Showing 2 changed files with 122 additions and 1 deletions
+119
sources/news-star.php
... ...
@@ -0,0 +1,119 @@
1
+<?php
2
+include_once( 'news-constants.php' );
3
+
4
+$rss_content = file_get_contents(NEWS_RSS_STAR);
5
+$orgStrings = array( 'media:content');
6
+$newStrings = array( 'mediacontent');
7
+$rss_content  = str_replace($orgStrings, $newStrings, $rss_content);
8
+$xml = simplexml_load_string($rss_content);
9
+if ($xml === false) {
10
+  echo 'Failed to read RSS';
11
+} else {
12
+  $channel = array();
13
+  $channel['title'] = $xml->channel->title;
14
+  $channel['link'] = $xml->channel->link;
15
+  $channel['description'] = $xml->channel->description;
16
+  $channel['pubDate'] = $xml->channel->pubDate;
17
+  $channel['timestamp'] = strtotime($xml->channel->pubDate);
18
+  echo '<h4>' . $channel['title'];
19
+  echo '<button id="html-btn" onclick="printHTMLAll(\''.$channel['title'].'\')" style="display:inline;"><img src="img/html5.png" width="24px" height="24px"></button>'.PHP_EOL;
20
+  echo '</h4>';
21
+  $cpt=0;
22
+  foreach ($xml->channel->item as $item) {
23
+    $article = array();
24
+    $article['title'] = $item->title;
25
+    $article['link'] = $item->link;
26
+    $SEARCHREF="?ref=rss";
27
+    //Remove reference from links
28
+    $posref=strpos($article['link'], $SEARCHREF);
29
+    if( $posref ) {
30
+      $article['link'] = substr($article['link'],0,$posref);
31
+    }
32
+    $article['pubDate'] = $item->pubDate;
33
+    $article['timestamp'] = strtotime($item->pubDate);
34
+    $article['description'] = $item->description;
35
+    $article['image'] = $item->mediacontent['url'];
36
+    $articles[$cpt] = $article;
37
+
38
+    echo '<div onclick="onArticle('.$cpt.')" style="display:inline;">'.PHP_EOL;
39
+    echo '<div class="img-menu"><img src="'.$article['image'].'" style="display:inline;" width="100%"></div><br>'.PHP_EOL;
40
+    echo '<div id="nav-up" style="display:inline;"><a href="#top"><i class="fa fa-home fa-2x"></i></a></div>&nbsp;&nbsp;'.PHP_EOL;
41
+    echo '<div id="nav-up" style="display:inline;"><a href="#article-top"><i class="fa fa-chevron-down fa-2x"></i></a></div>&nbsp;'.PHP_EOL;
42
+    echo $article['title'].'&nbsp;&nbsp;';
43
+    echo '<div id="nav-source" style="display:inline;"><a href="'.$article['link'].'" target="new-'.$cpt.'"><i class="fa fa-link fa-2x"></i></a><br></div></div>'.PHP_EOL;
44
+    $cpt++;
45
+    if( $cpt > $NEWS_RSS_MAX_ITEMS ) {
46
+      break;
47
+    }
48
+  }
49
+}
50
+
51
+echo '</div><!-- ./col-4 -->'.PHP_EOL;
52
+echo '<div id="article-display" class="col-6">'.PHP_EOL;
53
+echo '<a name="article-top"></a><div id="article-current"></div>'.PHP_EOL;
54
+echo '</div><!-- ./col-6 -->'.PHP_EOL;
55
+
56
+$cpt=0;
57
+foreach ($articles as $article ) {
58
+  $cpt_prev=$cpt-1;
59
+  $cpt_next=$cpt+1;
60
+  echo '<!-- ==================== article '.$cpt.'============== -->';
61
+  echo "<div class=\"article\" id=\"article-$cpt\" style=\"display: none;\">\n";
62
+  echo "<hr>";
63
+  echo "<a name=\"article-$cpt\">";
64
+  $article_content = file_get_contents($article['link']);
65
+  $doc = new DOMDocument();
66
+  $doc->preserveWhiteSpace = false;
67
+  $doc->formatOutput       = true;
68
+  $libxml_previous_state = libxml_use_internal_errors(true);
69
+  $doc->loadHTML($article_content);
70
+  libxml_clear_errors();
71
+  libxml_use_internal_errors($libxml_previous_state);
72
+
73
+  //Article is in <div class="article-body-items"
74
+  $articles = $doc->getElementsByTagName('div');
75
+  $article_only = "";
76
+  WARNING($cpt);
77
+  foreach ( $articles as $node) {
78
+    $classname = $node->getAttribute('class');
79
+    if($classname == 'article-body-items' ) {
80
+      $article_only = DOMinnerHTML($node);
81
+      break;
82
+    }
83
+  }
84
+  if( 0 == strlen($article_only)) {
85
+    $article_only = "Extraction failed";
86
+  }
87
+
88
+  $article_only = re_remove($article_only, '/<div class="side-box__button"><span><span><a href="\/emails\.html">SIGN UP<\/a><\/span><\/span><\/div>/');
89
+  $article_only = re_remove($article_only, '/<span class="subline-icon-color-headlines">NEW NEWSLETTER<\/span><span>HEADLINES<\/span>/');
90
+  $article_only = re_remove($article_only, '/<li class="report-error"><a><i class="staricon staricon-error-reporting "><\/i>Report an error<\/a><\/li>/');
91
+  $article_only = re_remove($article_only, '/<li class="about-the"><span><span><a href="\/about\/aboutus\.html"><i class="staricon staricon-trust-icon "><\/i>About <em>The Star<\/em><\/a><\/span><\/span><\/li>/');
