_counter . "\t" . $advertReference . "\t" . $model . "\t" . $type . "\t" . $year . "\t" . $age . "\t" . $distance . "\t" . $mileage . "\t" . $price . "\t" . $advertType . "\t" . $url . "\n";
// if ($type=="GS") break; //dont save crappy GS models
// if (strpos($model,"ommercial")>0 ) break ; //no commercials allowed
// if (strpos($model,"OMMERCIAL")>0 ) break ; //no commercials allowed
//if (strpos($description," Cloth ")>0 ) break ; //dont save cloth seats
// if ($type=="HSE") break;
// if ($type=="SE") break;
function debug_table($schema, $tname, $showSchema = FALSE)
{
global $DEBUG_TABLES;
if (!$DEBUG_TABLES) {
return;
}
$tablename = $schema . "." . $tname;
$num = scraperwiki::select("count(*) AS n FROM " . $tablename);
print "{$tablename} size: " . $num[0]['n'] . " rows.\n";
if ($showSchema) {
print "{$tablename} schema: ";
$info = scraperwiki::table_info($tablename);
#debug_array($info, "Table_info($tablename)");
foreach ($info as $column) {
print $column['name'] . "(" . $column['type'] . "); ";
}
print "\n";
}
}
foreach ($all_by_area as $item) {
echo '<tr><td>' . $item['name'] . '</td><td>' . $item['area'] . '</td></tr>' . "\n";
}
echo '</table>';
echo '<h2>Landkreise nach Bevölkerungsdichte (Einwohner/km<sup>2</sup>)</h2>';
echo '<table>';
foreach ($all_by_density as $item) {
echo '<tr><td>' . $item['name'] . '</td><td>' . $item['inhab_density'] . '</td></tr>' . "\n";
}
echo '</table>';
$sourcescraper = 'german-landkreise';
scraperwiki::attach($sourcescraper);
$grouped_by_state = scraperwiki::select("state, COUNT(*) AS num FROM swdata GROUP BY state");
$all_by_population = scraperwiki::select("name, inhabitants FROM swdata ORDER BY inhabitants DESC");
$all_by_area = scraperwiki::select("name, CAST(area AS NUMERIC) AS area FROM swdata ORDER BY area DESC");
$all_by_density = scraperwiki::select("name, inhab_density FROM swdata ORDER BY inhab_density DESC");
echo '<h2>Landkreise nach Bundesland</h2>';
echo '<table>';
foreach ($grouped_by_state as $item) {
echo '<tr><td>' . $item['state'] . '</td><td>' . $item['num'] . '</td></tr>' . "\n";
}
echo '</table>';
echo '<h2>Landkreise nach Einwohnerzahl</h2>';
echo '<table>';
foreach ($all_by_population as $item) {
echo '<tr><td>' . $item['name'] . '</td><td>' . $item['inhabitants'] . '</td></tr>' . "\n";
}
echo '</table>';
echo '<h2>Landkreise nach Fläche (km<sup>2</sup>)</h2>';
echo '<table>';
foreach ($all_by_area as $item) {
$vevents = scraperwiki::select("* from ons_release_schedule_ical.vevents limit {$limit} offset {$offset}");
$icalevents = array();
foreach ($vevents as $vevent) {
$icalevent = "BEGIN:VEVENT\nDTSTAMP" . $vevent["DTSTAMP"] . "\nDTSTART" . $vevent["DTSTART"] . "\nX-TITLE:" . $vevent["Title"] . "\nSUMMARY:" . $vevent["Summary"] . "\nDESCRIPTION:Theme: " . $vevent["Theme"] . "\n" . $vevent["Summary"] . "\\nEND:VEVENT\n";
#print_r($icalevent);
$icalevents[] = $icalevent;
}
print "BEGIN:VCALENDAR\nMETHOD:PUBLISH\nVERSION:2.0\nX-WR-CALNAME:ONS Release Calendar\nPRODID:-//Apple Inc.//iCal 4.0.4//EN\nX-APPLE-CALENDAR-COLOR:#B027AE\nX-WR-TIMEZONE:Europe/London\nCALSCALE:GREGORIAN\n" . implode("", $icalevents) . "\nEND:VCALENDAR";
