mirror of
https://github.com/heygen-com/hyperframes.git
synced 2026-09-07 10:06:21 +00:00
feat: website capture pipeline + 7-step video production skill (#284)
* feat(cli): add website capture with AI-powered DESIGN.md generation Adds `hyperframes capture <url>` command that extracts a complete design system from any website, producing AI-agent-ready output: - Full-page screenshot (lazy-load aware, nav at top) - AI-generated DESIGN.md via Claude API (colors, typography, elevation, components, do's/don'ts) with programmatic asset catalog (136+ assets with HTML context annotations like img[src], css url(), link[rel=preload]) - CSS-purged compositions (87% size reduction via PurgeCSS) - HTML-prettified compositions (one-tag-per-line for AI readability) - CLAUDE.md + .cursorrules auto-generated for AI agent instructions - Asset deduplication (srcset variants) and tracking pixel filtering * feat(cli): add gemini 3.1 pro, playwright screenshots, replica refinement - switch to gemini 3.1 pro (gemini-3.1-pro-preview) with claude fallback - playwright for full-page screenshots (fixes puppeteer gradient/fixed bugs) - replica refinement loop: generate, screenshot, compare, fix - extract inline svgs (50 max, 10kb each) to assets/svgs/ - extract visible text in dom order for content accuracy - detect js libraries (gsap, three.js, scrolltrigger) via globals - improved asset catalog grouping and naming - reverse-engineered aura system prompt documentation - comprehensive session handoff doc Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * docs: update session handoff with slack research findings - key finding: team already wants DESIGN.md integration (James, Bin, Vance) - skills quality matters enormously - must invoke /hyperframes-compose - eval infrastructure exists (Abhay's dashboards, Teodora's 78-criteria guide) - templates at templates/ need study before finalizing skill - session handoff updated with critical next steps * refactor(cli): simplify capture pipeline, remove replica generator * feat(capture): add Lottie detection and WebGL shader extraction Captures Lottie animations via network interception and WebGL shader source via gl.shaderSource hooking during site crawl. Updates website-to-hyperframes skill with asset planning guidance, Lottie/shader reading instructions, and stronger creative direction for scene planning. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * refactor(capture): clean pipeline + shader-first creative workflow Capture pipeline: - Remove dead deps (puppeteer-extra, stealth plugin, duplicate devDeps) - Remove duplicate generateAgentPrompt() call (first lied about DESIGN.md) - Remove dead canvas-to-image code in htmlExtractor (post canvas removal) - Parallelize image downloads (batches of 5 via Promise.allSettled) - Fix pre-existing TS error (match[1] guard in font downloader) - Default capture output to captures/<hostname> Skill creative overhaul: - Add shader transition selection to creative director step (Step 4) - Add shader wiring instructions to engineer step (Step 5) - Replace 4-line energy modifiers with visual vocabulary table - Strip rigid scene-by-scene templates from video-recipes.md - Strip example fill data from scene plan tables - Add "read transition refs before planning" instruction - Add creative ambition language ("how the hell did they make this") Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * docs: add skill architecture redesign spec Comprehensive redesign of website-to-hyperframes skill and capture pipeline based on code review findings and Claude Code architecture research. Key changes: remove AI auto-generation, restructure skill into phases, embed shader boilerplate in scaffold, fix color format. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * docs: add implementation plan for skill architecture redesign 13-task plan covering: capture pipeline cleanup (remove AI generation, fix colors to HEX, add asset descriptions, shader-ready scaffold), skill restructuring (4 phases with artifact gates), and compose skill Visual Identity Gate upgrade. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * refactor(capture): remove AI auto-generation and SDK dependencies * fix(capture): convert extracted colors to HEX format * refactor(capture): remove AI key path, add asset descriptions generator * refactor(capture): update agent prompt, remove hasDesignMd, add asset descriptions * feat(capture): pre-wire shader transitions in index.html scaffold * chore: remove duplicate visual-styles.md (canonical is in hyperframes/) * refactor(skill): rewrite website-to-hyperframes as phase-based orchestrator * feat(skill): add Phase 1 understand reference * feat(skill): add Phase 2 design reference with full DESIGN.md schema * feat(skill): add Phase 3 creative direction reference * feat(skill): add Phase 4 build reference with inline shader example * feat(skill): upgrade Visual Identity Gate to produce full DESIGN.md * docs: update CLAUDE.md skill references for phase-based workflow * fix: address code review findings - Remove orphaned `false` argument in generateAgentPrompt call (critical: was shifting hasLottie, hasShaders, catalogedAssets parameters) - Add HSL color handling in rgbToHex via temp element resolution - Remove build artifact commit section from phase-4-build.md - Fix __GSAP_TIMELINE reference to __timelines Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(capture): regex double-escape + simplify scaffold + fix asset descriptions - Double-escape regex in tokenExtractor template literal (\s→\\s, \d→\\d, \(→\\() so browser receives valid regex patterns via page.evaluate() - Simplify index.html scaffold: scene slots + audio + timeline + comment pointing to shader-setup.md reference (no broken inline shader boilerplate) - Fix asset descriptions: use CatalogedAsset.contexts/notes instead of nonexistent htmlContext field Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: code review — 16 bugs, 7-step skill rewrite, cleanup Code fixes: - snapshot.ts: path traversal guard, browser leak (try/finally), div-by-zero for --frames 1, port bind error handling, rAF-based render settle - index.ts: remove invalid thinkingConfig for gemini-2.5-flash, fix Gemini batch/rate-limit comments, fix video preview viewport y-coordinate - tokenExtractor.ts: remove dead seen[si] dedup code - gsap.ts: index ALL classes for inline-style transform conflict detection Skill architecture rewrite (4-phase → 7-step): - Replace phase-1 through phase-4 with step-1 through step-7 - Add techniques.md (10 visual techniques with code patterns) - Fix /hyperframes-compose → /hyperframes (skill doesn't exist) - Fix captures/arc-browser reference → shader-setup.md (file doesn't exist) - Fix step-7 hardcoded captures/stripe path - Document Gemini API free/paid rate limits in step-1 Cleanup: - CLAUDE.md: restore from Stripe-capture overwrite, update 4-phase → 7-step - .gitignore: add PR #267 skills (hyperframes-animation-map, hyperframes-contrast) - Delete old phase-*.md, animation-recreation.md, tts-integration.md Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * chore: remove dev artifacts, research docs, wrong lockfiles Remove files that shouldn't ship in this PR: - docs/research/ (aura analysis, prompt catalogs) - docs/session-*.md, docs/SESSION-HANDOFF.md (dev notes) - docs/superpowers/ planning and spec docs - pnpm-lock.yaml at root and cli (repo uses bun, not pnpm) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(CLAUDE.md): align with main — slim format, add website-to-hyperframes mention Main PR #283 removed the full skills table from CLAUDE.md and moved it to AGENTS.md. Align with that decision: use main's slim dev-focused format, fix pnpm→bun references, add one-line /website-to-hyperframes pointer. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(cli): add capture command to help groups The capture command was registered in cli.ts but missing from the help groups, so it wouldn't appear in `hyperframes --help`. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * style: format skill reference files (oxfmt) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: regenerate bun.lock after rebase The lockfile was stale after rebasing onto main — bun install --frozen-lockfile failed in CI because new dependencies (google/genai, patchright, purgecss) weren't reflected in the lockfile. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: address PR review comments + improve capture quality Review fixes (16 comments from jrusso1020 + vanceingalls): - screenshotCapture: remove Playwright dep, use Puppeteer for all screenshots - screenshotCapture: dynamic screenshot count based on page height (30% overlap) - snapshot.ts: fix duration() function-vs-property bug, cross-platform path guard - htmlExtractor: fix code injection via parameterized evaluate - index.ts: video preview re-measures position after scroll, .env file loading - capture.ts: BLOCKED.md on timeout failures - gsap.ts: 5 inline-style lint tests added (all pass) - Remove Playwright, patchright deps; @google/genai to optionalDependencies - Gitignore: generic patterns instead of 20 hardcoded directories - Remove asset-sourcing.md, video-recipes.md (unused, duplicated guidance) Capture quality improvements (tested on 10+ websites): - Color extraction: canvas-based oklch/lab resolver, pixel sampling via elementFromPoint, broad sweep for accent colors, gradient/shadow extraction - Section detection: broadened selectors for div-based layouts, height cap to skip page-level wrappers, parent bg walkup for dark sites - Font downloads: cap 6 per family / 30 total (Cal.com: 306→30) - CTA detection: text pattern matching + nav context filtering - Heading text: innerText with whitespace normalization - Gemini captioning: maxOutputTokens 100→300, .env auto-loading - .env.example updated with GEMINI_API_KEY docs - TTS ranking: Kokoro first with Python 3.10+ note * fix: address PR review comments + improve capture quality Review round 2 fixes (jrusso1020 + vanceingalls): - verify/index.ts: add path traversal guard (relative + isAbsolute) - verify/index.ts: fix sections[i] undefined typecheck error (CI green) - index.ts: escape Lottie JSON with \u003c to prevent </script> breakout - step-4-storyboard: fix technique count contradiction (2-3 per beat, not across whole video) - step-6-build: perspective tilt uses gsap.set() instead of CSS transform (avoids GSAP overwrite conflict) - step-1-capture: reorder — command first, Gemini note after (zero-config is the default path, API key is optional enhancement) - step-7-validate: add tsx fallback for snapshot command - step-3-script: vary hook patterns, don't default to number every time - assetDownloader: exempt SVGs from 10KB minimum filter (company logos like Hubspot/Intel/DHL are 2-6KB; HeyGen capture: 13→75 assets) Note: adm-zip was NOT removed (reviewer #3) — it's still in packages/cli/package.json:30. The root package.json had patchright and purgecss removed, not adm-zip. Note: ANTHROPIC_API_KEY not restored in .env.example — grep confirms zero references in the entire codebase. The @anthropic-ai/sdk dependency was removed earlier in this branch. * refactor(capture): split index.ts (1175 to 566 lines) into modules Mechanical extraction, zero logic changes. New files: - mediaCapture.ts (345 lines): Lottie preview, video manifest/screenshots - contentExtractor.ts (314 lines): library detection, text, Gemini, asset descriptions - scaffolding.ts (135 lines): .env loading, project scaffold generation Also fixes false-positive BLOCKED.md with structural Cloudflare detection. Tested on 20 websites, pre/post output identical. * chore(capture): remove --split flow (splitter, verify, cssPurger, purgecss) The --split feature auto-generates compositions from captured HTML — a different approach from the /website-to-hyperframes skill workflow where agents build compositions from scratch using the storyboard. No skill file, no step reference, and no test session ever used --split. Removes 923 lines of unused code + purgecss dependency. Backed up to ~/Desktop/capture-split-backup/ for reference. * fix(security): add ssrf protection, lottie injection fix, oom guard - assetDownloader: add isPrivateUrl() guard blocking private IP ranges (127.x, 10.x, 172.16-31.x, 192.168.x, 169.254.x), cloud metadata endpoints, localhost, and non-HTTP schemes - mediaCapture: fix Lottie JSON injection by loading shell HTML first then passing animation data via parameterized page.evaluate() - index.ts: check Content-Length header before response.buffer() in Lottie network interception to avoid OOM on multi-GB responses * fix(capture): security fixes, timeout, sub-agent dispatch instructions Security (from miguel-heygen review): - assetDownloader: export isPrivateUrl() SSRF guard - htmlExtractor: add isPrivateUrl check before CSS fetch - mediaCapture: add isPrivateUrl check before Lottie fetch - mediaCapture: fix previewPage leak (try/finally) - mediaCapture: skip Lottie files > 2MB for preview (CDP limit) - contentExtractor: skip images > 4MB for Gemini captioning - index.ts: check Content-Length before response.buffer() (OOM guard) - snapshot.ts: register error handler before server.listen() Capture improvements: - Default timeout 30s to 120s (Shopify needs ~90s for Cloudflare) - step-6-build: sub-agent dispatch template with explicit rules: pass file PATHS not contents, use local fonts not Google Fonts, verify ../assets/ references after each beat * fix(capture): catalog before DOM mutation, networkidle2, faster Gemini Critical: asset cataloger now runs BEFORE extractHtml which converts img src to data URLs. Framer sites like heykuba.com went from 2 to 78 images. - networkidle2 instead of networkidle0 (unblocks SPAs with WebSockets) - Lazy-load wait: scroll to bottom, wait for img.complete - CSS background-image cataloging for Framer/Webflow - SVG naming: checks class, id, parent, inner text (not just aria-label) - Gemini batch 5->20, pause 12s->2s (paid tier: 2000 RPM, ~0.001/img) - maxOutputTokens 300->500, descriptions sorted captioned-first - Remove tsx fallback from step-1 (reviewer nit, published CLI has it) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ular Kimsanov
co-authored by
Claude Opus 4.6
Claude Opus 4.6
parent
ebc12f7dc9
commit
87f4c77e2f
@@ -0,0 +1,242 @@
|
||||
/**
|
||||
* Extract full-page HTML from a website using Puppeteer CDP.
