Last active
June 14, 2016 06:25
-
-
Save matiasfrndz/e7589fc166ea4d788dcbce5928930e54 to your computer and use it in GitHub Desktop.
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 | |
$data_source = array(); | |
$data_source['kmuratgeber.ch'] = | |
array( | |
'start_url' => 'http://kmuratgeber.ch/Handel/Angebote.asp', | |
'process' => "//div[@class='HLCol1']/a", | |
'context' => '//div[@id="BLOCKI"]', | |
'fields' => | |
array( | |
'title' => '//div[@class="HTitel"]', | |
'description' => '//div//tr[@id="TextGanz"]/td', | |
'region' => './/div[@class="HDCol2"]//td[@class="HDLabel" and text()="Region:"]/following-sibling::td[@class="HDText"]', | |
'price' => './/div[@class="HDCol2"]//td[@class="HDLabel" and starts-with(text(),"Transaktionswert")]/following-sibling::td[@class="HDText"]', | |
), | |
); | |
$data_source['www.businessmarket.ch'] = | |
array( | |
'start_url' => 'http://www.businessmarket.ch/Firmen/Suchen.9.html', | |
'follow' => '//div[@class="inserate_list_counter"]/div/a[contains(text(),"Weiter")]', | |
'process' => '//div[contains(@class,"inserat_brick")]/div[@class="details"]/a[@class="button"]', | |
'context' => '//html', | |
'fields' => | |
array( | |
'title' => '//article/h1', | |
'description' => '//div[@class="inserat_detail_left"]', | |
'region' => '//div[@class="inserat_detail_right"]//table[@class="inserat_infos"]//td[text()="Region"]/following-sibling::td', | |
'price' => '//div[@class="inserat_detail_right"]//table[@class="inserat_infos"]//td[text()="Verkaufspreis"]/following-sibling::td', | |
), | |
); |
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 | |
require('./goutte.phar'); | |
use Goutte\Client; | |
use Symfony\Component\DomCrawler\Link; | |
// import $data_source config | |
require_once('./config.php'); | |
foreach ($data_source as $source) { | |
$next_url = $source['start_url']; | |
// we have to use the same client for crawling the entire site | |
// so that we keep the same session during the crawl process | |
$client = new Client(); | |
while (isset($next_url) && $next_url) { | |
$crawler = $client->request('GET', $next_url); | |
$link_nodes = $crawler->filterXPath($source['process']); | |
foreach ($link_nodes as $node) { | |
$link = new Link($node, $source['start_url'], 'GET'); | |
$content_crawler = $client->request('GET', $link->getUri()); | |
$context = $content_crawler->filterXPath($source['context']); | |
$item = array(); | |
$item['uri'] = $client->getRequest()->getUri(); | |
foreach ($source['fields'] as $field => $xpath) { | |
$item[$field] = getValue($context, $xpath); | |
} | |
echo json_encode($item) . "\n"; | |
} | |
unset($next_url); | |
if ($source['follow']) { | |
$follow_link = $crawler->filterXPath($source['follow']); | |
if (count($follow_link)) { | |
$next_url = new Link($follow_link->getNode(0), $source['start_url'], 'GET'); | |
$next_url = $next_url->getUri(); | |
} | |
} | |
} | |
} | |
function getValue($crawler, $xpath) { | |
$filtered = $crawler->filterXPath($xpath); | |
if (count($filtered)) { | |
return $filtered->text(); | |
} | |
return ''; | |
} | |
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 | |
require('./goutte.phar'); | |
use Goutte\Client; | |
use Symfony\Component\DomCrawler\Link; | |
date_default_timezone_set('Europe/Zurich'); | |
$source = | |
array( | |
'start_url' => 'http://www.remicom.com/de/assets/list#top_window', | |
'follow' => '//div[contains(@class,"show_more")]/a[contains(@class,"stndrd-btn-highlight")]//following-sibling::a', | |
'process' => '//div[@id="vignettes"]/div/a[position()=1]', | |
'context' => '//div[@id="detail_objet"]', | |
'fields' => | |
array( | |
'title' => '//div[contains(@class,"main-content-wrap")]/div[contains(@class,"title")]', | |
'description' => '//div[@id="fiche_block_info"]/div[contains(@class,"full_desc)]', | |
'region' => '//div[@class="inserat_detail_right"]//table[@class="inserat_infos"]//td[text()="Region"]/following-sibling::td', | |
'price' => '//div[@class="inserat_detail_right"]//table[@class="inserat_infos"]//td[text()="Verkaufspreis"]/following-sibling::td', | |
), | |
); | |
$params = [ | |
'country'=> 'CH', | |
'transmission_d_entreprises' => '{"35":"Unternehmen", "36":"KMU", "37":"Firma" }', | |
'moteur2' => 'ok', | |
'list_posted_id_type_transmission_d_entreprises' => null, | |
'canton' => '-', | |
'agency' => '-', | |
'reference' => null, | |
'offset2' => 0, | |
'lastoffer2' => null, | |
'page2' => 1 | |
]; | |
$offset = 1; | |
$next_url = $source['start_url']; | |
// we have to use the same client for crawling the entire site | |
// so that we keep the same session during the crawl process | |
$client = new Client(); | |
while (isset($params['page2']) && $params['page2']) { | |
$crawler = $client->request('POST', $next_url, $params); | |
$link_nodes = $crawler->filterXPath($source['process']); | |
foreach ($link_nodes as $node) { | |
$link = new Link($node, 'http://www.remicom.com/', 'GET'); | |
echo $link->getURI() . "\n"; | |
$content_crawler = $client->request('GET', $link->getUri()); | |
$context = $content_crawler->filterXPath($source['context']); | |
// echo $content_crawler->html() ."\n"; | |
$item = array(); | |
$item['uri'] = $client->getRequest()->getUri(); | |
foreach ($source['fields'] as $field => $xpath) { | |
$item[$field] = getValue($context, $xpath); | |
} | |
echo json_encode($item) . "\n"; | |
} | |
if ($source['follow']) { | |
$follow_link = $crawler->filterXPath($source['follow']); | |
if (count($follow_link)) { | |
$params['page2'] += 1; | |
} | |
else { | |
unset($params['page2']); | |
} | |
} | |
} | |
function getValue($crawler, $xpath) { | |
$filtered = $crawler->filterXPath($xpath); | |
if (count($filtered)) { | |
return $filtered->text(); | |
} | |
return ''; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment