From cd07592c29391ca374f78a75a10465f894d50042 Mon Sep 17 00:00:00 2001 From: Andrew Dolgov Date: Wed, 1 May 2013 17:04:57 +0400 Subject: [PATCH] add basic tinyparser/atom --- classes/feedenclosure.php | 7 +++ classes/feeditem.php | 15 +++++ classes/feeditem/atom.php | 118 ++++++++++++++++++++++++++++++++++++++ classes/feedparser.php | 101 ++++++++++++++++++++++++++++++++ include/rssfuncs.php | 27 ++++----- 5 files changed, 255 insertions(+), 13 deletions(-) create mode 100644 classes/feedenclosure.php create mode 100644 classes/feeditem.php create mode 100644 classes/feeditem/atom.php create mode 100644 classes/feedparser.php diff --git a/classes/feedenclosure.php b/classes/feedenclosure.php new file mode 100644 index 00000000..d610dd7c --- /dev/null +++ b/classes/feedenclosure.php @@ -0,0 +1,7 @@ + diff --git a/classes/feeditem.php b/classes/feeditem.php new file mode 100644 index 00000000..cc39fcee --- /dev/null +++ b/classes/feeditem.php @@ -0,0 +1,15 @@ + diff --git a/classes/feeditem/atom.php b/classes/feeditem/atom.php new file mode 100644 index 00000000..560484ed --- /dev/null +++ b/classes/feeditem/atom.php @@ -0,0 +1,118 @@ +elem = $elem; + } + + function get_id() { + $id = $this->elem->getElementsByTagName("id")->item(0); + + if ($id) { + return $id->nodeValue; + } else { + return $this->get_link(); + } + } + + function get_date() { + + + } + + function get_link() { + $links = $this->elem->getElementsByTagName("link"); + + foreach ($links as $link) { + if ($link && $link->hasAttribute("href") && !$link->hasAttribute("rel")) { + return $link->getAttribute("href"); + } + } + } + + function get_title() { + $title = $this->elem->getElementsByTagName("title")->item(0); + + if ($title) { + return $title->nodeValue; + } + } + + function get_content() { + $content = $this->elem->getElementsByTagName("content")->item(0); + + if ($content) { + return $content->nodeValue; + } + } + + function get_description() { + $summary = $this->elem->getElementsByTagName("summary")->item(0); + + if ($summary) { + return $summary->nodeValue; + } + } + + // todo + function get_comments_url() { + + } + + // todo + function get_comments_count() { + + } + + function get_categories() { + $categories = $this->elem->getElementsByTagName("category"); + $cats = array(); + + foreach ($categories as $cat) { + if ($cat->hasAttribute("term")) + array_push($cats, $cat->getAttribute("term")); + } + + + return $cats; + } + + function get_enclosures() { + $links = $this->elem->getElementsByTagName("link"); + + $encs = array(); + + foreach ($links as $link) { + if ($link && $link->hasAttribute("href") && $link->hasAttribute("rel")) { + if ($link->getAttribute("rel") == "enclosure") { + $enc = new FeedEnclosure(); + + $enc->type = $link->getAttribute("type"); + $enc->link = $link->getAttribute("href"); + $enc->length = $link->getAttribute("length"); + + array_push($encs, $enc); + } + } + } + + return $encs; + } + + function get_author() { + $author = $this->elem->getElementsByTagName("author")->item(0); + + if ($author) { + $name = $author->getElementsByTagName("name")->item(0); + + if ($name) return $name->nodeValue; + + $email = $author->getElementsByTagName("email")->item(0); + + if ($email) return $email->nodeValue; + + } + } +} +?