blallo/rss-bridge
1
0
Fork 1
Code Issues Pull requests Releases Wiki Activity

[contents] Replace file_get_contents by cURL

Browse source 
cURL is a powerful library specifically designed to connect to many
different types of servers with different types of protocols. For
more detailed information refer to the PHP cURL manual:

- http://php.net/manual/en/book.curl.php

Due to this change some parameters for the getContents function were
necessary (also applies to getSimpleHTMLDOM and getSimpleHTMLDOMCached):

> $use_include_path removed

  This parameter has never been used and doesn't even make sense in
  this context; If set to true file_get_contents would also search
  for files in the include_path (specified in php.ini).

> $context replaced by $header and $opts

  The $context parameter allowed for customization of the request in
  order to change how file_get_contents would acquire the data (i.e.
  using POST instead of GET, sending custom header, etc...)

  cURL also provides facilities to specify custom headers and change
  how it communicates to severs. cURL, however, is much more advanced.

  - $header is an optional parameter (empty by default). It receives
    an array of strings to send in the HTTP request header.

    See 'CURLOPT_HTTPHEADER':

    "An array of HTTP header fields to set, in the format
    array('Content-type: text/plain', 'Content-length: 100')"

    - php.net/manual/en/function.curl-setopt.php

  - $opts is an optional parameter (empty by default). It receives
    an array of options, where each option is a key-value-pair of
    a cURL option (CURLOPT_*) and it's associated parameter. This
    parameter accepts any of the CURLOPT_* settings.

    Example (sending POST instead of GET):

    $opts = array(
      CURLOPT_POST => 1,
      CURLOPT_POSTFIELDS => '&action=none'
    );
    $html = getContents($url, array(), $opts);

    Refer to the cURL setopt manual for more information:
    - php.net/manual/en/function.curl-setopt.php

> $offset and $maxlen removed

  These options were supported by file_get_contents, but there doesn't
  seem to be an equivalent in cURL. Since no caller uses them they are
  safe to remove.

Compressed data / Encoding

  By using cURL instead of file_get_contents RSS-Bridge no longer has
  to handle compressed data manually.

  See 'CURLOPT_ENCODING':

  "[...] Supported encodings are "identity", "deflate", and "gzip".
  If an empty string, "", is set, a header containing all supported
  encoding types is sent."

  - http://php.net/manual/en/function.curl-setopt.php

  Notice: By default all encoding types are accepted (""). This can
  be changed by setting a custom option via $opts.

    Example:

    $opts = array(CURLOPT_ENCODING => 'gzip');
    $html = getContents($url, array(), $opts);

Proxy

The proxy implementation should still work, but there doesn't seem
to be an equivalent for 'request_fulluri = true'. To my understanding
this isn't an issue because cURL knows how to handle proxy communication.
This commit is contained in:
logmanoriginal 2018-03-25 13:12:13 +02:00
parent 2df2623430
commit ee78e7613f
1 changed files with 21 additions and 59 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

80
lib/contents.php
View file

@ -1,77 +1,41 @@
<?php
function getContents($url,
$use_include_path = false,
$context = null,
$offset = 0,
$maxlen = null){
$contextOptions = array(
'http' => array(
'user_agent' => ini_get('user_agent'),
'accept_encoding' => 'gzip'
)
);
function getContents($url, $header = array(), $opts = array()){
$ch = curl_init($url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, $header);
curl_setopt($ch, CURLOPT_USERAGENT, ini_get('user_agent'));
curl_setopt($ch, CURLOPT_ENCODING, '');
if(defined('PROXY_URL') && !defined('NOPROXY')) {
$contextOptions['http']['proxy'] = PROXY_URL;
$contextOptions['http']['request_fulluri'] = true;
if(is_null($context)) {
$context = stream_context_create($contextOptions);
} else {
$prevContext = $context;
if(!stream_context_set_option($context, $contextOptions)) {
$context = $prevContext;
}
if(is_array($opts)) {
foreach($opts as $key => $value) {
curl_setopt($ch, $key, $value);
}
}
if(is_null($maxlen)) {
$content = file_get_contents($url, $use_include_path, $context, $offset);
} else {
$content = file_get_contents($url, $use_include_path, $context, $offset, $maxlen);
if(defined('PROXY_URL') && !defined('NOPROXY')) {
curl_setopt($ch, CURLOPT_PROXY, PROXY_URL);
}
$content = curl_exec($ch);
curl_close($ch);
if($content === false)
debugMessage('Cant\'t download ' . $url);
// handle compressed data
foreach($http_response_header as $header) {
if(stristr($header, 'content-encoding')) {
switch(true) {
case stristr($header, 'gzip'):
$content = gzinflate(substr($content, 10, -8));
break;
case stristr($header, 'compress'):
//TODO
case stristr($header, 'deflate'):
//TODO
case stristr($header, 'brotli'):
//TODO
returnServerError($header . '=> Not implemented yet');
break;
case stristr($header, 'identity'):
break;
default:
returnServerError($header . '=> Unknown compression');
}
}
}
return $content;
}
function getSimpleHTMLDOM($url,
$use_include_path = false,
$context = null,
$offset = 0,
$maxLen = null,
$header = array(),
$opts = array(),
$lowercase = true,
$forceTagsClosed = true,
$target_charset = DEFAULT_TARGET_CHARSET,
$stripRN = true,
$defaultBRText = DEFAULT_BR_TEXT,
$defaultSpanText = DEFAULT_SPAN_TEXT){
$content = getContents($url, $use_include_path, $context, $offset, $maxLen);
$content = getContents($url, $header, $opts);
return str_get_html($content,
$lowercase,
$forceTagsClosed,
@ -89,10 +53,8 @@ $defaultSpanText = DEFAULT_SPAN_TEXT){
*/
function getSimpleHTMLDOMCached($url,
$duration = 86400,
$use_include_path = false,
$context = null,
$offset = 0,
$maxLen = null,
$header = array(),
$opts = array(),
$lowercase = true,
$forceTagsClosed = true,
$target_charset = DEFAULT_TARGET_CHARSET,
@ -116,7 +78,7 @@ $defaultSpanText = DEFAULT_SPAN_TEXT){
&& (!defined('DEBUG') || DEBUG !== true)) { // Contents within duration
$content = $cache->loadData();
} else { // Content not within duration
$content = getContents($url, $use_include_path, $context, $offset, $maxLen);
$content = getContents($url, $header, $opts);
if($content !== false) {
$cache->saveData($content);
}