Created
November 17, 2012 15:49
-
-
Save skakri/4096962 to your computer and use it in GitHub Desktop.
Twitter streaming API + URL unshortening
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 | |
| /** | |
| * Unshorten links | |
| * | |
| * @param string $text | |
| * @return string | |
| */ | |
| function unshorten_links($text) { | |
| $pattern = '#\b(([\w-]+://?|www[.])[^\s()<>]+(?:\([\w\d]+\)|([^[:punct:]\s]|/)))#'; | |
| $callback = create_function('$matches', ' | |
| $url = array_shift($matches); | |
| $url_parts = parse_url($url); | |
| $text = parse_url($url, PHP_URL_HOST) . parse_url($url, PHP_URL_PATH); | |
| $ch = curl_init($text); | |
| curl_setopt_array($ch, array( | |
| CURLOPT_FOLLOWLOCATION => TRUE, | |
| CURLOPT_RETURNTRANSFER => TRUE, | |
| CURLOPT_SSL_VERIFYHOST => FALSE, // suppress certain SSL errors | |
| CURLOPT_SSL_VERIFYPEER => FALSE, | |
| )); | |
| curl_exec($ch); | |
| $text = curl_getinfo($ch, CURLINFO_EFFECTIVE_URL); | |
| curl_close($ch); | |
| return $text; | |
| '); | |
| return preg_replace_callback($pattern, $callback, $text); | |
| } | |
| set_time_limit(0); | |
| $users = array( | |
| '110089364' => array( | |
| 'nick' => 'Maadinsh', | |
| 'uid' => 1, | |
| 'gid' => 0 | |
| ), | |
| '172640737' => array( | |
| 'nick' => 'SkaForUs', | |
| 'uid' => 1548, | |
| 'gid' => 0 | |
| ), | |
| '123597407' => array( | |
| 'nick' => 'ieluvingrosana', | |
| 'uid' => 17077, | |
| 'gid' => 11 | |
| ), | |
| '932730655' => array( | |
| 'nick' => 'Rikinators', | |
| 'uid' => 22051, | |
| 'gid' => 0 | |
| ), | |
| '347040745' => array( | |
| 'nick' => 'StaticFake', | |
| 'uid' => 13004, | |
| 'gid' => 0 | |
| ), | |
| '65642258' => array( | |
| 'nick' => 'Trakais18', | |
| 'uid' => 1216, | |
| 'gid' => 0 | |
| ), | |
| '36635020' => array( | |
| 'nick' => 'viesty09', | |
| 'uid' => 2145, | |
| 'gid' => 0 | |
| ), | |
| '14276842' => array( | |
| 'nick' => 'skakri', | |
| 'uid' => 16261, | |
| 'gid' => 0 | |
| ), | |
| '104146775' => array( | |
| 'nick' => 'exs_lv', | |
| 'uid' => 1, | |
| 'gid' => 0 | |
| ), | |
| '15518000' => array() // freq tweeter test | |
| ); | |
| function cgets($ch, $line) { | |
| $length = strlen($line); | |
| printf("Received %d byte\n", $length); | |
| //echo($line); | |
| $tweet = json_decode($line); | |
| if (isset($tweet->{'text'})) { | |
| //if ($tweet->{'retweet_count'} == 0 && !isset($tweet->{'in_reply_to_user_id'})) { | |
| echo unshorten_links($tweet->{'text'}) . "\n"; | |
| //} | |
| } | |
| flush(); | |
| return $length; | |
| } | |
| while(true) { | |
| $ch = curl_init(); | |
| echo http_build_query( | |
| array( | |
| 'follow'=>implode(array_keys($users), ',') | |
| ) | |
| , '', '&'); | |
| curl_setopt($ch, CURLOPT_URL, 'https://stream.twitter.com/1/statuses/filter.json'); | |
| curl_setopt($ch, CURLOPT_WRITEFUNCTION, 'cgets'); | |
| curl_setopt($ch, CURLOPT_BUFFERSIZE, 20000); // we want all tweet data in buffer, so json isn't malformed; we're not writing to a file | |
| curl_setopt($ch, CURLOPT_USERPWD, 'user:password'); | |
| curl_setopt($ch, CURLOPT_HEADER, TRUE); // debug | |
| curl_setopt($ch, CURLOPT_POST, TRUE); | |
| curl_setopt($ch, CURLOPT_POSTFIELDS, | |
| http_build_query( | |
| array( | |
| 'follow'=>implode(array_keys($users), ',') | |
| ) | |
| , '', '&') | |
| ); | |
| curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false); | |
| curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false); | |
| curl_setopt($ch, CURLOPT_TIMEOUT, 1000000); // ~ 11 days | |
| curl_exec($ch); | |
| echo curl_getinfo($ch); // debug | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment