Last active
January 26, 2019 16:44
-
-
Save reliq/dd688149ef165c34f6543328e6e862ef to your computer and use it in GitHub Desktop.
Scavenger example for scraping https://www.khmer24.com/en/homes/apartment-for-sale.html
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 | |
return [ | |
// debug mode? | |
'debug' => false, | |
// whther log file should be written | |
'log' => true, | |
// How much detail is expected in output, 1 being the lowest, 3 being highest. | |
'verbosity' => 3, | |
// Set the database config | |
'database' => [ | |
// Scraps table | |
'scraps_table' => env('SCAVENGER_SCRAPS_TABLE', 'scavenger_scraps'), | |
], | |
// Daemon config - used to build daemon user | |
'daemon' => [ | |
// Model to use for Daemon identification and login | |
'model' => 'App\\User', | |
// Model property to check for daemon ID | |
'id_prop' => 'email', | |
// Daemon ID | |
'id' => '[email protected]', | |
// Any additional information required to create a user: | |
// NB. this is only used when creating a daemon user, there is no "safe" way | |
// to change the daemon's password once he has been created. | |
'info' => [ | |
'name' => 'Scavenger Daemon', | |
'password' => 'pass' | |
] | |
], | |
// Hashing algorithm to use | |
'hash_algorithm' => 'sha512', | |
// storage | |
'storage' => [ | |
// This directory will live inside your application's log directory. | |
'log_dir' => env('SCAVENGER_LOG_DIR', 'scavenger'), | |
], | |
// different model entities and mapping information | |
'targets' => [ | |
'apartments' => [ | |
'example' => false, | |
'model' => 'App\\Item', | |
'source' => 'https://www.khmer24.com/en/homes/apartment-for-sale.html', | |
'search' => null, | |
'pager' => [ | |
'selector' => '.pagination a[rel="next"]', | |
'text' => 'Next', | |
], | |
'markup' => [ | |
'title' => '.item-detail .item-title', | |
'__wrapper' => 'li.item article', | |
], | |
'pages' => 5, | |
], | |
], | |
]; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment