Relaxed readerable detection "algorithm" (like, a lot).

pull/127/head
Nicolas Perriault 9 years ago
parent 1fbed57832
commit b871c1e5e0

@ -1629,31 +1629,11 @@ Readability.prototype = {
* @return boolean Whether or not we suspect parse() will suceeed at returning an article object.
*/
isProbablyReaderable: function() {
var nodes = this._doc.getElementsByTagName("p");
if (nodes.length < 5) {
return false;
}
var possibleParagraphs = 0;
for (var i = 0; i < nodes.length; i++) {
var node = nodes[i];
var matchString = node.className + " " + node.id;
if (this.REGEXPS.unlikelyCandidates.test(matchString) &&
!this.REGEXPS.okMaybeItsACandidate.test(matchString)) {
continue;
}
if (node.textContent.trim().length < 100) {
continue;
}
possibleParagraphs++;
if (possibleParagraphs >= 5) {
return true;
}
}
return false;
return this._someNode(this._doc.body.getElementsByTagName("*"), function(node) {
return [1, 3].indexOf(node.nodeType) !== -1 &&
node.textContent.indexOf(",") !== -1 &&
node.textContent.trim().length > 100;
});
},
/**

@ -2,5 +2,5 @@
"title": "Base URL test",
"byline": null,
"excerpt": "Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod\n tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,\n quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo\n consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse\n cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non\n proident, sunt in culpa qui officia deserunt mollit anim id est laborum.",
"readerable": false
"readerable": true
}

@ -2,5 +2,5 @@
"title": "Embedded videos test",
"byline": null,
"excerpt": "Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod\n tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,\n quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo\n consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse\n cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non\n proident, sunt in culpa qui officia deserunt mollit anim id est laborum.",
"readerable": false
"readerable": true
}

@ -2,5 +2,5 @@
"title": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy\n eirmod tempor invidunt",
"byline": "Henri Sivonen",
"excerpt": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy\n eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam\n voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet\n clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit\n amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam\n nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat,\n sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum.\n Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor\n sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed\n diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat,\n sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum.\n Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor\n sit amet.",
"readerable": false
"readerable": true
}

@ -2,5 +2,5 @@
"title": "Normalize space test",
"byline": null,
"excerpt": "Lorem\n ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod\n\ttab here\n incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,\n quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo\n consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse\n cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non\n proident, sunt in culpa qui officia deserunt mollit anim id est laborum.",
"readerable": false
"readerable": true
}

@ -2,5 +2,5 @@
"title": "",
"byline": null,
"excerpt": "Regarding item# 11111, under sufficiently extreme conditions, quarks may\n become deconfined and exist as free particles. In the course of asymptotic\n freedom, the strong interaction becomes weaker at higher temperatures.\n Eventually, color confinement would be lost and an extremely hot plasma\n of freely moving quarks and gluons would be formed. This theoretical phase\n of matter is called quark-gluon plasma.[81] The exact conditions needed\n to give rise to this state are unknown and have been the subject of a great\n deal of speculation and experimentation.",
"readerable": false
"readerable": true
}

@ -2,5 +2,5 @@
"title": "Replace brs test",
"byline": null,
"excerpt": "Lorem ipsum",
"readerable": false
"readerable": true
}

@ -2,5 +2,5 @@
"title": "Replace font tags test",
"byline": null,
"excerpt": "Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod\n tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,\n quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo\n consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse\n cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non\n proident, sunt in culpa qui officia deserunt mollit anim id est laborum.",
"readerable": false
"readerable": true
}

@ -2,5 +2,5 @@
"title": "Style tags removal",
"byline": null,
"excerpt": "Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod\n tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,\n quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo\n consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse\n cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non\n proident, sunt in culpa qui officia deserunt mollit anim id est laborum.",
"readerable": false
"readerable": true
}

Loading…
Cancel
Save