? feeds_imagegrabber-direct_file_grabbing.20100719.patch
? feeds_imagegrabber-direct_url_grabber.png
? feeds_imagegrabber-use_library_directory.20100718.patch
Index: README.TXT
===================================================================
RCS file: /cvs/drupal-contrib/contributions/modules/feeds_imagegrabber/Attic/README.TXT,v
retrieving revision 1.1.2.2
diff -u -p -r1.1.2.2 README.TXT
--- README.TXT 12 Mar 2010 14:46:55 -0000 1.1.2.2
+++ README.TXT 19 Jul 2010 14:58:09 -0000
@@ -18,6 +18,7 @@ Installation
1) Place this module directory in your modules folder (this will usually be "sites/all/modules/").
2) Download the UrlToAbsolute package (http://sourceforge.net/projects/absoluteurl) and copy the "url_to_absolute.php" file to the feeds_imagegrabber directory.
+2.a) Alternatively, you can place the downloaded library into "sites/all/libraries" such that the php script can be found at "sites/all/libraries/AbsoluteUrl/url_to_absolute.php"
3) Enable the module.
Usage
Index: feeds_imagegrabber.install
===================================================================
RCS file: /cvs/drupal-contrib/contributions/modules/feeds_imagegrabber/Attic/feeds_imagegrabber.install,v
retrieving revision 1.1.2.2
diff -u -p -r1.1.2.2 feeds_imagegrabber.install
--- feeds_imagegrabber.install 12 Mar 2010 14:46:55 -0000 1.1.2.2
+++ feeds_imagegrabber.install 19 Jul 2010 14:58:09 -0000
@@ -94,11 +94,11 @@ function feeds_imagegrabber_requirements
switch ($phase) {
case 'install':
case 'runtime':
- $path = drupal_get_path('module', 'feeds_imagegrabber') .'/url_to_absolute.php';
- if (!file_exists($path)) {
+ module_load_include('module', 'feeds_imagegrabber', 'feeds_imagegrabber');
+ if (! feeds_imagegrabber_load_url_to_absolute()) {
$requirements['feeds_imagegrabber_absoluteurl'] = array(
'title' => $t("Feeds Image Grabber"),
- 'description' => $t("Obtain the !conversion package and copy url_to_absolute.php to the feeds_imagegrabber directory.",
+ 'description' => $t("Obtain the !conversion package and copy url_to_absolute.php to either the feeds_imagegrabber directory, or to sites/all/libraries so that the php script can be found at sites/all/libraries/AbsoluteUrl/url_to_absolute.php.",
array('!conversion' => l('UrlToAbsolute', 'http://sourceforge.net/projects/absoluteurl', array('absolute' => TRUE)))
),
'severity' => $phase == 'install' ? REQUIREMENT_WARNING : REQUIREMENT_ERROR,
Index: feeds_imagegrabber.module
===================================================================
RCS file: /cvs/drupal-contrib/contributions/modules/feeds_imagegrabber/feeds_imagegrabber.module,v
retrieving revision 1.1.4.7
diff -u -p -r1.1.4.7 feeds_imagegrabber.module
--- feeds_imagegrabber.module 28 Mar 2010 03:31:13 -0000 1.1.4.7
+++ feeds_imagegrabber.module 19 Jul 2010 14:58:10 -0000
@@ -15,6 +15,14 @@
*/
define('FIG_HTTP_REQUEST_TIMEOUT', 1);
+/**
+ * Options used as parameters to feeds_imagegrabber_webpage_scraper
+ */
+define('FIG_SCRAPER_METHOD_NONE', 0);
+define('FIG_SCRAPER_METHOD_ID', 1);
+define('FIG_SCRAPER_METHOD_CLASS', 2);
+define('FIG_SCRAPER_METHOD_URL', 3);
+
//=============
//DRUPAL HOOKS.
