Handle redirects when scraping feed from HTML (#7654)

* Handle redirects when scraping feed from HTML

* pass codesniffer

* pass PHPStan

* Optimize

* Another approach relying on HTML base
Standard way to save an HTML document with relative references

* Fix case of existing HTML base
which should not be overriden

---------

Co-authored-by: Alexandre Alapetite <alexandre@alapetite.fr>
This commit is contained in:
Inverle
2025-06-22 00:09:18 +02:00
committed by GitHub
parent a6948218fb
commit 18b5c8ec6d
5 changed files with 55 additions and 12 deletions

View File

@@ -48,7 +48,7 @@ class FreshRSS_extension_Controller extends FreshRSS_ActionController {
$cacheFile = CACHE_PATH . '/extension_list.json';
if (FreshRSS_Context::userConf()->retrieve_extension_list === true) {
if (!file_exists($cacheFile) || (time() - (filemtime($cacheFile) ?: 0) > 86400)) {
$json = httpGet($extensionListUrl, $cacheFile, 'json');
$json = httpGet($extensionListUrl, $cacheFile, 'json')['body'];
} else {
$json = @file_get_contents($cacheFile) ?: '';
}

View File

@@ -188,7 +188,7 @@ class FreshRSS_Category extends Minz_Model {
}
$ok = true;
$cachePath = $this->cacheFilename($url);
$opml = httpGet($url, $cachePath, 'opml', $this->attributes(), $this->curlOptions());
$opml = httpGet($url, $cachePath, 'opml', $this->attributes(), $this->curlOptions())['body'];
if ($opml == '') {
Minz_Log::warning('Error getting dynamic OPML for category ' . $this->id() . '! ' .
\SimplePie\Misc::url_remove_credentials($url));

View File

@@ -845,7 +845,7 @@ HTML;
* @param string $url Overridden URL. Will default to the entry URL.
* @throws Minz_Exception
*/
public function getContentByParsing(string $url = '', int $maxRedirs = 3): string {
public function getContentByParsing(string $url = '', int $maxRedirs = 4): string {
$url = $url ?: htmlspecialchars_decode($this->link(), ENT_QUOTES);
$feed = $this->feed();
if ($url === '' || $feed === null || $feed->pathEntries() === '') {
@@ -872,12 +872,16 @@ HTML;
}
$cachePath = $feed->cacheFilename($url . '#' . $feed->pathEntries());
$html = httpGet($url, $cachePath, 'html', $feed->attributes(), $feed->curlOptions());
if (strlen($html) > 0) {
$response = httpGet($url, $cachePath, 'html', $feed->attributes(), $feed->curlOptions());
$html = $response['body'];
if ($html !== '') {
$doc = new DOMDocument();
$doc->loadHTML($html, LIBXML_NONET | LIBXML_NOERROR | LIBXML_NOWARNING);
$xpath = new DOMXPath($doc);
// Account for HTTP redirections
$url = $response['effective_url'] ?: $url;
$maxRedirs -= $response['redirect_count'];
if ($maxRedirs > 0) {
//Follow any HTML redirection
$metas = $xpath->query('//meta[@content]') ?: [];

View File

@@ -788,7 +788,7 @@ class FreshRSS_Feed extends Minz_Model {
}
$httpAccept = $this->kind() === FreshRSS_Feed::KIND_HTML_XPATH_JSON_DOTNOTATION ? 'html' : 'json';
$content = httpGet($feedSourceUrl, $this->cacheFilename(), $httpAccept, $this->attributes(), $this->curlOptions());
$content = httpGet($feedSourceUrl, $this->cacheFilename(), $httpAccept, $this->attributes(), $this->curlOptions())['body'];
if (strlen($content) <= 0) {
return null;
}
@@ -846,7 +846,7 @@ class FreshRSS_Feed extends Minz_Model {
}
$httpAccept = $this->kind() === FreshRSS_Feed::KIND_XML_XPATH ? 'xml' : 'html';
$html = httpGet($feedSourceUrl, $this->cacheFilename(), $httpAccept, $this->attributes(), $this->curlOptions());
$html = httpGet($feedSourceUrl, $this->cacheFilename(), $httpAccept, $this->attributes(), $this->curlOptions())['body'];
if (strlen($html) <= 0) {
return null;
}

