修改ua信息
This commit is contained in:
@@ -1,246 +1,246 @@
|
|||||||
<?php
|
<?php
|
||||||
/*
|
/*
|
||||||
======================================================================
|
======================================================================
|
||||||
lastRSS 0.9.1
|
lastRSS 0.9.1
|
||||||
|
|
||||||
Simple yet powerfull PHP class to parse RSS files.
|
Simple yet powerfull PHP class to parse RSS files.
|
||||||
|
|
||||||
by Vojtech Semecky, webmaster @ webdot . cz
|
by Vojtech Semecky, webmaster @ webdot . cz
|
||||||
|
|
||||||
Latest version, features, manual and examples:
|
Latest version, features, manual and examples:
|
||||||
http://lastrss.webdot.cz/
|
http://lastrss.webdot.cz/
|
||||||
|
|
||||||
----------------------------------------------------------------------
|
----------------------------------------------------------------------
|
||||||
LICENSE
|
LICENSE
|
||||||
|
|
||||||
This program is free software; you can redistribute it and/or
|
This program is free software; you can redistribute it and/or
|
||||||
modify it under the terms of the GNU General Public License (GPL)
|
modify it under the terms of the GNU General Public License (GPL)
|
||||||
as published by the Free Software Foundation; either version 2
|
as published by the Free Software Foundation; either version 2
|
||||||
of the License, or (at your option) any later version.
|
of the License, or (at your option) any later version.
|
||||||
|
|
||||||
This program is distributed in the hope that it will be useful,
|
This program is distributed in the hope that it will be useful,
|
||||||
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||||
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||||
GNU General Public License for more details.
|
GNU General Public License for more details.
|
||||||
|
|
||||||
To read the license please visit http://www.gnu.org/copyleft/gpl.html
|
To read the license please visit http://www.gnu.org/copyleft/gpl.html
|
||||||
======================================================================
|
======================================================================
|
||||||
*/
|
*/
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* lastRSS
|
* lastRSS
|
||||||
* Simple yet powerfull PHP class to parse RSS files.
|
* Simple yet powerfull PHP class to parse RSS files.
|
||||||
*/
|
*/
|
||||||
class lastRSS {
|
class lastRSS {
|
||||||
// -------------------------------------------------------------------
|
// -------------------------------------------------------------------
|
||||||
// Public properties
|
// Public properties
|
||||||
// -------------------------------------------------------------------
|
// -------------------------------------------------------------------
|
||||||
var $default_cp = 'UTF-8';
|
var $default_cp = 'UTF-8';
|
||||||
var $CDATA = 'nochange';
|
var $CDATA = 'nochange';
|
||||||
var $cp = '';
|
var $cp = '';
|
||||||
var $items_limit = 0;
|
var $items_limit = 0;
|
||||||
var $stripHTML = False;
|
var $stripHTML = False;
|
||||||
var $date_format = '';
|
var $date_format = '';
|
||||||
|
|
||||||
// -------------------------------------------------------------------
|
// -------------------------------------------------------------------
|
||||||
// Private variables
|
// Private variables
|
||||||
// -------------------------------------------------------------------
|
// -------------------------------------------------------------------
|
||||||
var $channeltags = array ('title', 'link', 'description', 'language', 'copyright', 'managingEditor', 'webMaster', 'lastBuildDate', 'rating', 'docs');
|
var $channeltags = array ('title', 'link', 'description', 'language', 'copyright', 'managingEditor', 'webMaster', 'lastBuildDate', 'rating', 'docs');
|
||||||
var $itemtags = array('title', 'link', 'description', 'author', 'category', 'comments', 'enclosure', 'guid', 'pubDate', 'source');
|
var $itemtags = array('title', 'link', 'description', 'author', 'category', 'comments', 'enclosure', 'guid', 'pubDate', 'source');
|
||||||
var $imagetags = array('title', 'url', 'link', 'width', 'height');
|
var $imagetags = array('title', 'url', 'link', 'width', 'height');
|
||||||
var $textinputtags = array('title', 'description', 'name', 'link');
|
var $textinputtags = array('title', 'description', 'name', 'link');
|
||||||
|
|
||||||
// -------------------------------------------------------------------
|
// -------------------------------------------------------------------
|
||||||
// Parse RSS file and returns associative array.
|
// Parse RSS file and returns associative array.
|
||||||
// -------------------------------------------------------------------
|
// -------------------------------------------------------------------
|
||||||
function Get ($rss_url) {
|
function Get ($rss_url) {
|
||||||
// If CACHE ENABLED
|
// If CACHE ENABLED
|
||||||
if ($this->cache_dir != '') {
|
if ($this->cache_dir != '') {
|
||||||
$cache_file = $this->cache_dir . '/rsscache_' . md5($rss_url);
|
$cache_file = $this->cache_dir . '/rsscache_' . md5($rss_url);
|
||||||
$timedif = @(time() - filemtime($cache_file));
|
$timedif = @(time() - filemtime($cache_file));
|
||||||
if ($timedif < $this->cache_time) {
|
if ($timedif < $this->cache_time) {
|
||||||
// cached file is fresh enough, return cached array
|
// cached file is fresh enough, return cached array
|
||||||
$result = unserialize(join('', file($cache_file)));
|
$result = unserialize(join('', file($cache_file)));
|
||||||
// set 'cached' to 1 only if cached file is correct
|
// set 'cached' to 1 only if cached file is correct
|
||||||
if ($result) $result['cached'] = 1;
|
if ($result) $result['cached'] = 1;
|
||||||
} else {
|
} else {
|
||||||
// cached file is too old, create new
|
// cached file is too old, create new
|
||||||
$result = $this->Parse($rss_url);
|
$result = $this->Parse($rss_url);
|
||||||
$serialized = serialize($result);
|
$serialized = serialize($result);
|
||||||
if ($f = @fopen($cache_file, 'w')) {
|
if ($f = @fopen($cache_file, 'w')) {
|
||||||
fwrite ($f, $serialized, strlen($serialized));
|
fwrite ($f, $serialized, strlen($serialized));
|
||||||
fclose($f);
|
fclose($f);
|
||||||
}
|
}
|
||||||
if ($result) $result['cached'] = 0;
|
if ($result) $result['cached'] = 0;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
// If CACHE DISABLED >> load and parse the file directly
|
// If CACHE DISABLED >> load and parse the file directly
|
||||||
else {
|
else {
|
||||||
$result = $this->Parse($rss_url);
|
$result = $this->Parse($rss_url);
|
||||||
if ($result) $result['cached'] = 0;
|
if ($result) $result['cached'] = 0;
|
||||||
}
|
}
|
||||||
// return result
|
// return result
|
||||||
return $result;
|
return $result;
|
||||||
}
|
}
|
||||||
|
|
||||||
// -------------------------------------------------------------------
|
// -------------------------------------------------------------------
|
||||||
// Modification of preg_match(); return trimed field with index 1
|
// Modification of preg_match(); return trimed field with index 1
|
||||||
// from 'classic' preg_match() array output
|
// from 'classic' preg_match() array output
|
||||||
// -------------------------------------------------------------------
|
// -------------------------------------------------------------------
|
||||||
function my_preg_match ($pattern, $subject) {
|
function my_preg_match ($pattern, $subject) {
|
||||||
// start regullar expression
|
// start regullar expression
|
||||||
preg_match($pattern, $subject, $out);
|
preg_match($pattern, $subject, $out);
|
||||||
|
|
||||||
// if there is some result... process it and return it
|
// if there is some result... process it and return it
|
||||||
if(isset($out[1])) {
|
if(isset($out[1])) {
|
||||||
// Process CDATA (if present)
|
// Process CDATA (if present)
|
||||||
if ($this->CDATA == 'content') { // Get CDATA content (without CDATA tag)
|
if ($this->CDATA == 'content') { // Get CDATA content (without CDATA tag)
|
||||||
$out[1] = strtr($out[1], array('<![CDATA['=>'', ']]>'=>''));
|
$out[1] = strtr($out[1], array('<![CDATA['=>'', ']]>'=>''));
|
||||||
} elseif ($this->CDATA == 'strip') { // Strip CDATA
|
} elseif ($this->CDATA == 'strip') { // Strip CDATA
|
||||||
$out[1] = strtr($out[1], array('<![CDATA['=>'', ']]>'=>''));
|
$out[1] = strtr($out[1], array('<![CDATA['=>'', ']]>'=>''));
|
||||||
}
|
}
|
||||||
|
|
||||||
// If code page is set convert character encoding to required
|
// If code page is set convert character encoding to required
|
||||||
if ($this->cp != '')
|
if ($this->cp != '')
|
||||||
//$out[1] = $this->MyConvertEncoding($this->rsscp, $this->cp, $out[1]);
|
//$out[1] = $this->MyConvertEncoding($this->rsscp, $this->cp, $out[1]);
|
||||||
$out[1] = iconv($this->rsscp, $this->cp.'//TRANSLIT', $out[1]);
|
$out[1] = iconv($this->rsscp, $this->cp.'//TRANSLIT', $out[1]);
|
||||||
// Return result
|
// Return result
|
||||||
return trim($out[1]);
|
return trim($out[1]);
|
||||||
} else {
|
} else {
|
||||||
// if there is NO result, return empty string
|
// if there is NO result, return empty string
|
||||||
return '';
|
return '';
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// -------------------------------------------------------------------
|
// -------------------------------------------------------------------
|
||||||
// Replace HTML entities &something; by real characters
|
// Replace HTML entities &something; by real characters
|
||||||
// -------------------------------------------------------------------
|
// -------------------------------------------------------------------
|
||||||
function unhtmlentities ($string) {
|
function unhtmlentities ($string) {
|
||||||
// Get HTML entities table
|
// Get HTML entities table
|
||||||
$trans_tbl = get_html_translation_table (HTML_ENTITIES, ENT_QUOTES);
|
$trans_tbl = get_html_translation_table (HTML_ENTITIES, ENT_QUOTES);
|
||||||
// Flip keys<==>values
|
// Flip keys<==>values
|
||||||
$trans_tbl = array_flip ($trans_tbl);
|
$trans_tbl = array_flip ($trans_tbl);
|
||||||
// Add support for ' entity (missing in HTML_ENTITIES)
|
// Add support for ' entity (missing in HTML_ENTITIES)
|
||||||
$trans_tbl += array(''' => "'");
|
$trans_tbl += array(''' => "'");
|
||||||
// Replace entities by values
|
// Replace entities by values
|
||||||
return strtr ($string, $trans_tbl);
|
return strtr ($string, $trans_tbl);
|
||||||
}
|
}
|
||||||
|
|
||||||
// -------------------------------------------------------------------
|
// -------------------------------------------------------------------
|
||||||
// Get remote file or open url
|
// Get remote file or open url
|
||||||
// -------------------------------------------------------------------
|
// -------------------------------------------------------------------
|
||||||
function getRemoteFile ($url){
|
function getRemoteFile ($url){
|
||||||
$results = '';
|
$results = '';
|
||||||
$context = stream_context_create(array(
|
$context = stream_context_create(array(
|
||||||
'http' => array(
|
'http' => array(
|
||||||
'timeout' => 3
|
'timeout' => 3
|
||||||
)
|
)
|
||||||
));
|
));
|
||||||
if (get_cfg_var('allow_url_fopen')) {
|
if (get_cfg_var('allow_url_fopen')) {
|
||||||
$f = fopen($url, 'r');
|
$f = fopen($url, 'r');
|
||||||
while (!feof($f)) {
|
while (!feof($f)) {
|
||||||
$results .= fgets($f, 4096);
|
$results .= fgets($f, 4096);
|
||||||
}
|
}
|
||||||
fclose($f);
|
fclose($f);
|
||||||
} else if (extension_loaded('curl')) {
|
} else if (extension_loaded('curl')) {
|
||||||
$ch = curl_init();
|
$ch = curl_init();
|
||||||
curl_setopt($ch, CURLOPT_URL, $url);
|
curl_setopt($ch, CURLOPT_URL, $url);
|
||||||
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
|
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
|
||||||
curl_setopt($ch, CURLOPT_TIMEOUT, 5);
|
curl_setopt($ch, CURLOPT_TIMEOUT, 5);
|
||||||
curl_setopt($ch, CURLOPT_USERAGENT, 'PHP Curl/emlog Rss订阅插件');
|
curl_setopt($ch, CURLOPT_USERAGENT, 'PHP Curl/xiaosong.org 1.0 BETA');
|
||||||
$results = curl_exec($ch);
|
$results = curl_exec($ch);
|
||||||
curl_close($ch);
|
curl_close($ch);
|
||||||
} else {
|
} else {
|
||||||
$results = file_get_contents($url, 0, $context);
|
$results = file_get_contents($url, 0, $context);
|
||||||
}
|
}
|
||||||
return $results;
|
return $results;
|
||||||
}
|
}
|
||||||
|
|
||||||
// -------------------------------------------------------------------
|
// -------------------------------------------------------------------
|
||||||
// Parse() is private method used by Get() to load and parse RSS file.
|
// Parse() is private method used by Get() to load and parse RSS file.
|
||||||
// Don't use Parse() in your scripts - use Get($rss_file) instead.
|
// Don't use Parse() in your scripts - use Get($rss_file) instead.
