Skip to content

parse other JSON-LD elements if the first one is not of a recognized type #713

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Nov 3, 2021
Merged

parse other JSON-LD elements if the first one is not of a recognized type #713

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0ad5029
parse other JSON-LD elements if the first one is not of a recognized …
michaldvorak-gemalto Nov 2, 2021
f50f3bc
Merge branch 'master' into fix-engadget
gijsk Nov 3, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
145 changes: 73 additions & 72 deletions Readability.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1357,87 +1357,88 @@ Readability.prototype = {
_getJSONLD: function (doc) {
var scripts = this._getAllNodesWithTag(doc, ["script"]);

var jsonLdElement = this._findNode(scripts, function(el) {
return el.getAttribute("type") === "application/ld+json";
});
var metadata;

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*$/g, "");
var parsed = JSON.parse(content);
if (
!parsed["@context"] ||
!parsed["@context"].match(/^https?\:\/\/schema\.org$/)
) {
return;
}

if (jsonLdElement) {
try {
// Strip CDATA markers if present
var content = jsonLdElement.textContent.replace(/^\s*<!\[CDATA\[|\]\]>\s*$/g, "");
var parsed = JSON.parse(content);
var metadata = {};
if (
!parsed["@context"] ||
!parsed["@context"].match(/^https?\:\/\/schema\.org$/)
) {
return metadata;
}
if (!parsed["@type"] && Array.isArray(parsed["@graph"])) {
parsed = parsed["@graph"].find(function(it) {
return (it["@type"] || "").match(
this.REGEXPS.jsonLdArticleTypes
);
});
}

if (!parsed["@type"] && Array.isArray(parsed["@graph"])) {
parsed = parsed["@graph"].find(function(it) {
return (it["@type"] || "").match(
this.REGEXPS.jsonLdArticleTypes
);
});
}
if (
!parsed ||
!parsed["@type"] ||
!parsed["@type"].match(this.REGEXPS.jsonLdArticleTypes)
) {
return;
}

if (
!parsed ||
!parsed["@type"] ||
!parsed["@type"].match(this.REGEXPS.jsonLdArticleTypes)
) {
return metadata;
}
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.
metadata = {};

var title = this._getArticleTitle();
var nameMatches = this._textSimilarity(parsed.name, title) > 0.75;
var headlineMatches = this._textSimilarity(parsed.headline, title) > 0.75;
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.

if (headlineMatches && !nameMatches) {
metadata.title = parsed.headline;
} else {
metadata.title = parsed.name;
}
var title = this._getArticleTitle();
var nameMatches = this._textSimilarity(parsed.name, title) > 0.75;
var headlineMatches = this._textSimilarity(parsed.headline, title) > 0.75;

} else if (typeof parsed.name === "string") {
metadata.title = parsed.name.trim();
} else if (typeof parsed.headline === "string") {
metadata.title = parsed.headline.trim();
}
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") {
metadata.byline = parsed.author
.filter(function(author) {
return author && typeof author.name === "string";
})
.map(function(author) {
return author.name.trim();
})
.join(", ");
if (headlineMatches && !nameMatches) {
metadata.title = parsed.headline;
} else {
metadata.title = parsed.name;
}
} else if (typeof parsed.name === "string") {
metadata.title = parsed.name.trim();
} else if (typeof parsed.headline === "string") {
metadata.title = parsed.headline.trim();
}
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") {
metadata.byline = parsed.author
.filter(function(author) {
return author && typeof author.name === "string";
})
.map(function(author) {
return author.name.trim();
})
.join(", ");
}
}
if (typeof parsed.description === "string") {
metadata.excerpt = parsed.description.trim();
}
if (
parsed.publisher &&
typeof parsed.publisher.name === "string"
) {
metadata.siteName = parsed.publisher.name.trim();
}
return;
} catch (err) {
this.log(err.message);
}
if (typeof parsed.description === "string") {
metadata.excerpt = parsed.description.trim();
}
if (
parsed.publisher &&
typeof parsed.publisher.name === "string"
) {
metadata.siteName = parsed.publisher.name.trim();
}
return metadata;
} catch (err) {
this.log(err.message);
}
}
return {};
});
return metadata ? metadata : {};
},

/**
Expand Down
2 changes: 1 addition & 1 deletion test/test-pages/engadget/expected-metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
{
"title": "Xbox One X review: A console that keeps up with gaming PCs",
"byline": null,
"byline": "Devindra Hardawar",
"dir": null,
"excerpt": "The Xbox One X is the most powerful gaming console ever, but it's not for everyone yet.",
"siteName": "Engadget",
Expand Down