Last active
December 22, 2015 15:39
-
-
Save tkuldeep/6493838 to your computer and use it in GitHub Desktop.
To extract data from disqus exported comment. Convert XML file into php string by reference http://www.php.net/manual/en/simplexml.examples-basic.php
This file contains hidden or 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 | |
include 'XML_File.php'; | |
$pos1 = 0; | |
$pos2 = 0; | |
$pos3 = 0; | |
$pos4 = 0; | |
$email_pos_open = 0; | |
$email_pos_close = 0; | |
$name_pos_close = 0; | |
$name_pos_open = 0; | |
// Extract email ids from disqus exported comments | |
while ($email_pos_open = stripos($xmlstr,'<email>',$pos1)) { | |
$email_pos_close = stripos($xmlstr,'</email>',$pos2); | |
$pos2 = $email_pos_close + 8; | |
$pos1 = $email_pos_open + 7; | |
$email_pos_opening[] = $email_pos_open+7; | |
$email_pos_closeing[] = $email_pos_close; | |
} | |
// Extract name from disqus exported comments | |
$pos1 = 0; | |
$pos2 = 0; | |
while ($name_pos_open = stripos($xmlstr,'<name>',$pos1)) { | |
// check if name contains email or not | |
$temp = substr($xmlstr,($name_pos_open-8),6); | |
if (strcmp($temp, 'mail /') == 0 ) { | |
$name_pos_close = stripos($xmlstr,'</name>',$pos2); | |
$pos1 = $name_pos_open+6; | |
$pos2 = $name_pos_close+7; | |
continue; | |
} | |
$name_pos_close = stripos($xmlstr,'</name>',$pos2); | |
$pos1 = $name_pos_open+6; | |
$pos2 = $name_pos_close+7; | |
$name_pos_opening[] = $name_pos_open+6; | |
$name_pos_closeing[] = $name_pos_close; | |
} | |
$number_of_users = count($email_pos_opening); | |
$fp = fopen("/var/www/AAP_India/sites/default/files/Delhi_site_users1_disqus.csv", "w"); | |
echo $number_of_users; | |
for ($i = 0; $i <$number_of_users; $i++) { | |
$email = substr($xmlstr,$email_pos_opening[$i],($email_pos_closeing[$i])-($email_pos_opening[$i])). "\n"; | |
$name = substr($xmlstr,$name_pos_opening[$i],($name_pos_closeing[$i])-($name_pos_opening[$i])) . "\n"; | |
fwrite($fp, trim($name) . ','); | |
fwrite($fp, trim($email) . "\n"); | |
} | |
fclose($fp); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment