Last active
April 12, 2020 13:34
-
-
Save guandaxia/c9dcbee31d3d865402cf52df5b9c41f2 to your computer and use it in GitHub Desktop.
58同城租房爬虫——基于phpspider|-|{"files":{"58.php":{"env":"plain"}},"tag":"Uncategorized"}
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 | |
ini_set("memory_limit", "1024M"); | |
require dirname(__FILE__).'/../core/init.php'; | |
/* Do NOT delete this comment */ | |
/* 不要删除这段注释 */ | |
//58同城 | |
$configs = array( | |
'name' => '58租房', | |
'log_show' => false, | |
// 'log_type' => 'info, warn, error', | |
'tasknum' => 5, | |
'interval' => 1000, | |
'export' => array( | |
'type' => 'sql', | |
'file' => PATH_DATA.'/58.sql', | |
'table' => 'zufang', | |
), | |
'max_try' => 5, | |
// 'proxy' => 'http://115.202.167.238:808', | |
//'save_running_state' => true, | |
'domains' => array( | |
'tj.58.com', | |
), | |
'scan_urls' => array( | |
'http://tj.58.com/chuzu/0/' | |
), | |
'list_url_regexes' => array( | |
"http://tj.58.com/chuzu/0/pn\d+" | |
), | |
'content_url_regexes' => array( | |
"http://tj.58.com/zufang/\d{14}x.shtml(\?\w+)*", | |
), | |
'fields' => array( | |
[ | |
//标题 | |
'name' => "title", | |
'selector' => "//div[4]/div[1]/h1", | |
'required' => true, | |
], | |
[ | |
//租金 | |
'name' => "money", | |
'selector' => "//div[4]/div[2]/div[2]/div[1]/div[1]/div/span[1]/b", | |
'required' => true, | |
], | |
[ | |
//租赁方式 | |
'name' => "lease_mode", | |
'selector' => "//div[4]/div[2]/div[2]/div[1]/div[1]/ul/li[1]/span[2]", | |
'required' => true, | |
], | |
[ | |
//房屋类型 | |
'name' => "roome_type", | |
'selector' => "div[4]/div[2]/div[2]/div[1]/div[1]/ul/li[2]/span[1]", | |
'required' => true, | |
], | |
[ | |
//朝向楼层 | |
'name' => "floor", | |
'selector' => "div[4]/div[2]/div[2]/div[1]/div[1]/ul/li[3]/span[2]", | |
'required' => true, | |
], | |
[ | |
//所在小区 | |
'name' => "house_estate", | |
'selector' => "div[4]/div[2]/div[2]/div[1]/div[1]/ul/li[4]/span[2]/a", | |
'required' => true, | |
], | |
[ | |
//地址 | |
'name' => "address", | |
'selector' => "div[4]/div[2]/div[2]/div[1]/div[1]/ul/li[6]/span[2]", | |
'required' => true, | |
] | |
), | |
); | |
$spider = new phpspider($configs); | |
$spider->on_extract_field = function($fieldname, $data, $page) { | |
if($fieldname == "floor"){ | |
$data = str_replace(" ", "", $data); | |
} | |
return $data; | |
}; | |
$spider->start(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment