commit 58b522be65516578b812f767c1f37042d4ff6c5b
parent 2ce28303518c42cd17096145beecc1c89110429f
Author: NunoSempere <nuno.sempere@protonmail.com>
Date: Fri, 15 Sep 2023 12:40:50 +0300
prettier pass.
Diffstat:
1 file changed, 730 insertions(+), 419 deletions(-)
diff --git a/plugins/readability/readability.js b/plugins/readability/readability.js
@@ -31,7 +31,9 @@ function Readability(doc, options) {
doc = options;
options = arguments[2];
} else if (!doc || !doc.documentElement) {
- throw new Error("First argument to Readability constructor should be a document object.");
+ throw new Error(
+ "First argument to Readability constructor should be a document object."
+ );
}
options = options || {};
@@ -45,41 +47,49 @@ function Readability(doc, options) {
// Configurable options
this._debug = !!options.debug;
- this._maxElemsToParse = options.maxElemsToParse || this.DEFAULT_MAX_ELEMS_TO_PARSE;
- this._nbTopCandidates = options.nbTopCandidates || this.DEFAULT_N_TOP_CANDIDATES;
+ this._maxElemsToParse =
+ options.maxElemsToParse || this.DEFAULT_MAX_ELEMS_TO_PARSE;
+ this._nbTopCandidates =
+ options.nbTopCandidates || this.DEFAULT_N_TOP_CANDIDATES;
this._charThreshold = options.charThreshold || this.DEFAULT_CHAR_THRESHOLD;
- this._classesToPreserve = this.CLASSES_TO_PRESERVE.concat(options.classesToPreserve || []);
+ this._classesToPreserve = this.CLASSES_TO_PRESERVE.concat(
+ options.classesToPreserve || []
+ );
this._keepClasses = !!options.keepClasses;
- this._serializer = options.serializer || function(el) {
- return el.innerHTML;
- };
+ this._serializer =
+ options.serializer ||
+ function (el) {
+ return el.innerHTML;
+ };
this._disableJSONLD = !!options.disableJSONLD;
// Start with all flags set
- this._flags = this.FLAG_STRIP_UNLIKELYS |
- this.FLAG_WEIGHT_CLASSES |
- this.FLAG_CLEAN_CONDITIONALLY;
-
+ this._flags =
+ this.FLAG_STRIP_UNLIKELYS |
+ this.FLAG_WEIGHT_CLASSES |
+ this.FLAG_CLEAN_CONDITIONALLY;
// Control whether log messages are sent to the console
if (this._debug) {
- let logNode = function(node) {
+ let logNode = function (node) {
if (node.nodeType == node.TEXT_NODE) {
return `${node.nodeName} ("${node.textContent}")`;
}
- let attrPairs = Array.from(node.attributes || [], function(attr) {
+ let attrPairs = Array.from(node.attributes || [], function (attr) {
return `${attr.name}="${attr.value}"`;
}).join(" ");
return `<${node.localName} ${attrPairs}>`;
};
this.log = function () {
if (typeof dump !== "undefined") {
- var msg = Array.prototype.map.call(arguments, function(x) {
- return (x && x.nodeName) ? logNode(x) : x;
- }).join(" ");
+ var msg = Array.prototype.map
+ .call(arguments, function (x) {
+ return x && x.nodeName ? logNode(x) : x;
+ })
+ .join(" ");
dump("Reader: (Readability) " + msg + "\n");
} else if (typeof console !== "undefined") {
- let args = Array.from(arguments, arg => {
+ let args = Array.from(arguments, (arg) => {
if (arg && arg.nodeType == this.ELEMENT_NODE) {
return logNode(arg);
}
@@ -111,7 +121,9 @@ Readability.prototype = {
DEFAULT_N_TOP_CANDIDATES: 5,
// Element tags to score by default.
- DEFAULT_TAGS_TO_SCORE: "section,h2,h3,h4,h5,h6,p,td,pre".toUpperCase().split(","),
+ DEFAULT_TAGS_TO_SCORE: "section,h2,h3,h4,h5,h6,p,td,pre"
+ .toUpperCase()
+ .split(","),
// The default number of chars an article must have in order to return a result
DEFAULT_CHAR_THRESHOLD: 500,
@@ -121,16 +133,21 @@ Readability.prototype = {
REGEXPS: {
// NOTE: These two regular expressions are duplicated in
// Readability-readerable.js. Please keep both copies in sync.
- unlikelyCandidates: /-ad-|ai2html|banner|breadcrumbs|combx|comment|community|cover-wrap|disqus|extra|footer|gdpr|header|legends|menu|related|remark|replies|rss|shoutbox|sidebar|skyscraper|social|sponsor|supplemental|ad-break|agegate|pagination|pager|popup|yom-remote/i,
+ unlikelyCandidates:
+ /-ad-|ai2html|banner|breadcrumbs|combx|comment|community|cover-wrap|disqus|extra|footer|gdpr|header|legends|menu|related|remark|replies|rss|shoutbox|sidebar|skyscraper|social|sponsor|supplemental|ad-break|agegate|pagination|pager|popup|yom-remote/i,
okMaybeItsACandidate: /and|article|body|column|content|main|shadow/i,
- positive: /article|body|content|entry|hentry|h-entry|main|page|pagination|post|text|blog|story/i,
- negative: /-ad-|hidden|^hid$| hid$| hid |^hid |banner|combx|comment|com-|contact|foot|footer|footnote|gdpr|masthead|media|meta|outbrain|promo|related|scroll|share|shoutbox|sidebar|skyscraper|sponsor|shopping|tags|tool|widget/i,
- extraneous: /print|archive|comment|discuss|e[\-]?mail|share|reply|all|login|sign|single|utility/i,
+ positive:
+ /article|body|content|entry|hentry|h-entry|main|page|pagination|post|text|blog|story/i,
+ negative:
+ /-ad-|hidden|^hid$| hid$| hid |^hid |banner|combx|comment|com-|contact|foot|footer|footnote|gdpr|masthead|media|meta|outbrain|promo|related|scroll|share|shoutbox|sidebar|skyscraper|sponsor|shopping|tags|tool|widget/i,
+ extraneous:
+ /print|archive|comment|discuss|e[\-]?mail|share|reply|all|login|sign|single|utility/i,
byline: /byline|author|dateline|writtenby|p-author/i,
replaceFonts: /<(\/?)font[^>]*>/gi,
normalize: /\s{2,}/g,
- videos: /\/\/(www\.)?((dailymotion|youtube|youtube-nocookie|player\.vimeo|v\.qq)\.com|(archive|upload\.wikimedia)\.org|player\.twitch\.tv)/i,
+ videos:
+ /\/\/(www\.)?((dailymotion|youtube|youtube-nocookie|player\.vimeo|v\.qq)\.com|(archive|upload\.wikimedia)\.org|player\.twitch\.tv)/i,
shareElements: /(\b|_)(share|sharedaddy)(\b|_)/i,
nextLink: /(next|weiter|continue|>([^\|]|$)|»([^\|]|$))/i,
prevLink: /(prev|earl|old|new|<|«)/i,
@@ -141,40 +158,106 @@ Readability.prototype = {
srcsetUrl: /(\S+)(\s+[\d.]+[xw])?(\s*(?:,|$))/g,
b64DataUrl: /^data:\s*([^\s;,]+)\s*;\s*base64\s*,/i,
// See: https://schema.org/Article
- jsonLdArticleTypes: /^Article|AdvertiserContentArticle|NewsArticle|AnalysisNewsArticle|AskPublicNewsArticle|BackgroundNewsArticle|OpinionNewsArticle|ReportageNewsArticle|ReviewNewsArticle|Report|SatiricalArticle|ScholarlyArticle|MedicalScholarlyArticle|SocialMediaPosting|BlogPosting|LiveBlogPosting|DiscussionForumPosting|TechArticle|APIReference$/
+ jsonLdArticleTypes:
+ /^Article|AdvertiserContentArticle|NewsArticle|AnalysisNewsArticle|AskPublicNewsArticle|BackgroundNewsArticle|OpinionNewsArticle|ReportageNewsArticle|ReviewNewsArticle|Report|SatiricalArticle|ScholarlyArticle|MedicalScholarlyArticle|SocialMediaPosting|BlogPosting|LiveBlogPosting|DiscussionForumPosting|TechArticle|APIReference$/,
},
- UNLIKELY_ROLES: [ "menu", "menubar", "complementary", "navigation", "alert", "alertdialog", "dialog" ],
+ UNLIKELY_ROLES: [
+ "menu",
+ "menubar",
+ "complementary",
+ "navigation",
+ "alert",
+ "alertdialog",
+ "dialog",
+ ],
- DIV_TO_P_ELEMS: new Set([ "BLOCKQUOTE", "DL", "DIV", "IMG", "OL", "P", "PRE", "TABLE", "UL" ]),
+ DIV_TO_P_ELEMS: new Set([
+ "BLOCKQUOTE",
+ "DL",
+ "DIV",
+ "IMG",
+ "OL",
+ "P",
+ "PRE",
+ "TABLE",
+ "UL",
+ ]),
ALTER_TO_DIV_EXCEPTIONS: ["DIV", "ARTICLE", "SECTION", "P"],
- PRESENTATIONAL_ATTRIBUTES: [ "align", "background", "bgcolor", "border", "cellpadding", "cellspacing", "frame", "hspace", "rules", "style", "valign", "vspace" ],
+ PRESENTATIONAL_ATTRIBUTES: [
+ "align",
+ "background",
+ "bgcolor",
+ "border",
+ "cellpadding",
+ "cellspacing",
+ "frame",
+ "hspace",
+ "rules",
+ "style",
+ "valign",
+ "vspace",
+ ],
- DEPRECATED_SIZE_ATTRIBUTE_ELEMS: [ "TABLE", "TH", "TD", "HR", "PRE" ],
+ DEPRECATED_SIZE_ATTRIBUTE_ELEMS: ["TABLE", "TH", "TD", "HR", "PRE"],
// The commented out elements qualify as phrasing content but tend to be
// removed by readability when put into paragraphs, so we ignore them here.
PHRASING_ELEMS: [
// "CANVAS", "IFRAME", "SVG", "VIDEO",
- "ABBR", "AUDIO", "B", "BDO", "BR", "BUTTON", "CITE", "CODE", "DATA",
- "DATALIST", "DFN", "EM", "EMBED", "I", "IMG", "INPUT", "KBD", "LABEL",
- "MARK", "MATH", "METER", "NOSCRIPT", "OBJECT", "OUTPUT", "PROGRESS", "Q",
- "RUBY", "SAMP", "SCRIPT", "SELECT", "SMALL", "SPAN", "STRONG", "SUB",
- "SUP", "TEXTAREA", "TIME", "VAR", "WBR"
+ "ABBR",
+ "AUDIO",
+ "B",
+ "BDO",
+ "BR",
+ "BUTTON",
+ "CITE",
+ "CODE",
+ "DATA",
+ "DATALIST",
+ "DFN",
+ "EM",
+ "EMBED",
+ "I",
+ "IMG",
+ "INPUT",
+ "KBD",
+ "LABEL",
+ "MARK",
+ "MATH",
+ "METER",
+ "NOSCRIPT",
+ "OBJECT",
+ "OUTPUT",
+ "PROGRESS",
+ "Q",
+ "RUBY",
+ "SAMP",
+ "SCRIPT",
+ "SELECT",
+ "SMALL",
+ "SPAN",
+ "STRONG",
+ "SUB",
+ "SUP",
+ "TEXTAREA",
+ "TIME",
+ "VAR",
+ "WBR",
],
// These are the classes that readability sets itself.
- CLASSES_TO_PRESERVE: [ "page" ],
+ CLASSES_TO_PRESERVE: ["page"],
// These are the list of HTML entities that need to be escaped.
HTML_ESCAPE_MAP: {
- "lt": "<",
- "gt": ">",
- "amp": "&",
- "quot": '"',
- "apos": "'",
+ lt: "<",
+ gt: ">",
+ amp: "&",
+ quot: '"',
+ apos: "'",
},
/**
@@ -182,8 +265,8 @@ Readability.prototype = {
*
* @param Element
* @return void
- **/
- _postProcessContent: function(articleContent) {
+ **/
+ _postProcessContent: function (articleContent) {
// Readability cannot open relative uris so we convert them to absolute uris.
this._fixRelativeUris(articleContent);
@@ -205,7 +288,7 @@ Readability.prototype = {
* @param Function filterFn the function to use as a filter
* @return void
*/
- _removeNodes: function(nodeList, filterFn) {
+ _removeNodes: function (nodeList, filterFn) {
// Avoid ever operating on live node lists.
if (this._docJSDOMParser && nodeList._isLiveNodeList) {
throw new Error("Do not pass live node lists to _removeNodes");
@@ -228,7 +311,7 @@ Readability.prototype = {
* @param String newTagName the new tag name to use
* @return void
*/
- _replaceNodeTags: function(nodeList, newTagName) {
+ _replaceNodeTags: function (nodeList, newTagName) {
// Avoid ever operating on live node lists.
if (this._docJSDOMParser && nodeList._isLiveNodeList) {
throw new Error("Do not pass live node lists to _replaceNodeTags");
@@ -249,7 +332,7 @@ Readability.prototype = {
* @param Function fn The iterate function.
* @return void
*/
- _forEachNode: function(nodeList, fn) {
+ _forEachNode: function (nodeList, fn) {
Array.prototype.forEach.call(nodeList, fn, this);
},
@@ -264,7 +347,7 @@ Readability.prototype = {
* @param Function fn The test function.
* @return void
*/
- _findNode: function(nodeList, fn) {
+ _findNode: function (nodeList, fn) {
return Array.prototype.find.call(nodeList, fn, this);
},
@@ -279,7 +362,7 @@ Readability.prototype = {
* @param Function fn The iterate function.
* @return Boolean
*/
- _someNode: function(nodeList, fn) {
+ _someNode: function (nodeList, fn) {
return Array.prototype.some.call(nodeList, fn, this);
},
@@ -294,7 +377,7 @@ Readability.prototype = {
* @param Function fn The iterate function.
* @return Boolean
*/
- _everyNode: function(nodeList, fn) {
+ _everyNode: function (nodeList, fn) {
return Array.prototype.every.call(nodeList, fn, this);
},
@@ -304,23 +387,26 @@ Readability.prototype = {
* @return ...NodeList
* @return Array
*/
- _concatNodeLists: function() {
+ _concatNodeLists: function () {
var slice = Array.prototype.slice;
var args = slice.call(arguments);
- var nodeLists = args.map(function(list) {
+ var nodeLists = args.map(function (list) {
return slice.call(list);
});
return Array.prototype.concat.apply([], nodeLists);
},
- _getAllNodesWithTag: function(node, tagNames) {
+ _getAllNodesWithTag: function (node, tagNames) {
if (node.querySelectorAll) {
return node.querySelectorAll(tagNames.join(","));
}
- return [].concat.apply([], tagNames.map(function(tag) {
- var collection = node.getElementsByTagName(tag);
- return Array.isArray(collection) ? collection : Array.from(collection);
- }));
+ return [].concat.apply(
+ [],
+ tagNames.map(function (tag) {
+ var collection = node.getElementsByTagName(tag);
+ return Array.isArray(collection) ? collection : Array.from(collection);
+ })
+ );
},
/**
@@ -331,11 +417,11 @@ Readability.prototype = {
* @param Element
* @return void
*/
- _cleanClasses: function(node) {
+ _cleanClasses: function (node) {
var classesToPreserve = this._classesToPreserve;
var className = (node.getAttribute("class") || "")
.split(/\s+/)
- .filter(function(cls) {
+ .filter(function (cls) {
return classesToPreserve.indexOf(cls) != -1;
})
.join(" ");
@@ -358,7 +444,7 @@ Readability.prototype = {
* @param Element
* @return void
*/
- _fixRelativeUris: function(articleContent) {
+ _fixRelativeUris: function (articleContent) {
var baseURI = this._doc.baseURI;
var documentURI = this._doc.documentURI;
function toAbsoluteURI(uri) {
@@ -377,14 +463,17 @@ Readability.prototype = {
}
var links = this._getAllNodesWithTag(articleContent, ["a"]);
- this._forEachNode(links, function(link) {
+ this._forEachNode(links, function (link) {
var href = link.getAttribute("href");
if (href) {
// Remove links with javascript: URIs, since
// they won't work after scripts have been removed from the page.
if (href.indexOf("javascript:") === 0) {
// if the link only contains simple text content, it can be converted to a text node
- if (link.childNodes.length === 1 && link.childNodes[0].nodeType === this.TEXT_NODE) {
+ if (
+ link.childNodes.length === 1 &&
+ link.childNodes[0].nodeType === this.TEXT_NODE
+ ) {
var text = this._doc.createTextNode(link.textContent);
link.parentNode.replaceChild(text, link);
} else {
@@ -402,10 +491,15 @@ Readability.prototype = {
});
var medias = this._getAllNodesWithTag(articleContent, [
- "img", "picture", "figure", "video", "audio", "source"
+ "img",
+ "picture",
+ "figure",
+ "video",
+ "audio",
+ "source",
]);
- this._forEachNode(medias, function(media) {
+ this._forEachNode(medias, function (media) {
var src = media.getAttribute("src");
var poster = media.getAttribute("poster");
var srcset = media.getAttribute("srcset");
@@ -419,27 +513,40 @@ Readability.prototype = {
}
if (srcset) {
- var newSrcset = srcset.replace(this.REGEXPS.srcsetUrl, function(_, p1, p2, p3) {
- return toAbsoluteURI(p1) + (p2 || "") + p3;
- });
+ var newSrcset = srcset.replace(
+ this.REGEXPS.srcsetUrl,
+ function (_, p1, p2, p3) {
+ return toAbsoluteURI(p1) + (p2 || "") + p3;
+ }
+ );
media.setAttribute("srcset", newSrcset);
}
});
},
- _simplifyNestedElements: function(articleContent) {
+ _simplifyNestedElements: function (articleContent) {
var node = articleContent;
while (node) {
- if (node.parentNode && ["DIV", "SECTION"].includes(node.tagName) && !(node.id && node.id.startsWith("readability"))) {
+ if (
+ node.parentNode &&
+ ["DIV", "SECTION"].includes(node.tagName) &&
+ !(node.id && node.id.startsWith("readability"))
+ ) {
if (this._isElementWithoutContent(node)) {
node = this._removeAndGetNext(node);
continue;
- } else if (this._hasSingleTagInsideElement(node, "DIV") || this._hasSingleTagInsideElement(node, "SECTION")) {
+ } else if (
+ this._hasSingleTagInsideElement(node, "DIV") ||
+ this._hasSingleTagInsideElement(node, "SECTION")
+ ) {
var child = node.children[0];
for (var i = 0; i < node.attributes.length; i++) {
- child.setAttribute(node.attributes[i].name, node.attributes[i].value);
+ child.setAttribute(
+ node.attributes[i].name,
+ node.attributes[i].value
+ );
}
node.parentNode.replaceChild(child, node);
node = child;
@@ -456,7 +563,7 @@ Readability.prototype = {
*
* @return string
**/
- _getArticleTitle: function() {
+ _getArticleTitle: function () {
var doc = this._doc;
var curTitle = "";
var origTitle = "";
@@ -466,8 +573,12 @@ Readability.prototype = {
// If they had an element with id "title" in their HTML
if (typeof curTitle !== "string")
- curTitle = origTitle = this._getInnerText(doc.getElementsByTagName("title")[0]);
- } catch (e) {/* ignore exceptions setting the title. */}
+ curTitle = origTitle = this._getInnerText(
+ doc.getElementsByTagName("title")[0]
+ );
+ } catch (e) {
+ /* ignore exceptions setting the title. */
+ }
var titleHadHierarchicalSeparators = false;
function wordCount(str) {
@@ -475,7 +586,7 @@ Readability.prototype = {
}
// If there's a separator in the title, first remove the final part
- if ((/ [\|\-\\\/>»] /).test(curTitle)) {
+ if (/ [\|\-\\\/>»] /.test(curTitle)) {
titleHadHierarchicalSeparators = / [\\\/>»] /.test(curTitle);
curTitle = origTitle.replace(/(.*)[\|\-\\\/>»] .*/gi, "$1");
@@ -491,7 +602,7 @@ Readability.prototype = {
doc.getElementsByTagName("h2")
);
var trimmedTitle = curTitle.trim();
- var match = this._someNode(headings, function(heading) {
+ var match = this._someNode(headings, function (heading) {
return heading.textContent.trim() === trimmedTitle;
});
@@ -511,8 +622,7 @@ Readability.prototype = {
} else if (curTitle.length > 150 || curTitle.length < 15) {
var hOnes = doc.getElementsByTagName("h1");
- if (hOnes.length === 1)
- curTitle = this._getInnerText(hOnes[0]);
+ if (hOnes.length === 1) curTitle = this._getInnerText(hOnes[0]);
}
curTitle = curTitle.trim().replace(this.REGEXPS.normalize, " ");
@@ -521,9 +631,12 @@ Readability.prototype = {
// title or we decreased the number of words by more than 1 word, use
// the original title.