//=============
@@ -55,9 +63,10 @@ function feeds_imagegrabber_form_alter(&
'#type' => 'radios',
'#title' => t('Search for an image between the tag which is identified by'),
'#options' => array(
- t('None, search the whole web-page for the image.'),
- t('an Id'),
- t('a Class'),
+ FIG_SCRAPER_METHOD_NONE => t('None, search the whole web-page for the image.'),
+ FIG_SCRAPER_METHOD_ID => t('an Id'),
+ FIG_SCRAPER_METHOD_CLASS => t('a Class'),
+ FIG_SCRAPER_METHOD_URL => t('No scraping, the link is a direct path to an image.'),
),
'#default_value' => $settings['id_class'],
);
@@ -95,7 +104,7 @@ function feeds_imagegrabber_form_node_va
if ($form_state['values']['feeds_imagegrabber']['enabled'] == 1) {
$id_class = $form_state['values']['feeds_imagegrabber']['id_class'];
$id_class_desc = $form_state['values']['feeds_imagegrabber']['id_class_desc'];
- if ($id_class) {
+ if ($id_class == FIG_SCRAPER_METHOD_ID || $id_class == FIG_SCRAPER_METHOD_ID) {
if (!isset($id_class_desc) || empty($id_class_desc) || $id_class_desc == '') {
form_set_error('feeds_imagegrabber][id_class_desc', "Specify the id/class of the desired tag.");
}
@@ -187,16 +196,15 @@ function feeds_imagegrabber_feeds_node_p
function feeds_imagegrabber_feeds_set_target($node, $target, $page_url) {
$feed_nid = $node->feeds_node_item->feed_nid;
$settings = feeds_imagegrabber_get_settings($feed_nid);
+
if(!$settings || !$settings['enabled']) {
return;
}
- $path = drupal_get_path('module', 'feeds_imagegrabber') .'/url_to_absolute.php';
- if (!file_exists($path)) {
+ if (! feeds_imagegrabber_load_url_to_absolute()) {
drupal_set_message(t('Feeds Image Grabber: The URL conversion script is missing. Go to Status Report page', array('!admin-reports-status' => url('admin/reports/status'))), 'error');
- return;
+ return FALSE;
}
- require_once($path);
list($field_name) = split(':', $target);
$field = content_fields($field_name, $node->type);
@@ -212,20 +220,28 @@ function feeds_imagegrabber_feeds_set_ta
}
if (valid_url($page_url)) {
- $xml = feeds_imagegrabber_webpage_scraper($page_url, $settings['id_class'], $settings['id_class_desc'], $timeout);
- if ($xml == FALSE) {
- return;
+ if ($settings['id_class'] == FIG_SCRAPER_METHOD_URL) {
+ // No scraping, just get the image directly.
+ $images = array($page_url => 0);
}
- $timeout = $timeout - timer_read('page')/1000 + $page_time;
-
- $options = array(
- 'max_imagesize' => $max_filesize,
- 'timeout' => $timeout,
- 'feeling_lucky' => $settings['feeling_lucky'],
- );
-
- $images = feeds_imagegrabber_scrape_images($xml, $page_url, $options);
- if ($images == FALSE || count($images) <= 0) {
+ else {
+ $xml = feeds_imagegrabber_webpage_scraper($page_url, $settings['id_class'], $settings['id_class_desc'], $timeout);
+ if ($xml == FALSE) {
+ return;
+ }
+ $timeout = $timeout - timer_read('page')/1000 + $page_time;
+
+ $options = array(
+ 'max_imagesize' => $max_filesize,
+ 'timeout' => $timeout,
+ 'feeling_lucky' => $settings['feeling_lucky'],
+ );
+ $images = feeds_imagegrabber_scrape_images($xml, $page_url, $options);
+ // Done scraping.
+ }
+
+ if (empty($images)) {
+ watchdog('feeds_imagegrabber', 'No images to import from @url', array('@url' => $page_url), WATCHDOG_NOTICE);
return;
}
@@ -253,9 +269,15 @@ function feeds_imagegrabber_feeds_set_ta
break;
}
}
+ else {
+ watchdog('feeds_imagegrabber', 'Failed to retrieve image file from @url', array('@url' => $url), WATCHDOG_WARNING);
+ }
}
$node->$field_name = $items;
}
+ else {
+ watchdog('feeds_imagegrabber', 'Input to field was not a valid URL. @url', array('@url' => $page_url), WATCHDOG_WARNING);
+ }
}
//==================
@@ -448,17 +470,17 @@ function feeds_imagegrabber_webpage_scra
return FALSE;
}
- if ($itype == 0) {
+ if ($itype == FIG_SCRAPER_METHOD_NONE) {
$items = @$doc->getElementsByTagName("body");
if ($items != NULL && $items->length > 0) {
$dist = $items->item(0);
}
else $dist = NULL;
}
- elseif ($itype == 1) {
+ elseif ($itype == FIG_SCRAPER_METHOD_ID) {
$dist = @$doc->getElementById($ivalue);
}
- elseif ($itype == 2) {
+ elseif ($itype == FIG_SCRAPER_METHOD_CLASS) {
$xpath = new DOMXPath($doc);
$items = @$xpath->query("//*[@class and contains(concat(' ',normalize-space(@class),' '),' $ivalue ')]");
if ($items != NULL && $items->length > 0) {
@@ -837,3 +859,27 @@ function feeds_imagegrabber_http_request
return $result;
}
+/**
+ * Initializes the required AbsoluteUrl library.
+ *
+ * Package from http://sourceforge.net/projects/absoluteurl
+ * is expected to be in the module directory or sites/all/libraries
+ *
+ * @return bool success
+ */
+function feeds_imagegrabber_load_url_to_absolute() {
+ $paths = array(
+ drupal_get_path('module', 'feeds_imagegrabber'),
+ 'sites/all/libraries/absoluteurl',
+ 'sites/all/libraries/AbsoluteUrl',
+ );
+ foreach ($paths as $library_path) {
+ $path = $library_path . '/url_to_absolute.php';
+ if (file_exists($path)) {
+ require_once($path);
+ return TRUE;
+ }
+ }
+ // Failed.
+ return FALSE;
+}
\ No newline at end of file