loviuz/structured_scraper
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Separazione file config

Browse Source
This commit is contained in:
loviuz 2022-01-06 17:22:41 +01:00
parent 9db2ec22d9
commit d62aa375b8
2 changed files with 10 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
config.example.php Normal file
View File

@ -0,0 +1,10 @@
<?php
$start_url = 'https://www.iltuocomune.it/amministrazione-trasparente-url';
$filters = [
'//td[@class="actions"]/a[@title="Visualizza "]',
'//table[@class="allegati"]/a[@title="Download versione non firmata"]'
];
$download_dir = __DIR__.'/pdf';

9
scrape.php
View File

@ -4,16 +4,7 @@ require __DIR__.'/vendor/autoload.php';
use Scraping\Scraper; use Scraping\Scraper;
$start_url = 'https://este.trasparenza-valutazione-merito.it/web/amministrazionetrasparente/papca-ap/-/papca/igrid/1452834656/1452816457';
$filters = [
'//td[@class="actions"]/a[@title="Visualizza Allegato"]',
'//table[@class="allegati"]/a[@title="Download versione non firmata"]'
];
$scraper = new Scraper(); $scraper = new Scraper();
$scraper->levels = count($filters);
foreach ($filters as $i => $filter) { foreach ($filters as $i => $filter) {
$scraper->scrape('GET', $start_url, $filters, $i); $scraper->scrape('GET', $start_url, $filters, $i);