var curTitleWordCount = wordCount(curTitle);
- if (curTitleWordCount <= 4 &&
- (!titleHadHierarchicalSeparators ||
- curTitleWordCount != wordCount(origTitle.replace(/[\|\-\\\/>»]+/g, "")) - 1)) {
+ if (
+ curTitleWordCount <= 4 &&
+ (!titleHadHierarchicalSeparators ||
+ curTitleWordCount !=
+ wordCount(origTitle.replace(/[\|\-\\\/>»]+/g, "")) - 1)
+ ) {
curTitle = origTitle;
}
@@ -536,7 +649,7 @@ Readability.prototype = {
*
* @return void
**/
- _prepDocument: function() {
+ _prepDocument: function () {
var doc = this._doc;
// Remove all style tags in head
@@ -556,9 +669,11 @@ Readability.prototype = {
*/
_nextNode: function (node) {
var next = node;
- while (next
- && (next.nodeType != this.ELEMENT_NODE)
- && this.REGEXPS.whitespace.test(next.textContent)) {
+ while (
+ next &&
+ next.nodeType != this.ELEMENT_NODE &&
+ this.REGEXPS.whitespace.test(next.textContent)
+ ) {
next = next.nextSibling;
}
return next;
@@ -572,7 +687,7 @@ Readability.prototype = {
* <div>foo<br>bar<p>abc</p></div>
*/
_replaceBrs: function (elem) {
- this._forEachNode(this._getAllNodesWithTag(elem, ["br"]), function(br) {
+ this._forEachNode(this._getAllNodesWithTag(elem, ["br"]), function (br) {
var next = br.nextSibling;
// Whether 2 or more <br> elements have been found and replaced with a
@@ -582,7 +697,7 @@ Readability.prototype = {
// If we find a <br> chain, remove the <br>s until we hit another node
// or non-whitespace. This leaves behind the first <br> in the chain
// (which will be replaced with a <p> later).
- while ((next = this._nextNode(next)) && (next.tagName == "BR")) {
+ while ((next = this._nextNode(next)) && next.tagName == "BR") {
replaced = true;
var brSibling = next.nextSibling;
next.parentNode.removeChild(next);
@@ -601,12 +716,10 @@ Readability.prototype = {
// If we've hit another <br><br>, we're done adding children to this <p>.
if (next.tagName == "BR") {
var nextElem = this._nextNode(next.nextSibling);
- if (nextElem && nextElem.tagName == "BR")
- break;
+ if (nextElem && nextElem.tagName == "BR") break;
}
- if (!this._isPhrasingContent(next))
- break;
+ if (!this._isPhrasingContent(next)) break;
// Otherwise, make this node a child of the new <p>.
var sibling = next.nextSibling;
@@ -618,8 +731,7 @@ Readability.prototype = {
p.removeChild(p.lastChild);
}
- if (p.parentNode.tagName === "P")
- this._setNodeTag(p.parentNode, "DIV");
+ if (p.parentNode.tagName === "P") this._setNodeTag(p.parentNode, "DIV");
}
});
},
@@ -637,12 +749,14 @@ Readability.prototype = {
replacement.appendChild(node.firstChild);
}
node.parentNode.replaceChild(replacement, node);
- if (node.readability)
- replacement.readability = node.readability;
+ if (node.readability) replacement.readability = node.readability;
for (var i = 0; i < node.attributes.length; i++) {
try {
- replacement.setAttribute(node.attributes[i].name, node.attributes[i].value);
+ replacement.setAttribute(
+ node.attributes[i].name,
+ node.attributes[i].value
+ );
} catch (ex) {
/* it's possible for setAttribute() to throw if the attribute name
* isn't a valid XML Name. Such attributes can however be parsed from
@@ -662,7 +776,7 @@ Readability.prototype = {
* @param Element
* @return void
**/
- _prepArticle: function(articleContent) {
+ _prepArticle: function (articleContent) {
this._cleanStyles(articleContent);
// Check for data tables before we continue, to avoid removing items in
@@ -688,7 +802,10 @@ Readability.prototype = {
this._forEachNode(articleContent.children, function (topCandidate) {
this._cleanMatchedNodes(topCandidate, function (node, matchString) {
- return this.REGEXPS.shareElements.test(matchString) && node.textContent.length < shareElementThreshold;
+ return (
+ this.REGEXPS.shareElements.test(matchString) &&
+ node.textContent.length < shareElementThreshold
+ );
});
});
@@ -706,38 +823,56 @@ Readability.prototype = {
this._cleanConditionally(articleContent, "div");
// replace H1 with H2 as H1 should be only title that is displayed separately
- this._replaceNodeTags(this._getAllNodesWithTag(articleContent, ["h1"]), "h2");
+ this._replaceNodeTags(
+ this._getAllNodesWithTag(articleContent, ["h1"]),
+ "h2"
+ );
// Remove extra paragraphs
- this._removeNodes(this._getAllNodesWithTag(articleContent, ["p"]), function (paragraph) {
- var imgCount = paragraph.getElementsByTagName("img").length;
- var embedCount = paragraph.getElementsByTagName("embed").length;
- var objectCount = paragraph.getElementsByTagName("object").length;
- // At this point, nasty iframes have been removed, only remain embedded video ones.
- var iframeCount = paragraph.getElementsByTagName("iframe").length;
- var totalCount = imgCount + embedCount + objectCount + iframeCount;
-
- return totalCount === 0 && !this._getInnerText(paragraph, false);
- });
+ this._removeNodes(
+ this._getAllNodesWithTag(articleContent, ["p"]),
+ function (paragraph) {
+ var imgCount = paragraph.getElementsByTagName("img").length;
+ var embedCount = paragraph.getElementsByTagName("embed").length;
+ var objectCount = paragraph.getElementsByTagName("object").length;
+ // At this point, nasty iframes have been removed, only remain embedded video ones.
+ var iframeCount = paragraph.getElementsByTagName("iframe").length;
+ var totalCount = imgCount + embedCount + objectCount + iframeCount;
+
+ return totalCount === 0 && !this._getInnerText(paragraph, false);
+ }
+ );
- this._forEachNode(this._getAllNodesWithTag(articleContent, ["br"]), function(br) {
- var next = this._nextNode(br.nextSibling);
- if (next && next.tagName == "P")
- br.parentNode.removeChild(br);
- });
+ this._forEachNode(
+ this._getAllNodesWithTag(articleContent, ["br"]),
+ function (br) {
+ var next = this._nextNode(br.nextSibling);
+ if (next && next.tagName == "P") br.parentNode.removeChild(br);
+ }
+ );
// Remove single-cell tables
- this._forEachNode(this._getAllNodesWithTag(articleContent, ["table"]), function(table) {
- var tbody = this._hasSingleTagInsideElement(table, "TBODY") ? table.firstElementChild : table;
- if (this._hasSingleTagInsideElement(tbody, "TR")) {
- var row = tbody.firstElementChild;
- if (this._hasSingleTagInsideElement(row, "TD")) {
- var cell = row.firstElementChild;
- cell = this._setNodeTag(cell, this._everyNode(cell.childNodes, this._isPhrasingContent) ? "P" : "DIV");
- table.parentNode.replaceChild(cell, table);
+ this._forEachNode(
+ this._getAllNodesWithTag(articleContent, ["table"]),
+ function (table) {
+ var tbody = this._hasSingleTagInsideElement(table, "TBODY")
+ ? table.firstElementChild
+ : table;
+ if (this._hasSingleTagInsideElement(tbody, "TR")) {
+ var row = tbody.firstElementChild;
+ if (this._hasSingleTagInsideElement(row, "TD")) {
+ var cell = row.firstElementChild;
+ cell = this._setNodeTag(
+ cell,
+ this._everyNode(cell.childNodes, this._isPhrasingContent)
+ ? "P"
+ : "DIV"
+ );
+ table.parentNode.replaceChild(cell, table);
+ }
}
}
- });
+ );
},
/**
@@ -746,9 +881,9 @@ Readability.prototype = {
*
* @param Element
* @return void
- **/
- _initializeNode: function(node) {
- node.readability = {"contentScore": 0};
+ **/
+ _initializeNode: function (node) {
+ node.readability = { contentScore: 0 };
switch (node.tagName) {
case "DIV":
@@ -786,7 +921,7 @@ Readability.prototype = {
node.readability.contentScore += this._getClassWeight(node);
},
- _removeAndGetNext: function(node) {
+ _removeAndGetNext: function (node) {
var nextNode = this._getNextNode(node, true);
node.parentNode.removeChild(node);
return nextNode;
@@ -799,7 +934,7 @@ Readability.prototype = {
*
* Calling this in a loop will traverse the DOM depth-first.
*/
- _getNextNode: function(node, ignoreSelfAndKids) {
+ _getNextNode: function (node, ignoreSelfAndKids) {
// First check for kids if those aren't being ignored
if (!ignoreSelfAndKids && node.firstElementChild) {
return node.firstElementChild;
@@ -821,18 +956,24 @@ Readability.prototype = {
// 1 = same text, 0 = completely different text
// works the way that it splits both texts into words and then finds words that are unique in second text
// the result is given by the lower length of unique parts
- _textSimilarity: function(textA, textB) {
- var tokensA = textA.toLowerCase().split(this.REGEXPS.tokenize).filter(Boolean);
- var tokensB = textB.toLowerCase().split(this.REGEXPS.tokenize).filter(Boolean);
+ _textSimilarity: function (textA, textB) {
+ var tokensA = textA
+ .toLowerCase()
+ .split(this.REGEXPS.tokenize)
+ .filter(Boolean);
+ var tokensB = textB
+ .toLowerCase()
+ .split(this.REGEXPS.tokenize)
+ .filter(Boolean);
if (!tokensA.length || !tokensB.length) {
return 0;
}
- var uniqTokensB = tokensB.filter(token => !tokensA.includes(token));
+ var uniqTokensB = tokensB.filter((token) => !tokensA.includes(token));
var distanceB = uniqTokensB.join(" ").length / tokensB.join(" ").length;
return 1 - distanceB;
},
- _checkByline: function(node, matchString) {
+ _checkByline: function (node, matchString) {
if (this._articleByline) {
return false;
}
@@ -842,7 +983,12 @@ Readability.prototype = {
var itemprop = node.getAttribute("itemprop");
}
- if ((rel === "author" || (itemprop && itemprop.indexOf("author") !== -1) || this.REGEXPS.byline.test(matchString)) && this._isValidByline(node.textContent)) {
+ if (
+ (rel === "author" ||
+ (itemprop && itemprop.indexOf("author") !== -1) ||
+ this.REGEXPS.byline.test(matchString)) &&
+ this._isValidByline(node.textContent)
+ ) {
this._articleByline = node.textContent.trim();
return true;
}
@@ -850,13 +996,13 @@ Readability.prototype = {
return false;
},
- _getNodeAncestors: function(node, maxDepth) {
+ _getNodeAncestors: function (node, maxDepth) {
maxDepth = maxDepth || 0;
- var i = 0, ancestors = [];
+ var i = 0,
+ ancestors = [];
while (node.parentNode) {
ancestors.push(node.parentNode);
- if (maxDepth && ++i === maxDepth)
- break;
+ if (maxDepth && ++i === maxDepth) break;
node = node.parentNode;
}
return ancestors;
@@ -868,7 +1014,7 @@ Readability.prototype = {
*
* @param page a document to run upon. Needs to be a full document, complete with body.
* @return Element
- **/
+ **/
_grabArticle: function (page) {
this.log("**** grabArticle ****");
var doc = this._doc;
@@ -885,7 +1031,9 @@ Readability.prototype = {
while (true) {
this.log("Starting grabArticle loop");
- var stripUnlikelyCandidates = this._flagIsActive(this.FLAG_STRIP_UNLIKELYS);
+ var stripUnlikelyCandidates = this._flagIsActive(
+ this.FLAG_STRIP_UNLIKELYS
+ );
// First, node prepping. Trash nodes that look cruddy (like ones with the
// class name "comment", etc), and turn divs into P tags where they have been
@@ -896,7 +1044,6 @@ Readability.prototype = {
let shouldRemoveTitleHeader = true;
while (node) {
-
if (node.tagName === "HTML") {
this._articleLang = node.getAttribute("lang");
}
@@ -916,7 +1063,11 @@ Readability.prototype = {
}
if (shouldRemoveTitleHeader && this._headerDuplicatesTitle(node)) {
- this.log("Removing header: ", node.textContent.trim(), this._articleTitle.trim());
+ this.log(
+ "Removing header: ",
+ node.textContent.trim(),
+ this._articleTitle.trim()
+ );
shouldRemoveTitleHeader = false;
node = this._removeAndGetNext(node);
continue;
@@ -924,29 +1075,44 @@ Readability.prototype = {
// Remove unlikely candidates
if (stripUnlikelyCandidates) {
- if (this.REGEXPS.unlikelyCandidates.test(matchString) &&
- !this.REGEXPS.okMaybeItsACandidate.test(matchString) &&
- !this._hasAncestorTag(node, "table") &&
- !this._hasAncestorTag(node, "code") &&
- node.tagName !== "BODY" &&
- node.tagName !== "A") {
+ if (
+ this.REGEXPS.unlikelyCandidates.test(matchString) &&
+ !this.REGEXPS.okMaybeItsACandidate.test(matchString) &&
+ !this._hasAncestorTag(node, "table") &&
+ !this._hasAncestorTag(node, "code") &&
+ node.tagName !== "BODY" &&
+ node.tagName !== "A"
+ ) {
this.log("Removing unlikely candidate - " + matchString);
node = this._removeAndGetNext(node);
continue;
}
if (this.UNLIKELY_ROLES.includes(node.getAttribute("role"))) {
- this.log("Removing content with role " + node.getAttribute("role") + " - " + matchString);
+ this.log(
+ "Removing content with role " +
+ node.getAttribute("role") +
+ " - " +
+ matchString
+ );
node = this._removeAndGetNext(node);
continue;
}
}
// Remove DIV, SECTION, and HEADER nodes without any content(e.g. text, image, video, or iframe).
- if ((node.tagName === "DIV" || node.tagName === "SECTION" || node.tagName === "HEADER" ||
- node.tagName === "H1" || node.tagName === "H2" || node.tagName === "H3" ||
- node.tagName === "H4" || node.tagName === "H5" || node.tagName === "H6") &&
- this._isElementWithoutContent(node)) {
+ if (
+ (node.tagName === "DIV" ||
+ node.tagName === "SECTION" ||
+ node.tagName === "HEADER" ||
+ node.tagName === "H1" ||
+ node.tagName === "H2" ||
+ node.tagName === "H3" ||
+ node.tagName === "H4" ||
+ node.tagName === "H5" ||
+ node.tagName === "H6") &&
+ this._isElementWithoutContent(node)
+ ) {
node = this._removeAndGetNext(node);
continue;
}
@@ -983,7 +1149,10 @@ Readability.prototype = {
// element. DIVs with only a P element inside and no text content can be
// safely converted into plain P elements to avoid confusing the scoring
// algorithm with DIVs with are, in practice, paragraphs.
- if (this._hasSingleTagInsideElement(node, "P") && this._getLinkDensity(node) < 0.25) {
+ if (
+ this._hasSingleTagInsideElement(node, "P") &&
+ this._getLinkDensity(node) < 0.25
+ ) {
var newNode = node.children[0];
node.parentNode.replaceChild(newNode, node);
node = newNode;
@@ -1001,21 +1170,22 @@ Readability.prototype = {
* Then add their score to their parent node.
*
* A score is determined by things like number of commas, class names, etc. Maybe eventually link density.
- **/
+ **/
var candidates = [];
- this._forEachNode(elementsToScore, function(elementToScore) {
- if (!elementToScore.parentNode || typeof(elementToScore.parentNode.tagName) === "undefined")
+ this._forEachNode(elementsToScore, function (elementToScore) {
+ if (
+ !elementToScore.parentNode ||
+ typeof elementToScore.parentNode.tagName === "undefined"
+ )
return;
// If this paragraph is less than 25 characters, don't even count it.
var innerText = this._getInnerText(elementToScore);
- if (innerText.length < 25)
- return;
+ if (innerText.length < 25) return;
// Exclude nodes with no ancestor.
var ancestors = this._getNodeAncestors(elementToScore, 5);
- if (ancestors.length === 0)
- return;
+ if (ancestors.length === 0) return;
var contentScore = 0;
@@ -1029,11 +1199,15 @@ Readability.prototype = {
contentScore += Math.min(Math.floor(innerText.length / 100), 3);
// Initialize and score ancestors.
- this._forEachNode(ancestors, function(ancestor, level) {
- if (!ancestor.tagName || !ancestor.parentNode || typeof(ancestor.parentNode.tagName) === "undefined")
+ this._forEachNode(ancestors, function (ancestor, level) {
+ if (
+ !ancestor.tagName ||
+ !ancestor.parentNode ||
+ typeof ancestor.parentNode.tagName === "undefined"
+ )
return;
- if (typeof(ancestor.readability) === "undefined") {
+ if (typeof ancestor.readability === "undefined") {
this._initializeNode(ancestor);
candidates.push(ancestor);
}
@@ -1042,12 +1216,9 @@ Readability.prototype = {
// - parent: 1 (no division)
// - grandparent: 2
// - great grandparent+: ancestor level * 3
- if (level === 0)
- var scoreDivider = 1;
- else if (level === 1)
- scoreDivider = 2;
- else
- scoreDivider = level * 3;
+ if (level === 0) var scoreDivider = 1;
+ else if (level === 1) scoreDivider = 2;
+ else scoreDivider = level * 3;
ancestor.readability.contentScore += contentScore / scoreDivider;
});
});
@@ -1061,7 +1232,9 @@ Readability.prototype = {
// Scale the final candidates score based on link density. Good content
// should have a relatively small link density (5% or less) and be mostly
// unaffected by this operation.
- var candidateScore = candidate.readability.contentScore * (1 - this._getLinkDensity(candidate));
+ var candidateScore =
+ candidate.readability.contentScore *
+ (1 - this._getLinkDensity(candidate));
candidate.readability.contentScore = candidateScore;
this.log("Candidate:", candidate, "with score " + candidateScore);
@@ -1069,7 +1242,10 @@ Readability.prototype = {
for (var t = 0; t < this._nbTopCandidates; t++) {
var aTopCandidate = topCandidates[t];
- if (!aTopCandidate || candidateScore > aTopCandidate.readability.contentScore) {
+ if (
+ !aTopCandidate ||
+ candidateScore > aTopCandidate.readability.contentScore
+ ) {
topCandidates.splice(t, 0, candidate);
if (topCandidates.length > this._nbTopCandidates)
topCandidates.pop();
@@ -1103,8 +1279,14 @@ Readability.prototype = {
// and whose scores are quite closed with current `topCandidate` node.
var alternativeCandidateAncestors = [];
for (var i = 1; i < topCandidates.length; i++) {
- if (topCandidates[i].readability.contentScore / topCandidate.readability.contentScore >= 0.75) {
- alternativeCandidateAncestors.push(this._getNodeAncestors(topCandidates[i]));
+ if (
+ topCandidates[i].readability.contentScore /
+ topCandidate.readability.contentScore >=
+ 0.75
+ ) {
+ alternativeCandidateAncestors.push(
+ this._getNodeAncestors(topCandidates[i])
+ );
}
}
var MINIMUM_TOPCANDIDATES = 3;
@@ -1112,8 +1294,17 @@ Readability.prototype = {
parentOfTopCandidate = topCandidate.parentNode;
while (parentOfTopCandidate.tagName !== "BODY") {
var listsContainingThisAncestor = 0;
- for (var ancestorIndex = 0; ancestorIndex < alternativeCandidateAncestors.length && listsContainingThisAncestor < MINIMUM_TOPCANDIDATES; ancestorIndex++) {
- listsContainingThisAncestor += Number(alternativeCandidateAncestors[ancestorIndex].includes(parentOfTopCandidate));
+ for (
+ var ancestorIndex = 0;
+ ancestorIndex < alternativeCandidateAncestors.length &&
+ listsContainingThisAncestor < MINIMUM_TOPCANDIDATES;
+ ancestorIndex++
+ ) {
+ listsContainingThisAncestor += Number(
+ alternativeCandidateAncestors[ancestorIndex].includes(
+ parentOfTopCandidate
+ )
+ );
}
if (listsContainingThisAncestor >= MINIMUM_TOPCANDIDATES) {
topCandidate = parentOfTopCandidate;
@@ -1143,8 +1334,7 @@ Readability.prototype = {
continue;
}
var parentScore = parentOfTopCandidate.readability.contentScore;
- if (parentScore < scoreThreshold)
- break;
+ if (parentScore < scoreThreshold) break;
if (parentScore > lastScore) {
// Alright! We found a better parent to use.
topCandidate = parentOfTopCandidate;
@@ -1157,7 +1347,10 @@ Readability.prototype = {
// If the top candidate is the only child, use parent instead. This will help sibling
// joining logic when adjacent content is actually located in parent's sibling node.
parentOfTopCandidate = topCandidate.parentNode;
- while (parentOfTopCandidate.tagName != "BODY" && parentOfTopCandidate.children.length == 1) {
+ while (
+ parentOfTopCandidate.tagName != "BODY" &&
+ parentOfTopCandidate.children.length == 1
+ ) {
topCandidate = parentOfTopCandidate;
parentOfTopCandidate = topCandidate.parentNode;
}
@@ -1170,10 +1363,12 @@ Readability.prototype = {
// that might also be related. Things like preambles, content split by ads
// that we removed, etc.
var articleContent = doc.createElement("DIV");
- if (isPaging)
- articleContent.id = "readability-content";
+ if (isPaging) articleContent.id = "readability-content";
- var siblingScoreThreshold = Math.max(10, topCandidate.readability.contentScore * 0.2);
+ var siblingScoreThreshold = Math.max(
+ 10,
+ topCandidate.readability.contentScore * 0.2
+ );
// Keep potential top candidate's parent node to try to get text direction of it later.
parentOfTopCandidate = topCandidate.parentNode;
var siblings = parentOfTopCandidate.children;
@@ -1182,8 +1377,17 @@ Readability.prototype = {
var sibling = siblings[s];
var append = false;
- this.log("Looking at sibling node:", sibling, sibling.readability ? ("with score " + sibling.readability.contentScore) : "");
- this.log("Sibling has score", sibling.readability ? sibling.readability.contentScore : "Unknown");
+ this.log(
+ "Looking at sibling node:",
+ sibling,
+ sibling.readability
+ ? "with score " + sibling.readability.contentScore
+ : ""
+ );
+ this.log(
+ "Sibling has score",
+ sibling.readability ? sibling.readability.contentScore : "Unknown"
+ );
if (sibling === topCandidate) {
append = true;
@@ -1191,11 +1395,17 @@ Readability.prototype = {
var contentBonus = 0;
// Give a bonus if sibling nodes and top candidates have the example same classname
- if (sibling.className === topCandidate.className && topCandidate.className !== "")
+ if (
+ sibling.className === topCandidate.className &&
+ topCandidate.className !== ""
+ )
contentBonus += topCandidate.readability.contentScore * 0.2;
- if (sibling.readability &&
- ((sibling.readability.contentScore + contentBonus) >= siblingScoreThreshold)) {
+ if (
+ sibling.readability &&
+ sibling.readability.contentScore + contentBonus >=
+ siblingScoreThreshold
+ ) {
append = true;
} else if (sibling.nodeName === "P") {
var linkDensity = this._getLinkDensity(sibling);
@@ -1204,8 +1414,12 @@ Readability.prototype = {
if (nodeLength > 80 && linkDensity < 0.25) {
append = true;
- } else if (nodeLength < 80 && nodeLength > 0 && linkDensity === 0 &&
- nodeContent.search(/\.( |$)/) !== -1) {
+ } else if (
+ nodeLength < 80 &&
+ nodeLength > 0 &&
+ linkDensity === 0 &&
+ nodeContent.search(/\.( |$)/) !== -1
+ ) {
append = true;
}
}
@@ -1276,15 +1490,27 @@ Readability.prototype = {
if (this._flagIsActive(this.FLAG_STRIP_UNLIKELYS)) {
this._removeFlag(this.FLAG_STRIP_UNLIKELYS);
- this._attempts.push({articleContent: articleContent, textLength: textLength});
+ this._attempts.push({
+ articleContent: articleContent,
+ textLength: textLength,
+ });
} else if (this._flagIsActive(this.FLAG_WEIGHT_CLASSES)) {
this._removeFlag(this.FLAG_WEIGHT_CLASSES);
- this._attempts.push({articleContent: articleContent, textLength: textLength});
+ this._attempts.push({
+ articleContent: articleContent,
+ textLength: textLength,
+ });
} else if (this._flagIsActive(this.FLAG_CLEAN_CONDITIONALLY)) {
this._removeFlag(this.FLAG_CLEAN_CONDITIONALLY);
- this._attempts.push({articleContent: articleContent, textLength: textLength});
+ this._attempts.push({
+ articleContent: articleContent,
+ textLength: textLength,
+ });
} else {
- this._attempts.push({articleContent: articleContent, textLength: textLength});
+ this._attempts.push({
+ articleContent: articleContent,
+ textLength: textLength,
+ });
// No luck after removing flags, just return the longest text we found during the different loops
this._attempts.sort(function (a, b) {
return b.textLength - a.textLength;
@@ -1302,10 +1528,11 @@ Readability.prototype = {
if (parseSuccessful) {
// Find out text direction from ancestors of final top candidate.
- var ancestors = [parentOfTopCandidate, topCandidate].concat(this._getNodeAncestors(parentOfTopCandidate));
- this._someNode(ancestors, function(ancestor) {
- if (!ancestor.tagName)
- return false;
+ var ancestors = [parentOfTopCandidate, topCandidate].concat(
+ this._getNodeAncestors(parentOfTopCandidate)
+ );
+ this._someNode(ancestors, function (ancestor) {
+ if (!ancestor.tagName) return false;
var articleDir = ancestor.getAttribute("dir");
if (articleDir) {
this._articleDir = articleDir;
@@ -1326,10 +1553,10 @@ Readability.prototype = {
* @param possibleByline {string} - a string to check whether its a byline.
* @return Boolean - whether the input string is a byline.
*/
- _isValidByline: function(byline) {
+ _isValidByline: function (byline) {
if (typeof byline == "string" || byline instanceof String) {
byline = byline.trim();
- return (byline.length > 0) && (byline.length < 100);
+ return byline.length > 0 && byline.length < 100;
}
return false;
},
@@ -1340,18 +1567,23 @@ Readability.prototype = {
* @param str {string} - a string to unescape.
* @return string without HTML entity.
*/
- _unescapeHtmlEntities: function(str) {
+ _unescapeHtmlEntities: function (str) {
if (!str) {
return str;
}
var htmlEscapeMap = this.HTML_ESCAPE_MAP;
- return str.replace(/&(quot|amp|apos|lt|gt);/g, function(_, tag) {
- return htmlEscapeMap[tag];
- }).replace(/&#(?:x([0-9a-z]{1,4})|([0-9]{1,4}));/gi, function(_, hex, numStr) {
- var num = parseInt(hex || numStr, hex ? 16 : 10);
- return String.fromCharCode(num);
- });
+ return str
+ .replace(/&(quot|amp|apos|lt|gt);/g, function (_, tag) {
+ return htmlEscapeMap[tag];
+ })
+ .replace(
+ /&#(?:x([0-9a-z]{1,4})|([0-9]{1,4}));/gi,
+ function (_, hex, numStr) {
+ var num = parseInt(hex || numStr, hex ? 16 : 10);
+ return String.fromCharCode(num);
+ }
+ );
},
/**
@@ -1364,11 +1596,17 @@ Readability.prototype = {
var metadata;
- this._forEachNode(scripts, function(jsonLdElement) {
- if (!metadata && jsonLdElement.getAttribute("type") === "application/ld+json") {
+ this._forEachNode(scripts, function (jsonLdElement) {
+ if (
+ !metadata &&
+ jsonLdElement.getAttribute("type") === "application/ld+json"
+ ) {
try {
// Strip CDATA markers if present
- var content = jsonLdElement.textContent.replace(/^\s*<!\[CDATA\[|\]\]>\s*$/g, "");
+ var content = jsonLdElement.textContent.replace(
+ /^\s*<!\[CDATA\[|\]\]>\s*$/g,
+ ""
+ );
var parsed = JSON.parse(content);
if (
!parsed["@context"] ||
@@ -1378,10 +1616,8 @@ Readability.prototype = {
}
if (!parsed["@type"] && Array.isArray(parsed["@graph"])) {
- parsed = parsed["@graph"].find(function(it) {
- return (it["@type"] || "").match(
- this.REGEXPS.jsonLdArticleTypes
- );
+ parsed = parsed["@graph"].find(function (it) {
+ return (it["@type"] || "").match(this.REGEXPS.jsonLdArticleTypes);
});
}
@@ -1395,14 +1631,19 @@ Readability.prototype = {
metadata = {};
- if (typeof parsed.name === "string" && typeof parsed.headline === "string" && parsed.name !== parsed.headline) {
+ if (
+ typeof parsed.name === "string" &&
+ typeof parsed.headline === "string" &&
+ parsed.name !== parsed.headline
+ ) {
// we have both name and headline element in the JSON-LD. They should both be the same but some websites like aktualne.cz
// put their own name into "name" and the article title to "headline" which confuses Readability. So we try to check if either
// "name" or "headline" closely matches the html title, and if so, use that one. If not, then we use "name" by default.
var title = this._getArticleTitle();
var nameMatches = this._textSimilarity(parsed.name, title) > 0.75;
- var headlineMatches = this._textSimilarity(parsed.headline, title) > 0.75;
+ var headlineMatches =
+ this._textSimilarity(parsed.headline, title) > 0.75;
if (headlineMatches && !nameMatches) {
metadata.title = parsed.headline;
@@ -1417,12 +1658,16 @@ Readability.prototype = {
if (parsed.author) {
if (typeof parsed.author.name === "string") {
metadata.byline = parsed.author.name.trim();
- } else if (Array.isArray(parsed.author) && parsed.author[0] && typeof parsed.author[0].name === "string") {
+ } else if (
+ Array.isArray(parsed.author) &&
+ parsed.author[0] &&
+ typeof parsed.author[0].name === "string"
+ ) {
metadata.byline = parsed.author
- .filter(function(author) {
+ .filter(function (author) {
return author && typeof author.name === "string";
})
- .map(function(author) {
+ .map(function (author) {
return author.name.trim();
})
.join(", ");
@@ -1431,10 +1676,7 @@ Readability.prototype = {
if (typeof parsed.description === "string") {
metadata.excerpt = parsed.description.trim();
}
- if (
- parsed.publisher &&
- typeof parsed.publisher.name === "string"
- ) {
+ if (parsed.publisher && typeof parsed.publisher.name === "string") {
metadata.siteName = parsed.publisher.name.trim();
}
return;
@@ -1454,19 +1696,21 @@ Readability.prototype = {
*
* @return Object with optional "excerpt" and "byline" properties
*/
- _getArticleMetadata: function(jsonld) {
+ _getArticleMetadata: function (jsonld) {
var metadata = {};
var values = {};
var metaElements = this._doc.getElementsByTagName("meta");
// property is a space-separated list of values
- var propertyPattern = /\s*(dc|dcterm|og|twitter)\s*:\s*(author|creator|description|title|site_name)\s*/gi;
+ var propertyPattern =
+ /\s*(dc|dcterm|og|twitter)\s*:\s*(author|creator|description|title|site_name)\s*/gi;
// name is a single value
- var namePattern = /^\s*(?:(dc|dcterm|og|twitter|weibo:(article|webpage))\s*[\.:]\s*)?(author|creator|description|title|site_name)\s*$/i;
+ var namePattern =
+ /^\s*(?:(dc|dcterm|og|twitter|weibo:(article|webpage))\s*[\.:]\s*)?(author|creator|description|title|site_name)\s*$/i;
// Find description tags.
- this._forEachNode(metaElements, function(element) {
+ this._forEachNode(metaElements, function (element) {
var elementName = element.getAttribute("name");
var elementProperty = element.getAttribute("property");
var content = element.getAttribute("content");
@@ -1498,38 +1742,40 @@ Readability.prototype = {
});
// get title
- metadata.title = jsonld.title ||
- values["dc:title"] ||
- values["dcterm:title"] ||
- values["og:title"] ||
- values["weibo:article:title"] ||
- values["weibo:webpage:title"] ||
- values["title"] ||
- values["twitter:title"];
+ metadata.title =
+ jsonld.title ||
+ values["dc:title"] ||
+ values["dcterm:title"] ||
+ values["og:title"] ||
+ values["weibo:article:title"] ||
+ values["weibo:webpage:title"] ||
+ values["title"] ||
+ values["twitter:title"];
if (!metadata.title) {
metadata.title = this._getArticleTitle();
}
// get author
- metadata.byline = jsonld.byline ||
- values["dc:creator"] ||
- values["dcterm:creator"] ||
- values["author"];
+ metadata.byline =
+ jsonld.byline ||
+ values["dc:creator"] ||
+ values["dcterm:creator"] ||
+ values["author"];
// get description
- metadata.excerpt = jsonld.excerpt ||
- values["dc:description"] ||
- values["dcterm:description"] ||
- values["og:description"] ||
- values["weibo:article:description"] ||
- values["weibo:webpage:description"] ||
- values["description"] ||
- values["twitter:description"];
+ metadata.excerpt =
+ jsonld.excerpt ||
+ values["dc:description"] ||
+ values["dcterm:description"] ||
+ values["og:description"] ||
+ values["weibo:article:description"] ||
+ values["weibo:webpage:description"] ||
+ values["description"] ||
+ values["twitter:description"];
// get site name
- metadata.siteName = jsonld.siteName ||
- values["og:site_name"];
+ metadata.siteName = jsonld.siteName || values["og:site_name"];
// in many sites the meta value is escaped with HTML entities,
// so here we need to unescape it
@@ -1546,8 +1792,8 @@ Readability.prototype = {
* whether as a direct child or as its descendants.
*
* @param Element
- **/
- _isSingleImage: function(node) {
+ **/
+ _isSingleImage: function (node) {
if (node.tagName === "IMG") {
return true;
}
@@ -1566,12 +1812,12 @@ Readability.prototype = {
* some sites (e.g. Medium).
*
* @param Element
- **/
- _unwrapNoscriptImages: function(doc) {
+ **/
+ _unwrapNoscriptImages: function (doc) {
// Find img without source or attributes that might contains image, and remove it.
// This is done to prevent a placeholder img is replaced by img from noscript in next step.
var imgs = Array.from(doc.getElementsByTagName("img"));
- this._forEachNode(imgs, function(img) {
+ this._forEachNode(imgs, function (img) {
for (var i = 0; i < img.attributes.length; i++) {
var attr = img.attributes[i];
switch (attr.name) {
@@ -1592,7 +1838,7 @@ Readability.prototype = {
// Next find noscript and try to extract its image
var noscripts = Array.from(doc.getElementsByTagName("noscript"));
- this._forEachNode(noscripts, function(noscript) {
+ this._forEachNode(noscripts, function (noscript) {
// Parse content of noscript and make sure it only contains image
var tmp = doc.createElement("div");
tmp.innerHTML = noscript.innerHTML;
@@ -1617,7 +1863,11 @@ Readability.prototype = {
continue;
}
- if (attr.name === "src" || attr.name === "srcset" || /\.(jpg|jpeg|png|webp)/i.test(attr.value)) {
+ if (
+ attr.name === "src" ||
+ attr.name === "srcset" ||
+ /\.(jpg|jpeg|png|webp)/i.test(attr.value)
+ ) {
if (newImg.getAttribute(attr.name) === attr.value) {
continue;
}
@@ -1640,13 +1890,16 @@ Readability.prototype = {
* Removes script tags from the document.
*
* @param Element
- **/
- _removeScripts: function(doc) {
- this._removeNodes(this._getAllNodesWithTag(doc, ["script"]), function(scriptNode) {
- scriptNode.nodeValue = "";
- scriptNode.removeAttribute("src");
- return true;
- });
+ **/
+ _removeScripts: function (doc) {
+ this._removeNodes(
+ this._getAllNodesWithTag(doc, ["script"]),
+ function (scriptNode) {
+ scriptNode.nodeValue = "";
+ scriptNode.removeAttribute("src");
+ return true;
+ }
+ );
this._removeNodes(this._getAllNodesWithTag(doc, ["noscript"]));
},
@@ -1657,25 +1910,31 @@ Readability.prototype = {
*
* @param Element
* @param string tag of child element
- **/
- _hasSingleTagInsideElement: function(element, tag) {
+ **/
+ _hasSingleTagInsideElement: function (element, tag) {
// There should be exactly 1 element child with given tag
if (element.children.length != 1 || element.children[0].tagName !== tag) {
return false;
}
// And there should be no text nodes with real content
- return !this._someNode(element.childNodes, function(node) {
- return node.nodeType === this.TEXT_NODE &&
- this.REGEXPS.hasContent.test(node.textContent);
+ return !this._someNode(element.childNodes, function (node) {
+ return (
+ node.nodeType === this.TEXT_NODE &&
+ this.REGEXPS.hasContent.test(node.textContent)
+ );
});
},
- _isElementWithoutContent: function(node) {
- return node.nodeType === this.ELEMENT_NODE &&
+ _isElementWithoutContent: function (node) {
+ return (
+ node.nodeType === this.ELEMENT_NODE &&
node.textContent.trim().length == 0 &&
(node.children.length == 0 ||
- node.children.length == node.getElementsByTagName("br").length + node.getElementsByTagName("hr").length);
+ node.children.length ==
+ node.getElementsByTagName("br").length +
+ node.getElementsByTagName("hr").length)
+ );
},
/**
@@ -1684,25 +1943,35 @@ Readability.prototype = {
* @param Element
*/
_hasChildBlockElement: function (element) {
- return this._someNode(element.childNodes, function(node) {
- return this.DIV_TO_P_ELEMS.has(node.tagName) ||
- this._hasChildBlockElement(node);
+ return this._someNode(element.childNodes, function (node) {
+ return (
+ this.DIV_TO_P_ELEMS.has(node.tagName) ||
+ this._hasChildBlockElement(node)
+ );
});
},
/***
* Determine if a node qualifies as phrasing content.
* https://developer.mozilla.org/en-US/docs/Web/Guide/HTML/Content_categories#Phrasing_content
- **/
- _isPhrasingContent: function(node) {
- return node.nodeType === this.TEXT_NODE || this.PHRASING_ELEMS.indexOf(node.tagName) !== -1 ||
- ((node.tagName === "A" || node.tagName === "DEL" || node.tagName === "INS") &&
- this._everyNode(node.childNodes, this._isPhrasingContent));
+ **/
+ _isPhrasingContent: function (node) {
+ return (
+ node.nodeType === this.TEXT_NODE ||
+ this.PHRASING_ELEMS.indexOf(node.tagName) !== -1 ||
+ ((node.tagName === "A" ||
+ node.tagName === "DEL" ||
+ node.tagName === "INS") &&
+ this._everyNode(node.childNodes, this._isPhrasingContent))
+ );
},
- _isWhitespace: function(node) {
- return (node.nodeType === this.TEXT_NODE && node.textContent.trim().length === 0) ||
- (node.nodeType === this.ELEMENT_NODE && node.tagName === "BR");
+ _isWhitespace: function (node) {
+ return (
+ (node.nodeType === this.TEXT_NODE &&
+ node.textContent.trim().length === 0) ||
+ (node.nodeType === this.ELEMENT_NODE && node.tagName === "BR")
+ );
},
/**
@@ -1712,9 +1981,10 @@ Readability.prototype = {
* @param Element
* @param Boolean normalizeSpaces (default: true)
* @return string
- **/
- _getInnerText: function(e, normalizeSpaces) {
- normalizeSpaces = (typeof normalizeSpaces === "undefined") ? true : normalizeSpaces;
+ **/
+ _getInnerText: function (e, normalizeSpaces) {
+ normalizeSpaces =
+ typeof normalizeSpaces === "undefined" ? true : normalizeSpaces;
var textContent = e.textContent.trim();
if (normalizeSpaces) {
@@ -1729,8 +1999,8 @@ Readability.prototype = {
* @param Element
* @param string - what to split on. Default is ","
* @return number (integer)
- **/
- _getCharCount: function(e, s) {
+ **/
+ _getCharCount: function (e, s) {
s = s || ",";
return this._getInnerText(e).split(s).length - 1;
},
@@ -1741,10 +2011,9 @@ Readability.prototype = {
*
* @param Element
* @return void
- **/
- _cleanStyles: function(e) {
- if (!e || e.tagName.toLowerCase() === "svg")
- return;
+ **/
+ _cleanStyles: function (e) {
+ if (!e || e.tagName.toLowerCase() === "svg") return;
// Remove `style` and deprecated presentational attributes
for (var i = 0; i < this.PRESENTATIONAL_ATTRIBUTES.length; i++) {
@@ -1769,16 +2038,15 @@ Readability.prototype = {
*
* @param Element
* @return number (float)
- **/
- _getLinkDensity: function(element) {
+ **/
+ _getLinkDensity: function (element) {
var textLength = this._getInnerText(element).length;
- if (textLength === 0)
- return 0;
+ if (textLength === 0) return 0;
var linkLength = 0;
// XXX implement _reduceNodeList?
- this._forEachNode(element.getElementsByTagName("a"), function(linkNode) {
+ this._forEachNode(element.getElementsByTagName("a"), function (linkNode) {
var href = linkNode.getAttribute("href");
var coefficient = href && this.REGEXPS.hashUrl.test(href) ? 0.3 : 1;
linkLength += this._getInnerText(linkNode).length * coefficient;
@@ -1793,29 +2061,24 @@ Readability.prototype = {
*
* @param Element
* @return number (Integer)
- **/
- _getClassWeight: function(e) {
- if (!this._flagIsActive(this.FLAG_WEIGHT_CLASSES))
- return 0;
+ **/
+ _getClassWeight: function (e) {
+ if (!this._flagIsActive(this.FLAG_WEIGHT_CLASSES)) return 0;
var weight = 0;
// Look for a special classname
- if (typeof(e.className) === "string" && e.className !== "") {
- if (this.REGEXPS.negative.test(e.className))
- weight -= 25;
+ if (typeof e.className === "string" && e.className !== "") {
+ if (this.REGEXPS.negative.test(e.className)) weight -= 25;
- if (this.REGEXPS.positive.test(e.className))
- weight += 25;
+ if (this.REGEXPS.positive.test(e.className)) weight += 25;
}
// Look for a special ID
- if (typeof(e.id) === "string" && e.id !== "") {
- if (this.REGEXPS.negative.test(e.id))
- weight -= 25;
+ if (typeof e.id === "string" && e.id !== "") {
+ if (this.REGEXPS.negative.test(e.id)) weight -= 25;
- if (this.REGEXPS.positive.test(e.id))
- weight += 25;
+ if (this.REGEXPS.positive.test(e.id)) weight += 25;
}
return weight;
@@ -1829,10 +2092,10 @@ Readability.prototype = {
* @param string tag to clean
* @return void
**/
- _clean: function(e, tag) {
+ _clean: function (e, tag) {
var isEmbed = ["object", "embed", "iframe"].indexOf(tag) !== -1;
- this._removeNodes(this._getAllNodesWithTag(e, [tag]), function(element) {
+ this._removeNodes(this._getAllNodesWithTag(e, [tag]), function (element) {
// Allow youtube and vimeo videos through as people usually want to see those.
if (isEmbed) {
// First, check the elements attributes to see if any of them contain youtube or vimeo
@@ -1843,7 +2106,10 @@ Readability.prototype = {
}
// For embed with <object> tag, check inner HTML as well.
- if (element.tagName === "object" && this.REGEXPS.videos.test(element.innerHTML)) {
+ if (
+ element.tagName === "object" &&
+ this.REGEXPS.videos.test(element.innerHTML)
+ ) {
return false;
}
}
@@ -1861,14 +2127,16 @@ Readability.prototype = {
* @param Function filterFn a filter to invoke to determine whether this node 'counts'
* @return Boolean
*/
- _hasAncestorTag: function(node, tagName, maxDepth, filterFn) {
+ _hasAncestorTag: function (node, tagName, maxDepth, filterFn) {
maxDepth = maxDepth || 3;
tagName = tagName.toUpperCase();
var depth = 0;
while (node.parentNode) {
- if (maxDepth > 0 && depth > maxDepth)
- return false;
- if (node.parentNode.tagName === tagName && (!filterFn || filterFn(node.parentNode)))
+ if (maxDepth > 0 && depth > maxDepth) return false;
+ if (
+ node.parentNode.tagName === tagName &&
+ (!filterFn || filterFn(node.parentNode))
+ )
return true;
node = node.parentNode;
depth++;
@@ -1879,7 +2147,7 @@ Readability.prototype = {
/**
* Return an object indicating how many rows and columns this table has.
*/
- _getRowAndColumnCount: function(table) {
+ _getRowAndColumnCount: function (table) {
var rows = 0;
var columns = 0;
var trs = table.getElementsByTagName("tr");
@@ -1888,7 +2156,7 @@ Readability.prototype = {
if (rowspan) {
rowspan = parseInt(rowspan, 10);
}
- rows += (rowspan || 1);
+ rows += rowspan || 1;
// Now look for column-related info
var columnsInThisRow = 0;
@@ -1898,11 +2166,11 @@ Readability.prototype = {
if (colspan) {
colspan = parseInt(colspan, 10);
}
- columnsInThisRow += (colspan || 1);
+ columnsInThisRow += colspan || 1;
}
columns = Math.max(columns, columnsInThisRow);
}
- return {rows: rows, columns: columns};
+ return { rows: rows, columns: columns };
},
/**
@@ -1910,7 +2178,7 @@ Readability.prototype = {
* similar checks as
* https://searchfox.org/mozilla-central/rev/f82d5c549f046cb64ce5602bfd894b7ae807c8f8/accessible/generic/TableAccessible.cpp#19
*/
- _markDataTables: function(root) {
+ _markDataTables: function (root) {
var tables = root.getElementsByTagName("table");
for (var i = 0; i < tables.length; i++) {
var table = tables[i];
@@ -1938,7 +2206,7 @@ Readability.prototype = {
// If the table has a descendant with any of these tags, consider a data table:
var dataTableDescendants = ["col", "colgroup", "tfoot", "thead", "th"];
- var descendantExists = function(tag) {
+ var descendantExists = function (tag) {
return !!table.getElementsByTagName(tag)[0];
};
if (dataTableDescendants.some(descendantExists)) {
@@ -1965,82 +2233,98 @@ Readability.prototype = {
/* convert images and figures that have properties like data-src into images that can be loaded without JS */
_fixLazyImages: function (root) {
- this._forEachNode(this._getAllNodesWithTag(root, ["img", "picture", "figure"]), function (elem) {
- // In some sites (e.g. Kotaku), they put 1px square image as base64 data uri in the src attribute.
- // So, here we check if the data uri is too short, just might as well remove it.
- if (elem.src && this.REGEXPS.b64DataUrl.test(elem.src)) {
- // Make sure it's not SVG, because SVG can have a meaningful image in under 133 bytes.
- var parts = this.REGEXPS.b64DataUrl.exec(elem.src);
- if (parts[1] === "image/svg+xml") {
- return;
- }
-
- // Make sure this element has other attributes which contains image.
- // If it doesn't, then this src is important and shouldn't be removed.
- var srcCouldBeRemoved = false;
- for (var i = 0; i < elem.attributes.length; i++) {
- var attr = elem.attributes[i];
- if (attr.name === "src") {
- continue;
+ this._forEachNode(
+ this._getAllNodesWithTag(root, ["img", "picture", "figure"]),
+ function (elem) {
+ // In some sites (e.g. Kotaku), they put 1px square image as base64 data uri in the src attribute.
+ // So, here we check if the data uri is too short, just might as well remove it.
+ if (elem.src && this.REGEXPS.b64DataUrl.test(elem.src)) {
+ // Make sure it's not SVG, because SVG can have a meaningful image in under 133 bytes.
+ var parts = this.REGEXPS.b64DataUrl.exec(elem.src);
+ if (parts[1] === "image/svg+xml") {
+ return;
}
- if (/\.(jpg|jpeg|png|webp)/i.test(attr.value)) {
- srcCouldBeRemoved = true;
- break;
+ // Make sure this element has other attributes which contains image.
+ // If it doesn't, then this src is important and shouldn't be removed.
+ var srcCouldBeRemoved = false;
+ for (var i = 0; i < elem.attributes.length; i++) {
+ var attr = elem.attributes[i];
+ if (attr.name === "src") {
+ continue;
+ }
+
+ if (/\.(jpg|jpeg|png|webp)/i.test(attr.value)) {
+ srcCouldBeRemoved = true;
+ break;
+ }
}
- }
- // Here we assume if image is less than 100 bytes (or 133B after encoded to base64)
- // it will be too small, therefore it might be placeholder image.
- if (srcCouldBeRemoved) {
- var b64starts = elem.src.search(/base64\s*/i) + 7;
- var b64length = elem.src.length - b64starts;
- if (b64length < 133) {
- elem.removeAttribute("src");
+ // Here we assume if image is less than 100 bytes (or 133B after encoded to base64)
+ // it will be too small, therefore it might be placeholder image.
+ if (srcCouldBeRemoved) {
+ var b64starts = elem.src.search(/base64\s*/i) + 7;
+ var b64length = elem.src.length - b64starts;
+ if (b64length < 133) {
+ elem.removeAttribute("src");
+ }
}
}
- }
-
- // also check for "null" to work around https://github.com/jsdom/jsdom/issues/2580
- if ((elem.src || (elem.srcset && elem.srcset != "null")) && elem.className.toLowerCase().indexOf("lazy") === -1) {
- return;
- }
- for (var j = 0; j < elem.attributes.length; j++) {
- attr = elem.attributes[j];
- if (attr.name === "src" || attr.name === "srcset" || attr.name === "alt") {
- continue;
- }
- var copyTo = null;
- if (/\.(jpg|jpeg|png|webp)\s+\d/.test(attr.value)) {
- copyTo = "srcset";
- } else if (/^\s*\S+\.(jpg|jpeg|png|webp)\S*\s*$/.test(attr.value)) {
- copyTo = "src";
+ // also check for "null" to work around https://github.com/jsdom/jsdom/issues/2580
+ if (
+ (elem.src || (elem.srcset && elem.srcset != "null")) &&
+ elem.className.toLowerCase().indexOf("lazy") === -1
+ ) {
+ return;
}
- if (copyTo) {
- //if this is an img or picture, set the attribute directly
- if (elem.tagName === "IMG" || elem.tagName === "PICTURE") {
- elem.setAttribute(copyTo, attr.value);
- } else if (elem.tagName === "FIGURE" && !this._getAllNodesWithTag(elem, ["img", "picture"]).length) {
- //if the item is a <figure> that does not contain an image or picture, create one and place it inside the figure
- //see the nytimes-3 testcase for an example
- var img = this._doc.createElement("img");
- img.setAttribute(copyTo, attr.value);
- elem.appendChild(img);
+
+ for (var j = 0; j < elem.attributes.length; j++) {
+ attr = elem.attributes[j];
+ if (
+ attr.name === "src" ||
+ attr.name === "srcset" ||
+ attr.name === "alt"
+ ) {
+ continue;
+ }
+ var copyTo = null;
+ if (/\.(jpg|jpeg|png|webp)\s+\d/.test(attr.value)) {
+ copyTo = "srcset";
+ } else if (/^\s*\S+\.(jpg|jpeg|png|webp)\S*\s*$/.test(attr.value)) {
+ copyTo = "src";
+ }
+ if (copyTo) {
+ //if this is an img or picture, set the attribute directly
+ if (elem.tagName === "IMG" || elem.tagName === "PICTURE") {
+ elem.setAttribute(copyTo, attr.value);
+ } else if (
+ elem.tagName === "FIGURE" &&
+ !this._getAllNodesWithTag(elem, ["img", "picture"]).length
+ ) {
+ //if the item is a <figure> that does not contain an image or picture, create one and place it inside the figure
+ //see the nytimes-3 testcase for an example
+ var img = this._doc.createElement("img");
+ img.setAttribute(copyTo, attr.value);
+ elem.appendChild(img);
+ }
}
}
}
- });
+ );
},
- _getTextDensity: function(e, tags) {
+ _getTextDensity: function (e, tags) {
var textLength = this._getInnerText(e, true).length;
if (textLength === 0) {
return 0;
}
var childrenLength = 0;
var children = this._getAllNodesWithTag(e, tags);
- this._forEachNode(children, (child) => childrenLength += this._getInnerText(child, true).length);
+ this._forEachNode(
+ children,
+ (child) => (childrenLength += this._getInnerText(child, true).length)
+ );
return childrenLength / textLength;
},
@@ -2050,18 +2334,17 @@ Readability.prototype = {
*
* @return void
**/
- _cleanConditionally: function(e, tag) {
- if (!this._flagIsActive(this.FLAG_CLEAN_CONDITIONALLY))
- return;
+ _cleanConditionally: function (e, tag) {
+ if (!this._flagIsActive(this.FLAG_CLEAN_CONDITIONALLY)) return;
// Gather counts for other typical elements embedded within.
// Traverse backwards so we can remove nodes at the same time
// without effecting the traversal.
//
// TODO: Consider taking into account original contentScore here.
- this._removeNodes(this._getAllNodesWithTag(e, [tag]), function(node) {
+ this._removeNodes(this._getAllNodesWithTag(e, [tag]), function (node) {
// First check if this node IS data table, in which case don't remove it.
- var isDataTable = function(t) {
+ var isDataTable = function (t) {
return t._readabilityDataTable;
};
@@ -2069,7 +2352,10 @@ Readability.prototype = {
if (!isList) {
var listLength = 0;
var listNodes = this._getAllNodesWithTag(node, ["ul", "ol"]);
- this._forEachNode(listNodes, (list) => listLength += this._getInnerText(list).length);
+ this._forEachNode(
+ listNodes,
+ (list) => (listLength += this._getInnerText(list).length)
+ );
isList = listLength / this._getInnerText(node).length > 0.9;
}
@@ -2104,10 +2390,21 @@ Readability.prototype = {
var img = node.getElementsByTagName("img").length;
var li = node.getElementsByTagName("li").length - 100;
var input = node.getElementsByTagName("input").length;
- var headingDensity = this._getTextDensity(node, ["h1", "h2", "h3", "h4", "h5", "h6"]);
+ var headingDensity = this._getTextDensity(node, [
+ "h1",
+ "h2",
+ "h3",
+ "h4",
+ "h5",
+ "h6",
+ ]);
var embedCount = 0;
- var embeds = this._getAllNodesWithTag(node, ["object", "embed", "iframe"]);
+ var embeds = this._getAllNodesWithTag(node, [
+ "object",
+ "embed",
+ "iframe",
+ ]);
for (var i = 0; i < embeds.length; i++) {
// If this embed has attribute that matches video regex, don't delete it.
@@ -2118,7 +2415,10 @@ Readability.prototype = {
}
// For embed with <object> tag, check inner HTML as well.
- if (embeds[i].tagName === "object" && this.REGEXPS.videos.test(embeds[i].innerHTML)) {
+ if (
+ embeds[i].tagName === "object" &&
+ this.REGEXPS.videos.test(embeds[i].innerHTML)
+ ) {
return false;
}
@@ -2131,11 +2431,16 @@ Readability.prototype = {
var haveToRemove =
(img > 1 && p / img < 0.5 && !this._hasAncestorTag(node, "figure")) ||
(!isList && li > p) ||
- (input > Math.floor(p/3)) ||
- (!isList && headingDensity < 0.9 && contentLength < 25 && (img === 0 || img > 2) && !this._hasAncestorTag(node, "figure")) ||
+ input > Math.floor(p / 3) ||
+ (!isList &&
+ headingDensity < 0.9 &&
+ contentLength < 25 &&
+ (img === 0 || img > 2) &&
+ !this._hasAncestorTag(node, "figure")) ||
(!isList && weight < 25 && linkDensity > 0.2) ||
(weight >= 25 && linkDensity > 0.5) ||
- ((embedCount === 1 && contentLength < 75) || embedCount > 1);
+ (embedCount === 1 && contentLength < 75) ||
+ embedCount > 1;
// Allow simple lists of images to remain in pages
if (isList && haveToRemove) {
for (var x = 0; x < node.children.length; x++) {
@@ -2164,7 +2469,7 @@ Readability.prototype = {
* @param Function determines whether a node should be removed
* @return void
**/
- _cleanMatchedNodes: function(e, filter) {
+ _cleanMatchedNodes: function (e, filter) {
var endOfSearchMarkerNode = this._getNextNode(e, true);
var next = this._getNextNode(e);
while (next && next != endOfSearchMarkerNode) {
@@ -2181,10 +2486,10 @@ Readability.prototype = {
*
* @param Element
* @return void
- **/
- _cleanHeaders: function(e) {
+ **/
+ _cleanHeaders: function (e) {
let headingNodes = this._getAllNodesWithTag(e, ["h1", "h2"]);
- this._removeNodes(headingNodes, function(node) {
+ this._removeNodes(headingNodes, function (node) {
let shouldRemove = this._getClassWeight(node) < 0;
if (shouldRemove) {
this.log("Removing header with low class weight:", node);
@@ -2200,7 +2505,7 @@ Readability.prototype = {
* @param Element the node to check.
* @return boolean indicating whether this is a title-like header.
*/
- _headerDuplicatesTitle: function(node) {
+ _headerDuplicatesTitle: function (node) {
if (node.tagName != "H1" && node.tagName != "H2") {
return false;
}
@@ -2209,20 +2514,26 @@ Readability.prototype = {
return this._textSimilarity(this._articleTitle, heading) > 0.75;
},
- _flagIsActive: function(flag) {
+ _flagIsActive: function (flag) {
return (this._flags & flag) > 0;
},
- _removeFlag: function(flag) {
+ _removeFlag: function (flag) {
this._flags = this._flags & ~flag;
},
- _isProbablyVisible: function(node) {
+ _isProbablyVisible: function (node) {
// Have to null-check node.style and node.className.indexOf to deal with SVG and MathML nodes.
- return (!node.style || node.style.display != "none")
- && !node.hasAttribute("hidden")
+ return (
+ (!node.style || node.style.display != "none") &&
+ !node.hasAttribute("hidden") &&
//check for "fallback-image" so that wikimedia math images are displayed
- && (!node.hasAttribute("aria-hidden") || node.getAttribute("aria-hidden") != "true" || (node.className && node.className.indexOf && node.className.indexOf("fallback-image") !== -1));
+ (!node.hasAttribute("aria-hidden") ||
+ node.getAttribute("aria-hidden") != "true" ||
+ (node.className &&
+ node.className.indexOf &&
+ node.className.indexOf("fallback-image") !== -1))
+ );
},
/**
@@ -2242,7 +2553,9 @@ Readability.prototype = {
if (this._maxElemsToParse > 0) {
var numTags = this._doc.getElementsByTagName("*").length;
if (numTags > this._maxElemsToParse) {
- throw new Error("Aborting parsing document; " + numTags + " elements found");
+ throw new Error(
+ "Aborting parsing document; " + numTags + " elements found"
+ );
}
}
@@ -2261,8 +2574,7 @@ Readability.prototype = {
this._articleTitle = metadata.title;
var articleContent = this._grabArticle();
- if (!articleContent)
- return null;
+ if (!articleContent) return null;
this.log("Grabbed: " + articleContent.innerHTML);
@@ -2288,9 +2600,9 @@ Readability.prototype = {
textContent: textContent,
length: textContent.length,
excerpt: metadata.excerpt,
- siteName: metadata.siteName || this._articleSiteName
+ siteName: metadata.siteName || this._articleSiteName,
};
- }
+ },
};
if (typeof module === "object") {
@@ -2355,7 +2667,7 @@ a[href^="#footnote-"]::after {
content:"] ";
}
-</style>`
+</style>`;
/*
body {
@@ -2366,17 +2678,16 @@ body {
color: #444
}
*/
-/* See also
+/* See also
* <https://gist.github.com/aanand/399131>
* and the one included in firefox @ <chrome://global/skin/aboutReader.css>
*/
-var documentClone = document.cloneNode(true);
+var documentClone = document.cloneNode(true);
var article = new Readability(documentClone).parse();
-document.head.innerHTML = `<title>${article.title}</title>\n${style_sheet_simple}`
-document.body.innerHTML = `<h1>${article.title}</h1>\n${article.content}`
-
+document.head.innerHTML = `<title>${article.title}</title>\n${style_sheet_simple}`;
+document.body.innerHTML = `<h1>${article.title}</h1>\n${article.content}`;
-/* Hack for archive.is */
+/* Hack for archive.is */
var styles = `
img {
max-width: 80% !important;
@@ -2385,10 +2696,10 @@ img {
margin-left: auto;
margin-right: auto;
}
-`
+`;
-if (document.domain == "archive.is" ){
- styles+= `
+if (document.domain == "archive.is") {
+ styles += `
li > span {
display: none !important;
@@ -2405,10 +2716,10 @@ if (document.domain == "archive.is" ){
#div[id^='stickypbModal'] {
display: none;
}
- `
+ `;
}
-var styleSheet = document.createElement('style')
-styleSheet.innerText = styles
-document.head.appendChild(styleSheet)
-console.log('Style changed')
+var styleSheet = document.createElement("style");
+styleSheet.innerText = styles;
+document.head.appendChild(styleSheet);
+console.log("Style changed");