View File

@@ -507,12 +507,47 @@ function enforceHttpEncoding(string $html, string $contentType = ''): string {
return $html;
}
/**
* Set an HTML base URL to the HTML content if there is none.
* @param string $html the raw downloaded HTML content
* @param string $href the HTML base URL
* @return string an HTML string
*/
function enforceHtmlBase(string $html, string $href): string {
$doc = new DOMDocument();
$doc->loadHTML($html, LIBXML_NONET | LIBXML_NOERROR | LIBXML_NOWARNING);
if ($doc->documentElement === null) {
return '';
}
$xpath = new DOMXPath($doc);
$bases = $xpath->evaluate('//base');
if (!($bases instanceof DOMNodeList) || $bases->length === 0) {
$base = $doc->createElement('base');
if ($base === false) {
return $html;
}
$base->setAttribute('href', $href);
$head = null;
$heads = $xpath->evaluate('//head');
if ($heads instanceof DOMNodeList && $heads->length > 0) {
$head = $heads->item(0);
}
if ($head instanceof DOMElement) {
$head->insertBefore($base, $head->firstChild);
} else {
$doc->insertBefore($base, $doc->documentElement->firstChild);
}
}
return $doc->saveHTML() ?: $html;
}
/**
* @param string $type {html,json,opml,xml}
* @param array<string,mixed> $attributes
* @param array<int,mixed> $curl_options
* @return array{body:string,effective_url:string,redirect_count:int,fail:bool}
*/
function httpGet(string $url, string $cachePath, string $type = 'html', array $attributes = [], array $curl_options = []): string {
function httpGet(string $url, string $cachePath, string $type = 'html', array $attributes = [], array $curl_options = []): array {
$limits = FreshRSS_Context::systemConf()->limits;
$feed_timeout = empty($attributes['timeout']) || !is_numeric($attributes['timeout']) ? 0 : intval($attributes['timeout']);
@@ -521,7 +556,7 @@ function httpGet(string $url, string $cachePath, string $type = 'html', array $a
$body = @file_get_contents($cachePath);
if ($body != false) {
syslog(LOG_DEBUG, 'FreshRSS uses cache for ' . \SimplePie\Misc::url_remove_credentials($url));
return $body;
return ['body' => $body, 'effective_url' => $url, 'redirect_count' => 0, 'fail' => false];
}
}
@@ -553,7 +588,7 @@ function httpGet(string $url, string $cachePath, string $type = 'html', array $a
// TODO: Implement HTTP 1.1 conditional GET If-Modified-Since
$ch = curl_init();
if ($ch === false) {
return '';
return ['body' => '', 'effective_url' => '', 'redirect_count' => 0, 'fail' => true];
}
curl_setopt_array($ch, [
CURLOPT_URL => $url,
@@ -598,10 +633,13 @@ function httpGet(string $url, string $cachePath, string $type = 'html', array $a
$body = curl_exec($ch);
$c_status = curl_getinfo($ch, CURLINFO_HTTP_CODE);
$c_content_type = '' . curl_getinfo($ch, CURLINFO_CONTENT_TYPE);
$c_effective_url = curl_getinfo($ch, CURLINFO_EFFECTIVE_URL);
$c_redirect_count = curl_getinfo($ch, CURLINFO_REDIRECT_COUNT);
$c_error = curl_error($ch);
curl_close($ch);
if ($c_status != 200 || $c_error != '' || $body === false) {
$fail = $c_status != 200 || $c_error != '' || $body === false;
if ($fail) {
Minz_Log::warning('Error fetching content: HTTP code ' . $c_status . ': ' . $c_error . ' ' . $url);
$body = '';
// TODO: Implement HTTP 410 Gone
@@ -611,6 +649,7 @@ function httpGet(string $url, string $cachePath, string $type = 'html', array $a
$body = trim($body, " \n\r\t\v"); // Do not trim \x00 to avoid breaking a BOM
if ($type !== 'json') {
$body = enforceHttpEncoding($body, $c_content_type);
$body = enforceHtmlBase($body, $c_effective_url);
}
}
@@ -618,7 +657,7 @@ function httpGet(string $url, string $cachePath, string $type = 'html', array $a
Minz_Log::warning("Error saving cache $cachePath for $url");
}
return $body;
return ['body' => $body, 'effective_url' => $c_effective_url, 'redirect_count' => $c_redirect_count, 'fail' => $fail];
}
/**