92
+  $article_only = re_remove($article_only, '/<div class="banner-inner-content__left side-box__title title-color-headlines"><div class="about-text">TOP STORIES, DELIVERED TO YOUR INBOX.<\/div><\/div>/');
93
+  $article_only = re_remove($article_only, '/<li class="journalistic-standards"><span><span><a href="\/about\/statementofprinciples.html"><i class="staricon staricon-journalistic-standards "><\/i>Journalistic Standards<\/a><\/span><\/span><\/li>/');
94
+  $article_only = re_remove($article_only, '/<div class="article-continued"><div class="article-continued__heading">Article Continued Below<\/div><\/div>/');
95
+  $article_only = re_remove($article_only, '/<div class="alpha__big-box__body"><div class="big-box"><\/div><\/div>/');
96
+  //$article_only = re_remove($article_only, '//');
97
+  //$article_only = re_remove($article_only, '//');
98
+  $article_only = preg_replace("/(^[\r\n]*|[\r\n]+)[\s\t]*[\r\n]+/", "\n", $article_only);
99
+
100
+  echo '<div id="nav-up" style="display:inline;"><a href="#top"><i class="fa fa-home fa-2x"></i></a></div>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;'.PHP_EOL;
101
+  echo '<div id="nav-source" style="display:inline;"><a href="'.$article['link'].'" target="new-'.$cpt.'"><i class="fa fa-link fa-2x"></i></a></div>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;'.PHP_EOL;
102
+  echo '<button id="html-btn" onclick="printHTML()" style="display:inline;"><img src="img/html5.png" width="24px" height="24px"></button>'.PHP_EOL;
103
+  echo '<button id="pdf-btn" onclick="printPDF()" style="display:inline;"><img src="img/pdf.png" width="24px" height="24px"></button>'.PHP_EOL;
104
+  echo '<div id="nav-prev" onclick="onArticle('.$cpt_prev.')" style="display:inline;"><i class="fa fa-chevron-left fa-2x"></i></div>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;'.PHP_EOL;
105
+  echo '<div id="nav-next" onclick="onArticle('.$cpt_next.')" style="display:inline;"><i class="fa fa-chevron-right fa-2x"></i></div>'.PHP_EOL;
106
+  echo '<div class="extract-content" id="'.$cpt.'">'.'<h1>'.$article['title'].'</h1>'.$article_only.'</div>';
107
+  echo '<div id="nav-up" style="display:inline;"><a href="#top"><i class="fa fa-home fa-2x"></i></a></div>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;'.PHP_EOL;
108
+  echo '<div id="nav-up" style="display:inline;"><a href="#article-top"><i class="fa fa-chevron-up fa-2x"></i></a></div>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;'.PHP_EOL;
109
+  echo '<div id="nav-source" style="display:inline;"><a href="'.$article['link'].'" target="new-'.$cpt.'"><i class="fa fa-link fa-2x"></i></a></div>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;'.PHP_EOL;
110
+  echo '<div id="nav-prev" onclick="onArticle('.$cpt_prev.')" style="display:inline;"><i class="fa fa-chevron-left fa-2x"></i></div>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;'.PHP_EOL;
111
+  echo '<div id="nav-next" onclick="onArticle('.$cpt_next.')" style="display:inline;"><i class="fa fa-chevron-right fa-2x"></i></div></div>'.PHP_EOL;
112
+  $cpt++;
113
+  if( $cpt > $NEWS_RSS_MAX_ITEMS ) {
114
+      break;
115
+  }
116
+}
117
+?>
118
+
119
+
+3 -1
sources/rss.php
... ...
@@ -10,7 +10,7 @@ define('NEWS_RSS_SCMP', 'https://www.scmp.com/rss/91/feed');
10 10
 define('NEWS_RSS_STSG', 'https://www.straitstimes.com/news/singapore/rss.xml');
11 11
 define('NEWS_RSS_STASIA', 'https://www.straitstimes.com/news/asia/rss.xml');
12 12
 define('NEWS_RSS_STWORLD', 'https://www.straitstimes.com/news/world/rss.xml');
13
-//define('NEWS_RSS_STAR', '');
13
+define('NEWS_RSS_STAR', 'https://www.thestar.com/content/thestar/feed.RSSManagerServlet.articles.news.world.rss');
14 14
 
15 15
 $array_title=array(
16 16
   "nyt" => "New York Times",
... ...
@@ -20,6 +20,7 @@ $array_title=array(
20 20
   "aje" => "AlJazeera English",
21 21
   "smh" => "Sydney Morning Herald",
22 22
   "scmp" => "South China Morning Post",
23
+  "star" => "Toronto Star",
23 24
   "stsg" => "ST Singapore",
24 25
   "stasia" => "ST Asia",
25 26
   "stworld" => "ST World"
... ...
@@ -32,6 +33,7 @@ $array_url=array(
32 33
   "aje" => NEWS_RSS_AJE,
33 34
   "smh" => NEWS_RSS_SMH,
34 35
   "scmp" => NEWS_RSS_SCMP,
36
+  "star" => NEWS_RSS_STAR,
35 37
   "stsg" => NEWS_RSS_STSG,
36 38
   "stasia" => NEWS_RSS_STASIA,
37 39
   "stworld" => NEWS_RSS_STWORLD