mirror of
https://github.com/YGGverse/YGGo.git
synced 2025-09-11 13:51:49 +00:00
fix multimedia snaps
This commit is contained in:
parent
6862fb35cd
commit
efbbf19601
@ -586,110 +586,6 @@ foreach ($db->getHostPageCrawlQueue(CRAWL_PAGE_LIMIT, time() - CRAWL_PAGE_SECOND
|
||||
continue;
|
||||
}
|
||||
|
||||
// Is HTML document
|
||||
if (false !== stripos(Filter::mime($contentType), 'text/html')) {
|
||||
|
||||
// Define variables
|
||||
$metaDescription = null;
|
||||
$metaKeywords = null;
|
||||
$metaYggoManifest = null;
|
||||
|
||||
// Parse page content
|
||||
$dom = new DomDocument();
|
||||
|
||||
if ($encoding = mb_detect_encoding($content)) {
|
||||
|
||||
@$dom->loadHTML(sprintf('<?xml encoding="%s" ?>', $encoding) . $content);
|
||||
|
||||
} else {
|
||||
|
||||
$hostPagesBanned += $db->updateHostPageTimeBanned($queueHostPage->hostPageId, time());
|
||||
|
||||
$db->commit();
|
||||
|
||||
continue;
|
||||
}
|
||||
|
||||
// Skip index page links without title tag
|
||||
$title = @$dom->getElementsByTagName('title');
|
||||
|
||||
if ($title->length == 0) {
|
||||
|
||||
$hostPagesBanned += $db->updateHostPageTimeBanned($queueHostPage->hostPageId, time());
|
||||
|
||||
$db->commit();
|
||||
|
||||
continue;
|
||||
|
||||
} else {
|
||||
|
||||
$metaTitle = $title->item(0)->nodeValue;
|
||||
}
|
||||
|
||||
// Get optional page meta data
|
||||
foreach (@$dom->getElementsByTagName('meta') as $meta) {
|
||||
|
||||
if (@$meta->getAttribute('name') == 'description') {
|
||||
$metaDescription = @$meta->getAttribute('content');
|
||||
}
|
||||
|
||||
if (@$meta->getAttribute('name') == 'keywords') {
|
||||
$metaKeywords = @$meta->getAttribute('content');
|
||||
}
|
||||
|
||||
if (@$meta->getAttribute('name') == 'robots') {
|
||||
|
||||
$metaRobots = @$meta->getAttribute('content');
|
||||
|
||||
// Ban page with meta robots:noindex attribute
|
||||
if (false !== stripos($metaRobots, 'noindex')) {
|
||||
|
||||
$hostPagesBanned += $db->updateHostPageTimeBanned($queueHostPage->hostPageId, time());
|
||||
|
||||
continue;
|
||||
}
|
||||
}
|
||||
|
||||
// Grab meta yggo:manifest link when available
|
||||
if (@$meta->getAttribute('name') == 'yggo:manifest') {
|
||||
$metaYggoManifest = Filter::url(@$meta->getAttribute('content'));
|
||||
}
|
||||
}
|
||||
|
||||
// Add queued page description if not exists
|
||||
$db->addHostPageDescription($queueHostPage->hostPageId,
|
||||
$metaTitle,
|
||||
$metaDescription ? Filter::pageDescription($metaDescription) : null,
|
||||
$metaKeywords ? Filter::pageKeywords($metaKeywords) : null,
|
||||
$content ? ($queueHostPage->crawlMetaOnly ? null : base64_encode($content)) : null,
|
||||
time());
|
||||
|
||||
// Collect page DOM elements data on enabled
|
||||
if (CRAWL_HOST_PAGE_DOM_SELECTORS) {
|
||||
|
||||
// Begin selectors extraction
|
||||
$html = str_get_html($content);
|
||||
|
||||
foreach ((array) explode(',', CRAWL_HOST_PAGE_DOM_SELECTORS) as $selector) {
|
||||
|
||||
foreach($html->find($selector) as $element) {
|
||||
|
||||
if (!empty($element->innertext)) {
|
||||
|
||||
$db->addHostPageDom($queueHostPage->hostPageId,
|
||||
time(),
|
||||
$selector,
|
||||
trim(CRAWL_HOST_PAGE_DOM_STRIP_TAGS ? strip_tags(
|
||||
preg_replace('/[\s]+/',
|
||||
' ',
|
||||
str_replace(['<br />', '<br/>', '<br>', '</'],
|
||||
[' ', ' ', ' ', ' </'],
|
||||
$element->innertext))) : $element->innertext));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Begin snaps
|
||||
if (SNAP_STORAGE) {
|
||||
|
||||
@ -820,6 +716,110 @@ foreach ($db->getHostPageCrawlQueue(CRAWL_PAGE_LIMIT, time() - CRAWL_PAGE_SECOND
|
||||
}
|
||||
}
|
||||
|
||||
// Is HTML document
|
||||
if (false !== stripos(Filter::mime($contentType), 'text/html')) {
|
||||
|
||||
// Define variables
|
||||
$metaDescription = null;
|
||||
$metaKeywords = null;
|
||||
$metaYggoManifest = null;
|
||||
|
||||
// Parse page content
|
||||
$dom = new DomDocument();
|
||||
|
||||
if ($encoding = mb_detect_encoding($content)) {
|
||||
|
||||
@$dom->loadHTML(sprintf('<?xml encoding="%s" ?>', $encoding) . $content);
|
||||
|
||||
} else {
|
||||
|
||||
$hostPagesBanned += $db->updateHostPageTimeBanned($queueHostPage->hostPageId, time());
|
||||
|
||||
$db->commit();
|
||||
|
||||
continue;
|
||||
}
|
||||
|
||||
// Skip index page links without title tag
|
||||
$title = @$dom->getElementsByTagName('title');
|
||||
|
||||
if ($title->length == 0) {
|
||||
|
||||
$hostPagesBanned += $db->updateHostPageTimeBanned($queueHostPage->hostPageId, time());
|
||||
|
||||
$db->commit();
|
||||
|
||||
continue;
|
||||
|
||||
} else {
|
||||
|
||||
$metaTitle = $title->item(0)->nodeValue;
|
||||
}
|
||||
|
||||
// Get optional page meta data
|
||||
foreach (@$dom->getElementsByTagName('meta') as $meta) {
|
||||
|
||||
if (@$meta->getAttribute('name') == 'description') {
|
||||
$metaDescription = @$meta->getAttribute('content');
|
||||
}
|
||||
|
||||
if (@$meta->getAttribute('name') == 'keywords') {
|
||||
$metaKeywords = @$meta->getAttribute('content');
|
||||
}
|
||||
|
||||
if (@$meta->getAttribute('name') == 'robots') {
|
||||
|
||||
$metaRobots = @$meta->getAttribute('content');
|
||||
|
||||
// Ban page with meta robots:noindex attribute
|
||||
if (false !== stripos($metaRobots, 'noindex')) {
|
||||
|
||||
$hostPagesBanned += $db->updateHostPageTimeBanned($queueHostPage->hostPageId, time());
|
||||
|
||||
continue;
|
||||
}
|
||||
}
|
||||
|
||||
// Grab meta yggo:manifest link when available
|
||||
if (@$meta->getAttribute('name') == 'yggo:manifest') {
|
||||
$metaYggoManifest = Filter::url(@$meta->getAttribute('content'));
|
||||
}
|
||||
}
|
||||
|
||||
// Add queued page description if not exists
|
||||
$db->addHostPageDescription($queueHostPage->hostPageId,
|
||||
$metaTitle,
|
||||
$metaDescription ? Filter::pageDescription($metaDescription) : null,
|
||||
$metaKeywords ? Filter::pageKeywords($metaKeywords) : null,
|
||||
$content ? ($queueHostPage->crawlMetaOnly ? null : base64_encode($content)) : null,
|
||||
time());
|
||||
|
||||
// Collect page DOM elements data on enabled
|
||||
if (CRAWL_HOST_PAGE_DOM_SELECTORS) {
|
||||
|
||||
// Begin selectors extraction
|
||||
$html = str_get_html($content);
|
||||
|
||||
foreach ((array) explode(',', CRAWL_HOST_PAGE_DOM_SELECTORS) as $selector) {
|
||||
|
||||
foreach($html->find($selector) as $element) {
|
||||
|
||||
if (!empty($element->innertext)) {
|
||||
|
||||
$db->addHostPageDom($queueHostPage->hostPageId,
|
||||
time(),
|
||||
$selector,
|
||||
trim(CRAWL_HOST_PAGE_DOM_STRIP_TAGS ? strip_tags(
|
||||
preg_replace('/[\s]+/',
|
||||
' ',
|
||||
str_replace(['<br />', '<br/>', '<br>', '</'],
|
||||
[' ', ' ', ' ', ' </'],
|
||||
$element->innertext))) : $element->innertext));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Skip page links following with meta robots:nofollow attribute
|
||||
foreach (@$dom->getElementsByTagName('meta') as $meta) {
|
||||
|
||||
|
Loading…
x
Reference in New Issue
Block a user