|
||||||
// -------------------------------------------------------------------
|
// -------------------------------------------------------------------
|
||||||
function Parse ($rss_url) {
|
function Parse ($rss_url) {
|
||||||
// Open and load RSS file
|
// Open and load RSS file
|
||||||
$rss_content = $this->getRemoteFile($rss_url);
|
$rss_content = $this->getRemoteFile($rss_url);
|
||||||
if (!empty($rss_content)) {
|
if (!empty($rss_content)) {
|
||||||
|
|
||||||
// Parse document encoding
|
// Parse document encoding
|
||||||
$result['encoding'] = $this->my_preg_match("'encoding=[\'\"](.*?)[\'\"]'si", $rss_content);
|
$result['encoding'] = $this->my_preg_match("'encoding=[\'\"](.*?)[\'\"]'si", $rss_content);
|
||||||
// if document codepage is specified, use it
|
// if document codepage is specified, use it
|
||||||
if ($result['encoding'] != '')
|
if ($result['encoding'] != '')
|
||||||
{ $this->rsscp = $result['encoding']; } // This is used in my_preg_match()
|
{ $this->rsscp = $result['encoding']; } // This is used in my_preg_match()
|
||||||
// otherwise use the default codepage
|
// otherwise use the default codepage
|
||||||
else
|
else
|
||||||
{ $this->rsscp = $this->default_cp; } // This is used in my_preg_match()
|
{ $this->rsscp = $this->default_cp; } // This is used in my_preg_match()
|
||||||
|
|
||||||
// Parse CHANNEL info
|
// Parse CHANNEL info
|
||||||
preg_match("'<channel.*?>(.*?)</channel>'si", $rss_content, $out_channel);
|
preg_match("'<channel.*?>(.*?)</channel>'si", $rss_content, $out_channel);
|
||||||
foreach($this->channeltags as $channeltag)
|
foreach($this->channeltags as $channeltag)
|
||||||
{
|
{
|
||||||
$temp = $this->my_preg_match("'<$channeltag.*?>(.*?)</$channeltag>'si", $out_channel[1]);
|
$temp = $this->my_preg_match("'<$channeltag.*?>(.*?)</$channeltag>'si", $out_channel[1]);
|
||||||
if ($temp != '') $result[$channeltag] = $temp; // Set only if not empty
|
if ($temp != '') $result[$channeltag] = $temp; // Set only if not empty
|
||||||
}
|
}
|
||||||
// If date_format is specified and lastBuildDate is valid
|
// If date_format is specified and lastBuildDate is valid
|
||||||
if ($this->date_format != '' && ($timestamp = strtotime($result['lastBuildDate'])) !==-1) {
|
if ($this->date_format != '' && ($timestamp = strtotime($result['lastBuildDate'])) !==-1) {
|
||||||
// convert lastBuildDate to specified date format
|
// convert lastBuildDate to specified date format
|
||||||
$result['lastBuildDate'] = date($this->date_format, $timestamp);
|
$result['lastBuildDate'] = date($this->date_format, $timestamp);
|
||||||
}
|
}
|
||||||
|
|
||||||
// Parse TEXTINPUT info
|
// Parse TEXTINPUT info
|
||||||
preg_match("'<textinput(|[^>]*[^/])>(.*?)</textinput>'si", $rss_content, $out_textinfo);
|
preg_match("'<textinput(|[^>]*[^/])>(.*?)</textinput>'si", $rss_content, $out_textinfo);
|
||||||
// This a little strange regexp means:
|
// This a little strange regexp means:
|
||||||
// Look for tag <textinput> with or without any attributes, but skip truncated version <textinput /> (it's not beggining tag)
|
// Look for tag <textinput> with or without any attributes, but skip truncated version <textinput /> (it's not beggining tag)
|
||||||
if (isset($out_textinfo[2])) {
|
if (isset($out_textinfo[2])) {
|
||||||
foreach($this->textinputtags as $textinputtag) {
|
foreach($this->textinputtags as $textinputtag) {
|
||||||
$temp = $this->my_preg_match("'<$textinputtag.*?>(.*?)</$textinputtag>'si", $out_textinfo[2]);
|
$temp = $this->my_preg_match("'<$textinputtag.*?>(.*?)</$textinputtag>'si", $out_textinfo[2]);
|
||||||
if ($temp != '') $result['textinput_'.$textinputtag] = $temp; // Set only if not empty
|
if ($temp != '') $result['textinput_'.$textinputtag] = $temp; // Set only if not empty
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
// Parse IMAGE info
|
// Parse IMAGE info
|
||||||
preg_match("'<image.*?>(.*?)</image>'si", $rss_content, $out_imageinfo);
