Hypo CSV爬虫-网上银行对账单下载从Hypovereinsbank慕尼黑，德国使用P

Posted

tags:

篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了Hypo CSV爬虫-网上银行对账单下载从Hypovereinsbank慕尼黑，德国使用P相关的知识，希望对你有一定的参考价值。

updated 2013-04-18!

just replace the XXX fields with your own numbers. Then run this php Script from the command line (CLI mode). It will fetch the online statements from Hypovereinsbank direct banking.

The code works by tweaking CURL settings around the HTTPS connection.
  1. <?php
  2. /**
  3.  * fetch CSV data from hypovereinsbank Direct [email protected]
  4.  * 
  5.  * @author  CU 
  6.  * @version 1.0
  7.  * @requires curl in CLI mode
  8.  */
  9.  
  10. getHypoData();
  11.  
  12. /**
  13.  * retrieves CSV data from hypovereinsbank Direct [email protected] website.
  14.  * @return  boolean    successful or not
  15.  * @access  public
  16.  * @static  makes the class property accessible without needing an instantiation of the class
  17.  */
  18. function getHypoData()
  19. {
  20. 	# CONFIG
  21. 	$sleepMin = 5;
  22. 	$sleepMax = 10;
  23. #	$proxyCfg = ' -x XXX.XXX.XXX.XXX:XXXX';
  24. 	$direktbankingNr = 'xxxxxxxxxxx';
  25. 	$pwdOnline = 'xxxxxxxxx';
  26. 	# CONFIG
  27.  
  28. 	# to use strftime's magic
  29. 	setlocale(LC_TIME, "de_DE"); 
  30.  
  31. 	$curlParameters = $proxyCfg. ' --silent --user-agent "Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)" -b cookies_hypo.txt -c cookies_hypo.txt --location';
  32. #	to debug CURL simply uncomment next line
  33. #	$curlParameters = ' --include --trace-ascii debugdump0.txt '.$proxyCfg.' --user-agent "Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)" -b cookies_hypo.txt -c cookies_hypo.txt --location';
  34.  
  35. 	if (file_exists('cookies_hypo.txt')) {
  36. 		unlink('cookies_hypo.txt') || die (print 'Cannot remove cookies_hypo.txt');    
  37. 	}
  38. 	echo date('Y-m-d H:i:s') .' initial URL fetch' ."
";
  39. 	$output = array();
  40. 	$run = exec('curl https://my.hypovereinsbank.de/login?view=/privatkunden/login.jsp '. $curlParameters, $output);
  41. 	if (!$run) {
  42. 		print "could not execute CURL line ". __LINE__;
  43. 		return false;
  44. 	}
  45. 	if (count($output)<=10 || count($output)>=1000) {
  46. 		print_r($output);
  47. 		print "FATAL: buggy input. ";
  48. 		return false;
  49. 	}
  50. 	$ViewState = '';
  51. 	# find the "ViewState"
  52. 	foreach ($output as $line) {
  53. 		if ($ViewState=='' && strpos($line, 'hidden')!==false && strpos($line, 'ViewState')!==false) {
  54. 			echo date('Y-m-d H:i:s') .' identified ViewState Line' ."
";
  55. 			$challenge_line = split('"', $line);
  56. 			if ($ViewState = $challenge_line[7]) {
  57. 				echo date('Y-m-d H:i:s') .' identified ViewState: '. $ViewState ."
";
  58. 			}
  59. 		}
  60. 	}
  61. 	if (strlen($ViewState)<=10 || strlen($ViewState)>=200) {
  62. 		echo date('Y-m-d H:i:s') .' FATAL: weird ViewState: '. $ViewState ."
";
  63. 		return false;
  64. 	}
  65. 	sleep(rand($sleepMin,$sleepMax));
  66.  
  67. 	echo date('Y-m-d H:i:s') .' attempt login' ."
";
  68. 	$output = array();
  69. 	$run = exec('curl https://my.hypovereinsbank.de/login?view=/privatkunden/login.jsp --data "username='. $direktbankingNr .'&px2='. $pwdOnline .'&secP=FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF&fp=&directBankingLoginForm%3AloginPanel%3AloginCommand=Anmelden&directBankingLoginForm%3A_idcl=&directBankingLoginForm%3A_link_hidden_=&directBankingLoginForm_SUBMIT=1&javax.faces.ViewState='. $ViewState .'"'. $curlParameters, $output);
