mirror/php-rss-bridge
1
0
Fork 0
mirror of https://github.com/RSS-Bridge/rss-bridge.git synced 2025-08-22 08:03:52 +02:00
Code Issues Releases Wiki Activity

[bridges] Change to extend from FeedExpander

Browse Source
This commit is contained in:
logmanoriginal
2016-09-05 18:43:56 +02:00
parent 11be7ccb60
commit 179e73fb80
12 changed files with 262 additions and 437 deletions
Download Patch File Download Diff File Expand all files Collapse all files

178
bridges/FuturaSciencesBridge.php
View File

@@ -1,5 +1,5 @@
<?php
class FuturaSciencesBridge extends BridgeAbstract {
class FuturaSciencesBridge extends FeedExpander {
const MAINTAINER = 'ORelio';
const NAME = 'Futura-Sciences Bridge';
@@ -78,109 +78,89 @@ class FuturaSciencesBridge extends BridgeAbstract {
)
));
public function collectData(){
public function collectData(){
$url = self::URI . 'rss/' . $this->getInput('feed') . '.xml';
$this->collectExpandableDatas($url);
}
function StripCDATA($string) {
$string = str_replace('<![CDATA[', '', $string);
$string = str_replace(']]>', '', $string);
return $string;
}
protected function parseItem($newsItem){
$item = $this->parseRSS_2_0_Item($newsItem);
$item['uri'] = str_replace('#xtor=RSS-8', '', $item['uri']);
$article = $this->get_cached($item['uri'])
or $this->returnServerError('Could not request Futura-Sciences: ' . $item['uri']);
$item['content'] = $this->ExtractArticleContent($article);
$item['author'] = empty($this->ExtractAuthor($article)) ? $item['author'] : $this->ExtractAuthor($article);
return $item;
}
function StripWithDelimiters($string, $start, $end) {
while (strpos($string, $start) !== false) {
$section_to_remove = substr($string, strpos($string, $start));
$section_to_remove = substr($section_to_remove, 0, strpos($section_to_remove, $end) + strlen($end));
function StripWithDelimiters($string, $start, $end) {
while (strpos($string, $start) !== false) {
$section_to_remove = substr($string, strpos($string, $start));
$section_to_remove = substr($section_to_remove, 0, strpos($section_to_remove, $end) + strlen($end));
$string = str_replace($section_to_remove, '', $string);
} return $string;
}
function StripRecursiveHTMLSection($string, $tag_name, $tag_start) {
$open_tag = '<'.$tag_name;
$close_tag = '</'.$tag_name.'>';
$close_tag_length = strlen($close_tag);
if (strpos($tag_start, $open_tag) === 0) {
while (strpos($string, $tag_start) !== false) {
$max_recursion = 100;
$section_to_remove = null;
$section_start = strpos($string, $tag_start);
$search_offset = $section_start;
do {
$max_recursion--;
$section_end = strpos($string, $close_tag, $search_offset);
$search_offset = $section_end + $close_tag_length;
$section_to_remove = substr($string, $section_start, $section_end - $section_start + $close_tag_length);
$open_tag_count = substr_count($section_to_remove, $open_tag);
$close_tag_count = substr_count($section_to_remove, $close_tag);
} while ($open_tag_count > $close_tag_count && $max_recursion > 0);
$string = str_replace($section_to_remove, '', $string);
} return $string;
}
function StripRecursiveHTMLSection($string, $tag_name, $tag_start) {
$open_tag = '<'.$tag_name;
$close_tag = '</'.$tag_name.'>';
$close_tag_length = strlen($close_tag);
if (strpos($tag_start, $open_tag) === 0) {
while (strpos($string, $tag_start) !== false) {
$max_recursion = 100;
$section_to_remove = null;
$section_start = strpos($string, $tag_start);
$search_offset = $section_start;
do {
$max_recursion--;
$section_end = strpos($string, $close_tag, $search_offset);
$search_offset = $section_end + $close_tag_length;
$section_to_remove = substr($string, $section_start, $section_end - $section_start + $close_tag_length);
$open_tag_count = substr_count($section_to_remove, $open_tag);
$close_tag_count = substr_count($section_to_remove, $close_tag);
