feat(baoyu-danger-x-to-markdown): add referenced tweet rendering, media reuse, and hi-res downloads

- Render embedded tweets in articles as blockquotes with author info and text summary
- Reuse existing markdown when --download-media targets already-converted URLs
- Upgrade Twitter image downloads to 4096x4096 resolution
- Improve entity resolution with logical key lookup
- Support trailing media for all block types (headings, lists, blockquotes)
- Change output path to {username}/{tweet-id}/{content-slug}.md for stable paths
This commit is contained in:
Jim Liu 宝玉
2026-02-28 00:06:43 -06:00
parent 7d03685ade
commit b56e503b16
7 changed files with 523 additions and 47 deletions
@@ -187,11 +187,35 @@ function buildFileName(kind: MediaKind, index: number, sourceUrl: string, extens
const FRONTMATTER_COVER_RE = /^(coverImage:\s*")(https?:\/\/[^"]+)(")/m;
function toHighResUrl(rawUrl: string): string {
try {
const parsed = new URL(rawUrl);
if (parsed.hostname !== "pbs.twimg.com") return rawUrl;
const ext = path.posix.extname(parsed.pathname).replace(/^\./, "").toLowerCase();
if (!ext || !IMAGE_EXTENSIONS.has(ext)) return rawUrl;
parsed.pathname = parsed.pathname.replace(new RegExp(`\\.${ext}$`), "");
parsed.searchParams.set("format", ext === "jpeg" ? "jpg" : ext);
parsed.searchParams.set("name", "4096x4096");
return parsed.toString();
} catch {
return rawUrl;
}
}
function collectMarkdownLinkCandidates(markdown: string): MarkdownLinkCandidate[] {
MARKDOWN_LINK_RE.lastIndex = 0;
const candidates: MarkdownLinkCandidate[] = [];
const seen = new Set<string>();
const fmMatch = markdown.match(/^---\n([\s\S]*?)\n---/);
if (fmMatch) {
const coverMatch = fmMatch[1]?.match(FRONTMATTER_COVER_RE);
if (coverMatch?.[2] && !seen.has(coverMatch[2])) {
seen.add(coverMatch[2]);
candidates.push({ url: coverMatch[2], hint: "image" });
}
}
MARKDOWN_LINK_RE.lastIndex = 0;
let match: RegExpExecArray | null;
while ((match = MARKDOWN_LINK_RE.exec(markdown))) {
const label = match[1] ?? "";
@@ -204,15 +228,6 @@ function collectMarkdownLinkCandidates(markdown: string): MarkdownLinkCandidate[
});
}
const fmMatch = markdown.match(/^---\n([\s\S]*?)\n---/);
if (fmMatch) {
const coverMatch = fmMatch[1]?.match(FRONTMATTER_COVER_RE);
if (coverMatch?.[2] && !seen.has(coverMatch[2])) {
seen.add(coverMatch[2]);
candidates.push({ url: coverMatch[2], hint: "image" });
}
}
return candidates;
}
@@ -259,7 +274,8 @@ export async function localizeMarkdownMedia(
for (const candidate of candidates) {
try {
const response = await fetch(candidate.url, {
const downloadUrl = toHighResUrl(candidate.url);
const response = await fetch(downloadUrl, {
method: "GET",
redirect: "follow",
headers: {