// Derive an ical string of 10 eventss
$querylist = explode("&", getenv("QUERY_STRING"));
$limit = 10;
$offset = 0;
foreach ($querylist as $queryl) {
$ql = explode("=", $queryl);
if ($ql[0] == "limit" && count($ql) == 2) {
$limit = intval($ql[1]);
}
if ($ql[0] == "offset" && count($ql) == 2) {
$offset = intval($ql[1]);
}
}
scraperwiki::httpresponseheader("Content-Type", "text/plain");
scraperwiki::attach('ons_release_schedule_ical');
$vevents = scraperwiki::select("* from ons_release_schedule_ical.vevents limit {$limit} offset {$offset}");
$icalevents = array();
foreach ($vevents as $vevent) {
$icalevent = "BEGIN:VEVENT\nDTSTAMP" . $vevent["DTSTAMP"] . "\nDTSTART" . $vevent["DTSTART"] . "\nX-TITLE:" . $vevent["Title"] . "\nSUMMARY:" . $vevent["Summary"] . "\nDESCRIPTION:Theme: " . $vevent["Theme"] . "\n" . $vevent["Summary"] . "\\nEND:VEVENT\n";
#print_r($icalevent);
$icalevents[] = $icalevent;
}
print "BEGIN:VCALENDAR\nMETHOD:PUBLISH\nVERSION:2.0\nX-WR-CALNAME:ONS Release Calendar\nPRODID:-//Apple Inc.//iCal 4.0.4//EN\nX-APPLE-CALENDAR-COLOR:#B027AE\nX-WR-TIMEZONE:Europe/London\nCALSCALE:GREGORIAN\n" . implode("", $icalevents) . "\nEND:VCALENDAR";
function file_get_contents_curl($url)
{
$ch = curl_init();
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
//Set curl to return the data instead of printing it to the browser.
curl_setopt($ch, "http://" + CURLOPT_URL, $url);
$data = curl_exec($ch);
curl_close($ch);
return $data;
}
foreach ($scraper as $scr) {
scraperwiki::attach($scr);
$qry = "* from " . $scr . ".swdata";
//echo $qry;
$arr = scraperwiki::select($qry);
// print_r($arr);
foreach ($arr as $d) {
// print $d["key"];
// print $d["site"];
$pr = (int) getPagerank($d["url"]);
if (1) {
$d_key = $d["key"];
$d_site = $d["site"];
//print_r($d["url"]." PR is ". (string)$pr ." site is ".$d_site); // ." key is " . $d_key);
$record = array('url' => utf8_encode($d["url"]), 'pr' => utf8_encode($pr), 'ar' => utf8_encode($d["rank"]), 'id' => utf8_encode($d_key), 'desc' => $d["site"]);
#print_r($record);
scraperwiki::save_sqlite(array("id"), $record, "prank");
}
}
}
<?php
// .. CREACION DEL ARRAY
foreach ($data as $item) {
echo " <item>\n";
echo " <title>" . $item['artist'] . " - " . $item['title'] . "</title>\n";
echo " <enclosure url=\"" . $item['url'] . "\" type=\"audio/mpeg\" />\n";
echo " <guid>" . $item['loved_count'] . "</guid>\n";
echo " </item>\n";
}
?>
</channel>
</rss><?php
scraperwiki::httpresponseheader('Content-Type', 'application/atom+xml');
scraperwiki::attach("exfm");
$data = scraperwiki::select("* from exfm.swdata");
?>
<rss xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" version="2.0">
<channel>
<title>TuMusika Evolution Podcast</title>
<link>http://www.tumusika.net/</link>
<language>es-es</language>
<itunes:owner>
<itunes:name>TuMusika Evolution</itunes:name>
<itunes:email>darkgiank@darkgiank.com</itunes:email>
</itunes:owner>
<?php
// .. CREACION DEL ARRAY
foreach ($data as $item) {