} while ($open_tag_count > $close_tag_count && $max_recursion > 0);
$string = str_replace($section_to_remove, '', $string);
}
}
return $string;
}
// Extracts the author from an article or element
function ExtractAuthor($article, $element){
$article_author = $article->find('span.author', 0);
if($article_author){
$authorname = trim(str_replace(', Futura-Sciences', '', $article_author->plaintext));
if(empty($authorname)){
$element_author = $element->find('author', 0);
if($element_author)
$authorname = StripCDATA($element_author->plaintext);
else
return '';
}
return $authorname;
}
return '';
}
$url = $this->getURI().'rss/'.$this->getInput('feed').'.xml';
$html = $this->getSimpleHTMLDOM($url)
or $this->returnServerError('Could not request Futura-Sciences: '.$url);
$limit = 0;
foreach($html->find('item') as $element) {
if ($limit < 10) {
$article_url = str_replace('#xtor=RSS-8', '', StripCDATA($element->find('guid', 0)->plaintext));
$article = $this->getSimpleHTMLDOM($article_url) or $this->returnServerError('Could not request Futura-Sciences: '.$article_url);
$contents = $article->find('div.content', 0)->innertext;
foreach (array(
'<div class="clear',
'<div class="sharebar2',
'<div class="diaporamafullscreen"',
'<div style="margin-bottom:10px;" class="noprint"',
'<div class="ficheprevnext',
'<div class="bar noprint',
'<div class="toolbar noprint',
'<div class="addthis_toolbox',
'<div class="noprint',
'<div class="bg bglight border border-full noprint',
'<div class="httplogbar-wrapper noprint',
'<div id="forumcomments'
) as $div_start) {
$contents = StripRecursiveHTMLSection($contents , 'div', $div_start);
}
$contents = StripWithDelimiters($contents, '<hr ', '/>');
$contents = StripWithDelimiters($contents, '<p class="content-date', '</p>');
$contents = StripWithDelimiters($contents, '<h1 class="content-title', '</h1>');
$contents = StripWithDelimiters($contents, 'fs:definition="', '"');
$contents = StripWithDelimiters($contents, 'fs:xt:clicktype="', '"');
$contents = StripWithDelimiters($contents, 'fs:xt:clickname="', '"');
$item = array();
$item['author'] = ExtractAuthor($article, $element);
$item['uri'] = $article_url;
$item['title'] = StripCDATA($element->find('title', 0)->innertext);
$item['timestamp'] = strtotime(StripCDATA($element->find('pubDate', 0)->plaintext));
$item['content'] = trim($contents);
$this->items[] = $item;
$limit++;
}
}
return $string;
}
function ExtractArticleContent($article){
$contents = $article->find('div.content', 0)->innertext;
foreach (array(
'<div class="clear',
'<div class="sharebar2',
'<div class="diaporamafullscreen"',
'<div style="margin-bottom:10px;" class="noprint"',
'<div class="ficheprevnext',
'<div class="bar noprint',
'<div class="toolbar noprint',
'<div class="addthis_toolbox',
'<div class="noprint',
'<div class="bg bglight border border-full noprint',
'<div class="httplogbar-wrapper noprint',
'<div id="forumcomments'
) as $div_start) {
$contents = $this->StripRecursiveHTMLSection($contents , 'div', $div_start);
}
$contents = $this->StripWithDelimiters($contents, '<hr ', '/>');
$contents = $this->StripWithDelimiters($contents, '<p class="content-date', '</p>');
$contents = $this->StripWithDelimiters($contents, '<h1 class="content-title', '</h1>');
$contents = $this->StripWithDelimiters($contents, 'fs:definition="', '"');
$contents = $this->StripWithDelimiters($contents, 'fs:xt:clicktype="', '"');
$contents = $this->StripWithDelimiters($contents, 'fs:xt:clickname="', '"');
return $contents;
}
// Extracts the author from an article or element
function ExtractAuthor($article){
$article_author = $article->find('span.author', 0);
if($article_author){
return trim(str_replace(', Futura-Sciences', '', $article_author->plaintext));
}
return '';
}
}