mbirth/ttrss_plugin-af_feedmod
Archived
1
0
Fork 0
Code Issues 13 Pull Requests 5 Activity

added cleanup option for nodes fetched via xpath

Browse Source
This commit is contained in:
Roland Angerer 2013-06-19 11:31:31 +02:00
parent ff7ae3c171
commit 64a06e0c87
2 changed files with 13 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@ -50,7 +50,8 @@ A configuration looks like this:
},
"blog.beetlebum.de": {
"type": "xpath",
"xpath": "div[@class='entry-content']"
"xpath": "div[@class='entry-content']",
"cleanup": [ "header", "footer" ],
}
}
@ -62,6 +63,8 @@ The *array key* is part of the URL of the article links(!). You'll notice the `g
The **xpath** value is the actual Xpath-element to fetch from the linked page. Omit the leading `//` - they will get prepended automatically.
If **type** was set to `xpath' there is an additional option **cleanup** available. Its an array of Xpath-elements (relative to the fetched node) to remove from the fetched node. Omit the leading `//` - they will get prepended automatically.
**force_charset** allows to override automatic charset detection. If it is omitted, the charset will be parsed from the HTTP headers or loadHTML() will decide on its own.

9
init.php
View File

@ -116,6 +116,15 @@ class Af_Feedmod extends Plugin implements IHandler
if ($entries->length > 0) $basenode = $entries->item(0);
if ($basenode) {
// remove nodes from cleanup configuration
if (isset($config['cleanup'])) {
foreach ($config['cleanup'] as $cleanup) {
$nodelist = $xpath->query('//'.$cleanup, $basenode);
foreach ($nodelist as $node) {
$node->parentNode->removeChild($node);
}
}
}
$article['content'] = $doc->saveXML($basenode);
$article['plugin_data'] = "feedmod,$owner_uid:" . $article['plugin_data'];
}