Skip to content

fix(scrape): parse spaced meta attributes #83

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

Open
aiirvizionz wants to merge 1 commit into
base: master
Choose a base branch
from
Open

fix(scrape): parse spaced meta attributes #83

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
20 changes: 19 additions & 1 deletion apps/web/lib/scrape.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,25 @@ describe("scrapeUrl redirect guard", () => {

const post = await scrapeUrl("https://example.com/post");

expect(post.title).toBe("AI's ’test—case");
expect(post.title).toBe("AI's \u2019test\u2014case");
expect(post.body).toBe("Tom & Jerry check");
});

it("reads valid meta tags with spaced attribute assignments", async () => {
const fetchMock = vi.fn(async () =>
new Response(
`<html><head>
<meta property = "og:title" content = "Spaced title">
<meta content = "Spaced description" name = "description">
</head></html>`,
{ status: 200, headers: { "content-type": "text/html" } },
),
);
vi.stubGlobal("fetch", fetchMock);

const post = await scrapeUrl("https://example.com/post");

expect(post.title).toBe("Spaced title");
expect(post.body).toBe("Spaced description");
});
});
4 changes: 2 additions & 2 deletions apps/web/lib/scrape.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,8 +67,8 @@ function stripTags(html: string): string {

function metaContent(html: string, prop: string): string | null {
const patterns = [
new RegExp(`<meta[^>]+(?:property|name)=["']${prop}["'][^>]*content=["']([^"']*)["']`, "i"),
new RegExp(`<meta[^>]+content=["']([^"']*)["'][^>]*(?:property|name)=["']${prop}["']`, "i"),
new RegExp(`<meta[^>]+(?:property|name)\\s*=\\s*["']${prop}["'][^>]*content\\s*=\\s*["']([^"']*)["']`, "i"),
new RegExp(`<meta[^>]+content\\s*=\\s*["']([^"']*)["'][^>]*(?:property|name)\\s*=\\s*["']${prop}["']`, "i"),
];
for (const re of patterns) {
const m = html.match(re);
Expand Down
Loading