PHP curl collects off-site content sample code

//Initialize a cURL object
$curl = curl_init();
//Set the URL you need to crawl
curl_setopt($curl, CURLOPT_URL, 'http://bbs.it -home.org');
// Set header
curl_setopt($curl, CURLOPT_HEADER, 1);
// Set cURL parameters to ask whether the results are saved in a string or output to the screen.
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
// Run cURL and request the web page
$data = curl_exec($curl);
// Close the URL request
curl_close($curl); 3. Find key data through regular matching

//$data is the value returned by curl_exec, which is the target content collected

 echo 'The whole sentence matched: '.$value[0].'
';
 echo 'Single matching: '.$value[1].'
';
}


Copy Code


PHP curl tips
1. Timeout related settings
Some timeout settings can be set through curl_setopt($ch, opt), mainly including:
CURLOPT_TIMEOUT sets the maximum number of seconds cURL is allowed to execute. 
CURLOPT_TIMEOUT_MS sets the maximum number of milliseconds cURL is allowed to execute. (Added in cURL 7.16.2. Available as of PHP 5.2.3.)
CURLOPT_CONNECTTIMEOUT The time to wait before initiating a connection. If set to 0, it will wait indefinitely. 
CURLOPT_CONNECTTIMEOUT_MS The time, in milliseconds, to wait for a connection attempt. If set to 0, wait infinitely. Added in cURL 7.16.2. Available starting with PHP 5.2.3. 
CURLOPT_DNS_CACHE_TIMEOUT sets the time to save DNS information in memory, the default is 120 seconds.

//Curl simulated login discuz program, suitable for DZ7.0

!extension_loaded('curl') && die('The curl extension is not loaded.');

$discuz_url = 'http://bbs.it-home.org';//Forum address

1. $login_url = $discuz_url .'/logging. php?action=login';//Login page address
2. $get_url = $discuz_url .'/my.php?item=threads'; //My post

3. $post_fields = array( );

4. //The following two items do not need to be modified
5. $post_fields['loginfield'] = 'username';
6. $post_fields['loginsubmit'] = 'true';
7. //Username and password must be filled in
8. $post_fields[ 'username'] = 'jbxue';
9. $post_fields['password'] = '88888888';
10. //Security question
11. $post_fields['questionid'] = 0;
12. $post_fields['answer'] = '';
13. //@todo verification code
14. $post_fields['seccoverify'] = '';

15. //Get form FORMHASH

16. $ch = curl_init($login_url);
17. curl_setopt($ch, CURLOPT_HEADER, 0);
18. curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
19. $contents = curl_exec($ch);
20. curl_close($ch);
21. preg_match('//i', $contents, $matches);
22. if(!empty($matches)) {
23. $formhash = $matches[1 ];
24. } else {
25. die('Not found the forumhash.');
26. }

27. //POST data, get COOKIE

28. $cookie_file = dirname(__FILE__) . '/cookie. txt';
29. //$cookie_file = tempnam('/tmp');
30. $ch = curl_init($login_url);
31. curl_setopt($ch, CURLOPT_HEADER, 0);
32. curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
33. curl_setopt($ch, CURLOPT_POST, 1);
34. curl_setopt($ch, CURLOPT_POSTFIELDS, $post_fields);
35. curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_file);
36. curl_exec($ch);
37. curl_close($ch); < /p>

38. //Use the COOKIE obtained above to obtain the page content that needs to be logged in to view

39. $ch = curl_init($get_url);
40. curl_setopt($ch, CURLOPT_HEADER, 0);
41. curl_setopt($ ch, CURLOPT_RETURNTRANSFER, 0);
42. curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie_file);
43. $contents = curl_exec($ch);
44. curl_close($ch);

45. var_dump($contents );

49. Copy code