  70. 	if (!$run) {
  71. 		print "could not execute CURL line ". __LINE__;
  72. 		return false;
  73. 	}
  74. 	if ((strpos(implode(' ', $output), 'LogIn HVB Direct'))) {
  75. 		echo date('Y-m-d H:i:s') .' FATAL: login page again!'. "
";
  76. 		print_r($output);
  77. 		return false;
  78. 	}
  79. 	sleep(rand($sleepMin,$sleepMax));
  80.  
  81. 	echo date('Y-m-d H:i:s') .' attempt KONTO homepage' ."
";
  82. 	$output = array();
  83. 	$run = exec('curl https://my.hypovereinsbank.de/portal?view=/banking/accountManagement.jsp '. $curlParameters, $output);
  84. 	if (!$run) {
  85. 		print "could not execute CURL line ". __LINE__;
  86. 		return false;
  87. 	}
  88. 	if ((strpos(implode(' ', $output), 'LogIn HVB Direct'))) {
  89. 		echo date('Y-m-d H:i:s') .' FATAL: login page again!'. "
";
  90. 		print_r($output);
  91. 		return false;
  92. 	}
  93. 	$ViewState = '';
  94. 	# find the changed "ViewState"
  95. 	foreach ($output as $line) {
  96. 		if ($ViewState=='' && strpos($line, 'hidden')!==false && strpos($line, 'ViewState')!==false) {
  97. 			echo date('Y-m-d H:i:s') .' identified ViewState Line' ."
";
  98. 			$challenge_line = split('"', $line);
  99. 			if ($ViewState = $challenge_line[13]) {
  100. 				echo date('Y-m-d H:i:s') .' identified ViewState: '. $ViewState ."
";
  101. 			}
  102. 		}
  103. 	}
  104. 	if (strlen($ViewState)<=10 || strlen($ViewState)>=200) {
  105. 		echo date('Y-m-d H:i:s') .' FATAL: weird ViewState: '. $ViewState ."
";
  106. 		return false;
  107. 	}
  108. 	echo date('Y-m-d H:i:s') .' setting the time-frame' ."
";
  109. 	$output = array();
  110. 	$fromMonth = strftime("%B+%Y", time() - 31*24*3600);
  111. 	$toMonth = strftime("%B+%Y", time() - 4*24*3600);
  112. 	$toDay = strftime("%d", time() - 4*24*3600);
  113. 	echo date('Y-m-d H:i:s') ." TIMEFRAME: 01+$fromMonth - $toDay+$toMonth" ."
";
  114.  
  115. 	$run = exec('curl https://my.hypovereinsbank.de/portal?view=/banking/accountManagement.jsp --data "accountManagement%3AdayFrom=1&accountManagement%3AmonthFrom='. $fromMonth .'&accountManagement%3AdayTo='. $toDay .'&accountManagement%3AmonthTo='. $toMonth .'&accountManagement%3AnumberOfTurnovers=9999&accountManagement%3Arefresh=Anzeigen&accountManagement%3Apurpose=&accountManagement%3AamountMin=&accountManagement%3AamountMax=&accountManagement%3A_link_hidden_=&accountManagement%3A_idcl=&accountManagement_SUBMIT=1&&javax.faces.ViewState='. $ViewState .'"'. $curlParameters, $output);
  116. 	if (!$run) {
  117. 		print "could not execute CURL line ". __LINE__;
  118. 		return false;
  119. 	}
  120. 	if ((strpos(implode(' ', $output), 'LogIn HVB Direct'))) {
  121. 		echo date('Y-m-d H:i:s') .' FATAL: login page again!'. "
";
  122. 		print_r($output);
  123. 		return false;
  124. 	}
  125. 	sleep(rand($sleepMin,$sleepMax));
  126.  
  127. 	# fetch live & old Kontostand 
  128. 	$liveStart = false;
  129. 	foreach ($output as $line) {
  130. 		if (strpos($line, 'Aktueller Kontosaldo')!== false) {
  131. 			$liveStart = true;
  132. 		}
  133. 		if (strpos($line, '</fieldset>')!== false) {
  134. 			$liveStart = false;
  135. 		}
  136. 		if ($liveStart && trim($line) == trim(strip_tags($line)) && strpos($line, 'EUR')!== false) {
