summaryrefslogtreecommitdiff
path: root/scripts/importtwitteratom.php
diff options
context:
space:
mode:
authorEvan Prodromou <evan@status.net>2010-03-07 23:41:55 -0500
committerEvan Prodromou <evan@status.net>2010-03-07 23:41:55 -0500
commit3fba9a16f5e908b62e486d0e0df02fcb6e0a7796 (patch)
treec9cf241136a21a26a173f970321c2052cb377152 /scripts/importtwitteratom.php
parent5adb494c26e431948b50690b8efaeedb3f3513d1 (diff)
add a script to import Twitter atom feed as notices
Diffstat (limited to 'scripts/importtwitteratom.php')
-rw-r--r--scripts/importtwitteratom.php192
1 files changed, 192 insertions, 0 deletions
diff --git a/scripts/importtwitteratom.php b/scripts/importtwitteratom.php
new file mode 100644
index 000000000..7316f2108
--- /dev/null
+++ b/scripts/importtwitteratom.php
@@ -0,0 +1,192 @@
+#!/usr/bin/env php
+<?php
+/*
+ * StatusNet - the distributed open-source microblogging tool
+ * Copyright (C) 2010 StatusNet, Inc.
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+define('INSTALLDIR', realpath(dirname(__FILE__) . '/..'));
+
+$shortoptions = 'i:n:f:';
+$longoptions = array('id=', 'nickname=', 'file=');
+
+$helptext = <<<END_OF_IMPORTTWITTERATOM_HELP
+importtwitteratom.php [options]
+import an Atom feed from Twitter as notices by a user
+
+ -i --id ID of user to update
+ -n --nickname nickname of the user to update
+ -f --file file to import (Atom-only for now)
+
+END_OF_IMPORTTWITTERATOM_HELP;
+
+require_once INSTALLDIR.'/scripts/commandline.inc';
+require_once INSTALLDIR.'/extlib/htmLawed/htmLawed.php';
+
+function getUser()
+{
+ $user = null;
+
+ if (have_option('i', 'id')) {
+ $id = get_option_value('i', 'id');
+ $user = User::staticGet('id', $id);
+ if (empty($user)) {
+ throw new Exception("Can't find user with id '$id'.");
+ }
+ } else if (have_option('n', 'nickname')) {
+ $nickname = get_option_value('n', 'nickname');
+ $user = User::staticGet('nickname', $nickname);
+ if (empty($user)) {
+ throw new Exception("Can't find user with nickname '$nickname'");
+ }
+ } else {
+ show_help();
+ exit(1);
+ }
+
+ return $user;
+}
+
+function getAtomFeedDocument()
+{
+ $filename = get_option_value('f', 'file');
+
+ if (empty($filename)) {
+ show_help();
+ exit(1);
+ }
+
+ if (!file_exists($filename)) {
+ throw new Exception("No such file '$filename'.");
+ }
+
+ if (!is_file($filename)) {
+ throw new Exception("Not a regular file: '$filename'.");
+ }
+
+ if (!is_readable($filename)) {
+ throw new Exception("File '$filename' not readable.");
+ }
+
+ $xml = file_get_contents($filename);
+
+ $dom = DOMDocument::loadXML($xml);
+
+ if ($dom->documentElement->namespaceURI != Activity::ATOM ||
+ $dom->documentElement->localName != 'feed') {
+ throw new Exception("'$filename' is not an Atom feed.");
+ }
+
+ return $dom;
+}
+
+function importActivityStream($user, $doc)
+{
+ $feed = $doc->documentElement;
+
+ $entries = $feed->getElementsByTagNameNS(Activity::ATOM, 'entry');
+
+ for ($i = $entries->length - 1; $i >= 0; $i--) {
+ $entry = $entries->item($i);
+ $activity = new Activity($entry, $feed);
+ $object = $activity->object;
+ if (!have_option('q', 'quiet')) {
+ print $activity->content . "\n";
+ }
+ $html = getTweetHtml($object->link);
+
+ $config = array('safe' => 1,
+ 'deny_attribute' => 'class,rel,id,style,on*');
+
+ $html = htmLawed($html, $config);
+
+ $content = html_entity_decode(strip_tags($html));
+
+ $notice = Notice::saveNew($user->id,
+ $content,
+ 'importtwitter',
+ array('uri' => $object->id,
+ 'url' => $object->link,
+ 'rendered' => $html,
+ 'created' => common_sql_date($activity->time),
+ 'replies' => array(),
+ 'groups' => array()));
+ }
+}
+
+function getTweetHtml($url)
+{
+ try {
+ $client = new HTTPClient();
+ $response = $client->get($url);
+ } catch (HTTP_Request2_Exception $e) {
+ print "ERROR: HTTP response " . $e->getMessage() . "\n";
+ return false;
+ }
+
+ if (!$response->isOk()) {
+ print "ERROR: HTTP response " . $response->getCode() . "\n";
+ return false;
+ }
+
+ $body = $response->getBody();
+
+ return tweetHtmlFromBody($body);
+}
+
+function tweetHtmlFromBody($body)
+{
+ $doc = DOMDocument::loadHTML($body);
+ $xpath = new DOMXPath($doc);
+
+ $spans = $xpath->query('//span[@class="entry-content"]');
+
+ if ($spans->length == 0) {
+ print "ERROR: No content in tweet page.\n";
+ return '';
+ }
+
+ $span = $spans->item(0);
+
+ $children = $span->childNodes;
+
+ $text = '';
+
+ for ($i = 0; $i < $children->length; $i++) {
+ $child = $children->item($i);
+ if ($child instanceof DOMElement &&
+ $child->tagName == 'a' &&
+ !preg_match('#^https?://#', $child->getAttribute('href'))) {
+ $child->setAttribute('href', 'http://twitter.com' . $child->getAttribute('href'));
+ }
+ $text .= $doc->saveXML($child);
+ }
+
+ return $text;
+}
+
+try {
+
+ $doc = getAtomFeedDocument();
+ $user = getUser();
+
+ importActivityStream($user, $doc);
+
+} catch (Exception $e) {
+ print $e->getMessage()."\n";
+ exit(1);
+}
+