|
preg_match("'<image.*?>(.*?)</image>'si", $rss_content, $out_imageinfo);
|
||||||
if (isset($out_imageinfo[1])) {
|
if (isset($out_imageinfo[1])) {
|
||||||
foreach($this->imagetags as $imagetag) {
|
foreach($this->imagetags as $imagetag) {
|
||||||
$temp = $this->my_preg_match("'<$imagetag.*?>(.*?)</$imagetag>'si", $out_imageinfo[1]);
|
$temp = $this->my_preg_match("'<$imagetag.*?>(.*?)</$imagetag>'si", $out_imageinfo[1]);
|
||||||
if ($temp != '') $result['image_'.$imagetag] = $temp; // Set only if not empty
|
if ($temp != '') $result['image_'.$imagetag] = $temp; // Set only if not empty
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
// Parse ITEMS
|
// Parse ITEMS
|
||||||
preg_match_all("'<item(| .*?)>(.*?)</item>'si", $rss_content, $items);
|
preg_match_all("'<item(| .*?)>(.*?)</item>'si", $rss_content, $items);
|
||||||
$rss_items = $items[2];
|
$rss_items = $items[2];
|
||||||
$i = 0;
|
$i = 0;
|
||||||
$result['items'] = array(); // create array even if there are no items
|
$result['items'] = array(); // create array even if there are no items
|
||||||
foreach($rss_items as $rss_item) {
|
foreach($rss_items as $rss_item) {
|
||||||
// If number of items is lower then limit: Parse one item
|
// If number of items is lower then limit: Parse one item
|
||||||
if ($i < $this->items_limit || $this->items_limit == 0) {
|
if ($i < $this->items_limit || $this->items_limit == 0) {
|
||||||
foreach($this->itemtags as $itemtag) {
|
foreach($this->itemtags as $itemtag) {
|
||||||
$temp = $this->my_preg_match("'<$itemtag.*?>(.*?)</$itemtag>'si", $rss_item);
|
$temp = $this->my_preg_match("'<$itemtag.*?>(.*?)</$itemtag>'si", $rss_item);
|
||||||
if ($temp != '') $result['items'][$i][$itemtag] = $temp; // Set only if not empty
|
if ($temp != '') $result['items'][$i][$itemtag] = $temp; // Set only if not empty
|
||||||
}
|
}
|
||||||
// Strip HTML tags and other bullshit from DESCRIPTION
|
// Strip HTML tags and other bullshit from DESCRIPTION
|
||||||
if ($this->stripHTML && $result['items'][$i]['description'])
|
if ($this->stripHTML && $result['items'][$i]['description'])
|
||||||
$result['items'][$i]['description'] = strip_tags($this->unhtmlentities(strip_tags($result['items'][$i]['description'])));
|
$result['items'][$i]['description'] = strip_tags($this->unhtmlentities(strip_tags($result['items'][$i]['description'])));
|
||||||
// Strip HTML tags and other bullshit from TITLE
|
// Strip HTML tags and other bullshit from TITLE
|
||||||
if ($this->stripHTML && $result['items'][$i]['title'])
|
if ($this->stripHTML && $result['items'][$i]['title'])
|
||||||
$result['items'][$i]['title'] = strip_tags($this->unhtmlentities(strip_tags($result['items'][$i]['title'])));
|
$result['items'][$i]['title'] = strip_tags($this->unhtmlentities(strip_tags($result['items'][$i]['title'])));
|
||||||
// If date_format is specified and pubDate is valid
|
// If date_format is specified and pubDate is valid
|
||||||
if ($this->date_format != '' && ($timestamp = strtotime($result['items'][$i]['pubDate'])) !==-1) {
|
if ($this->date_format != '' && ($timestamp = strtotime($result['items'][$i]['pubDate'])) !==-1) {
|
||||||
// convert pubDate to specified date format
|
// convert pubDate to specified date format
|
||||||
$result['items'][$i]['pubDate'] = date($this->date_format, $timestamp);
|
$result['items'][$i]['pubDate'] = date($this->date_format, $timestamp);
|
||||||
}
|
}
|
||||||
// Item counter
|
// Item counter
|
||||||
$i++;
|
$i++;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
$result['items_count'] = $i;
|
$result['items_count'] = $i;
|
||||||
return $result;
|
return $result;
|
||||||
}
|
}
|
||||||
else // Error in opening return False
|
else // Error in opening return False
|
||||||
{
|
{
|
||||||
return False;
|
return False;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
?>
|
?>
|
||||||
Reference in New Issue
Block a user