  137. 			$Betrag[0] = trim(str_replace('EUR', '', $line));
  138. 		}
  139. 		if ($liveStart && strpos($line, 'negbal')!==false && strpos($line, 'EUR')!== false) {
  140. 			$Betrag[0] = trim(str_replace('EUR', '', strip_tags($line)));
  141. 		}
  142.  
  143. 		if (strpos($line, 'Kontostand am')!== false) {
  144. 			$linePart = strip_Tags(substr($line, strpos($line, 'Kontostand am')));
  145. 			$lineParts = explode(date('Y'), $linePart);
  146. 			$lineParts2 = explode(' ', trim(str_replace('EUR', '', $lineParts[1])));
  147. 			if ($lineParts2[1]) {
  148. 				$Betrag[1] = $lineParts2[1];
  149. 			} else {
  150. 				$Betrag[1] = trim(str_replace('EUR', '', $lineParts[1]));
  151. 			}
  152. 		}
  153. 	}
  154. 	echo date('Y-m-d H:i:s ') . ("Kontostand live ... " . $Betrag[0] ." EUR"). "
";
  155. 	echo date('Y-m-d H:i:s ') . ("Kontostand old .... " . $Betrag[1] ." EUR"). "
";
  156. 	if (!$Betrag) {
  157. 		print 'no Betrag in line: '. __LINE__;
  158. 		return false;
  159. 	}
  160. 	sleep(rand($sleepMin,$sleepMax));
  161.  
  162. 	echo date('Y-m-d H:i:s') .' attempt CSV Download' ."
";
  163. 	$output = array();
  164. 	$run = exec('curl https://my.hypovereinsbank.de/portal?view=/banking/accountManagement.jsp --data "accountManagement%3AdayFrom=1&accountManagement%3AmonthFrom='. $fromMonth .'&accountManagement%3AdayTo='. $toDay .'&accountManagement%3AmonthTo='. $toMonth .'&accountManagement%3AnumberOfTurnovers=9999&accountManagement%3Apurpose=&accountManagement%3AamountMin=&accountManagement%3AamountMax=&accountManagement%3AbuttonNavigation%3Aj_id_id182=Download+Kontoums%E4tze+&accountManagement%3A_link_hidden_=&accountManagement%3A_idcl=&accountManagement_SUBMIT=1&&javax.faces.ViewState='. $ViewState .'"'. $curlParameters, $output);
  165. 	if (!$run) {
  166. 		print "could not execute CURL line ". __LINE__;
  167. 		return false;
  168. 	}
  169. 	if ((strpos(implode(' ', $output), 'LogIn HVB Direct'))) {
  170. 		echo date('Y-m-d H:i:s') .' FATAL: login page again!'. "
";
  171. 		print_r($output);
  172. 		return false;
  173. 	}
  174. 	if ($output) {
  175. 		$fileName = 'hypo_'.date('Y-m-d.H-i-s'). '.csv';
  176. 		$result = file_put_contents($fileName, implode("
", $output)."
") || die (print "could not dump CSV content to file");
  177. 		echo date('Y-m-d H:i:s') .' '. count($output). ' lines written to file: '. $fileName .''. "
";
  178. 	}
  179. 	sleep(rand($sleepMin,$sleepMax));
  180.  
  181. 	echo date('Y-m-d H:i:s') .' attempt Logout' ."
";
  182. 	$output = array();
  183. 	$run = exec('curl https://my.hypovereinsbank.de/login?view=/privatkunden/logout.jsp '. $curlParameters, $output);
  184. 	if (!$run) {
  185. 		print "could not execute CURL line ". __LINE__;
  186. 		return false;
  187. 	}
  188. 	if ((strpos(implode(' ', $output), 'LogIn HVB Direct'))) {
  189. 		echo date('Y-m-d H:i:s') .' FATAL: login page again!'. "
";
  190. 		print_r($output);
  191. 		return false;
  192. 	}
  193. 	if ((strpos(implode(' ', $output), 'korrekt'))) {
  194. 		return true;
  195. 	}
  196. 	sleep(rand($sleepMin,$sleepMax));
  197.  
  198. 	return false;
  199. } // end func
  200.  
  201. # EOF
  202. ?>

以上是关于Hypo CSV爬虫-网上银行对账单下载从Hypovereinsbank慕尼黑，德国使用P的主要内容，如果未能解决你的问题，请参考以下文章

ios开发 ad hoc怎么用

欧几里得算法(辗转相除法)

机器为什么可以学习---一般化理论

爬虫日记(68)：Scrapy的CSVFeedSpider使用

支付系统的对账

使用Shell脚本忽略csv文件中的第一行（标题）