> diff --git a/classes/feedparser.php b/classes/feedparser.php new file mode 100644 index 00000000..274e871b --- /dev/null +++ b/classes/feedparser.php @@ -0,0 +1,101 @@ +doc = new DOMDocument(); + $this->doc->loadXML($data); + $this->error = $this->format_error(libxml_get_last_error()); + libxml_clear_errors(); + + $this->items = array(); + } + + function init() { + $root = $this->doc->firstChild; + + if ($root) { + switch ($root->tagName) { + case "rss": + $this->type = $this::FEED_RSS; + break; + case "feed": + $this->type = $this::FEED_ATOM; + break; + default: + $this->error = "Unknown/unsupported feed type"; + return; + } + + $xpath = new DOMXPath($this->doc); + + switch ($this->type) { + case $this::FEED_ATOM: + $xpath->registerNamespace('atom', 'http://www.w3.org/2005/Atom'); + + $title = $xpath->query("//atom:feed/atom:title")->item(0); + + if ($title) { + $this->title = $title->nodeValue; + } + + $link = $xpath->query("//atom:feed/atom:link[not(@rel)]")->item(0); + + if ($link && $link->hasAttributes()) { + $this->link = $link->getAttribute("href"); + } + + $articles = $xpath->query("//atom:entry"); + + foreach ($articles as $article) { + array_push($this->items, new FeedItem_Atom($article)); + } + + break; + case $this::FEED_RDF: + + break; + case $this::FEED_RSS: + break; + } + } + } + + function format_error($error) { + if ($error) { + return sprintf("LibXML error %s at line %d (column %d): %s", + $error->code, $error->line, $error->column, + $error->message); + } else { + return ""; + } + } + + function error() { + return $this->error; + } + + function get_link() { + return $this->link; + } + + function get_title() { + return $this->title; + } + + function get_items() { + return $this->items; + } + +} ?> diff --git a/include/rssfuncs.php b/include/rssfuncs.php index 08bf1fe6..3b7f7d2c 100644 --- a/include/rssfuncs.php +++ b/include/rssfuncs.php @@ -361,16 +361,17 @@ } if (!$rss) { - $rss = new SimplePie(); + /* $rss = new SimplePie(); $rss->set_sanitize_class("SanitizeDummy"); // simplepie ignores the above and creates default sanitizer anyway, // so let's override it... $rss->sanitize = new SanitizeDummy(); $rss->set_output_encoding('UTF-8'); $rss->set_raw_data($feed_data); - $rss->enable_cache(false); + $rss->enable_cache(false); */ - @$rss->init(); + $rss = new FeedParser($feed_data); + $rss->init(); } // print_r($rss); @@ -386,7 +387,7 @@ if ($new_rss_hash != $rss_hash) { _debug("saving $cache_filename", $debug_enabled); - @file_put_contents($cache_filename, serialize($rss)); + //@file_put_contents($cache_filename, serialize($rss)); NOT YET } } @@ -418,6 +419,9 @@ $site_url = db_escape_string(mb_substr(rewrite_relative_url($fetch_url, $rss->get_link()), 0, 245)); + _debug("site_url: $site_url", $debug_enabled); + _debug("feed_title: " . $rss->get_title(), $debug_enabled); + if ($favicon_needs_check || $force_refetch) { /* terrible hack: if we crash on floicon shit here, we won't check @@ -533,6 +537,8 @@ if (!$entry_guid) $entry_guid = $item->get_link(); if (!$entry_guid) $entry_guid = make_guid_from_title($item->get_title()); + _debug("f_guid $entry_guid", $debug_enabled); + if (!$entry_guid) continue; $entry_guid = "$owner_uid,$entry_guid"; @@ -575,20 +581,15 @@ print "\n"; } - $entry_comments = $item->data["comments"]; - - if ($item->get_author()) { - $entry_author_item = $item->get_author(); - $entry_author = $entry_author_item->get_name(); - if (!$entry_author) $entry_author = $entry_author_item->get_email(); - } + $entry_comments = $item->get_comments_url(); + $entry_author = $item->get_author(); $entry_guid = db_escape_string(mb_substr($entry_guid, 0, 245)); $entry_comments = db_escape_string(mb_substr(trim($entry_comments), 0, 245)); $entry_author = db_escape_string(mb_substr(trim($entry_author), 0, 245)); - $num_comments = $item->get_item_tags('http://purl.org/rss/1.0/modules/slash/', 'comments'); + $num_comments = $item->get_comments_count(); if (is_array($num_comments) && is_array($num_comments[0])) { $num_comments = (int) $num_comments[0]["data"]; @@ -608,7 +609,7 @@ if (is_array($additional_tags_src)) { foreach ($additional_tags_src as $tobj) { - array_push($additional_tags, $tobj->get_term()); + array_push($additional_tags, $tobj); } } -- 2.39.2