|
||||
*
|
||||
* All page.evaluate() calls use string expressions to avoid
|
||||
* tsx/esbuild __name injection (see esbuild issue #1031).
|
||||
*/
|
||||
|
||||
import type { Page } from "puppeteer-core";
|
||||
import type { ExtractedHtml } from "./types.js";
|
||||
import { isPrivateUrl } from "./assetDownloader.js";
|
||||
|
||||
const DEFAULT_SETTLE_TIME = 3000;
|
||||
|
||||
export async function extractHtml(
|
||||
page: Page,
|
||||
opts: { settleTime?: number } = {},
|
||||
): Promise<ExtractedHtml> {
|
||||
const settleTime = opts.settleTime ?? DEFAULT_SETTLE_TIME;
|
||||
|
||||
// Step 1: Trigger lazy loading by scrolling through the page
|
||||
await page.evaluate(`(async () => {
|
||||
var pageHeight = document.body.scrollHeight;
|
||||
var viewportH = window.innerHeight;
|
||||
var step = Math.floor(viewportH * 0.7);
|
||||
for (var y = 0; y < pageHeight + viewportH; y += step) {
|
||||
window.scrollTo(0, y);
|
||||
await new Promise(function(r) { setTimeout(r, 200); });
|
||||
}
|
||||
window.scrollTo(0, pageHeight);
|
||||
await new Promise(function(r) { setTimeout(r, 300); });
|
||||
window.scrollTo(0, 0);
|
||||
await new Promise(function(r) { setTimeout(r, 300); });
|
||||
})()`);
|
||||
|
||||
// Re-measure after lazy load
|
||||
await new Promise((r) => setTimeout(r, settleTime));
|
||||
|
||||
// Step 2: Inline external stylesheets
|
||||
// Fetch CSS from Node.js (bypasses CORS) then inject into page
|
||||
const stylesheetUrls = (await page.evaluate(`(() => {
|
||||
return Array.from(document.querySelectorAll('link[rel="stylesheet"][href]')).map(function(l) { return l.href; });
|
||||
})()`)) as string[];
|
||||
|
||||
for (const href of stylesheetUrls) {
|
||||
try {
|
||||
if (isPrivateUrl(href)) continue;
|
||||
const res = await fetch(href, {
|
||||
signal: AbortSignal.timeout(10000),
|
||||
headers: { "User-Agent": "Mozilla/5.0" },
|
||||
});
|
||||
if (!res.ok) continue;
|
||||
let css = await res.text();
|
||||
// Fix relative url() references
|
||||
css = css.replace(/url\(\s*['"]?([^'")\s]+)['"]?\s*\)/g, (match: string, url: string) => {
|
||||
if (url.startsWith("data:") || url.startsWith("http") || url.startsWith("//")) return match;
|
||||
try {
|
||||
return `url('${new URL(url, href).href}')`;
|
||||
} catch {
|
||||
return match;
|
||||
}
|
||||
});
|
||||
// Add the CSS as a <style> tag in <head> via Puppeteer's addStyleTag
|
||||
await page.addStyleTag({ content: css });
|
||||
// Remove the original <link> tag (use parameterized evaluate to avoid injection)
|
||||
await page.evaluate((targetHref: string) => {
|
||||
const links = document.querySelectorAll('link[rel="stylesheet"]');
|
||||
for (const link of links) {
|
||||
if ((link as HTMLLinkElement).href === targetHref) {
|
||||
link.remove();
|
||||
break;
|
||||
}
|
||||
}
|
||||
}, href);
|
||||
} catch {
|
||||
/* network error — skip */
|
||||
}
|
||||
}
|
||||
|
||||
// Step 3: Make URLs absolute and fix HTML entity encoding in src attributes
|
||||
await page.evaluate(`(() => {
|
||||
document.querySelectorAll("img[src]").forEach(function(el) {
|
||||
try {
|
||||
// getAttribute returns the raw HTML attribute (with &)
|
||||
// .src returns the resolved URL (with &) — use .src for the correct value
|
||||
var resolved = el.src;
|
||||
if (resolved) el.setAttribute("src", resolved);
|
||||
} catch(e) {}
|
||||
});
|
||||
// Fix srcset attributes too (Next.js image optimization)
|
||||
document.querySelectorAll("img[srcset]").forEach(function(el) {
|
||||
try {
|
||||
var srcset = el.getAttribute("srcset") || "";
|
||||
// Decode & entities in srcset
|
||||
srcset = srcset.replace(/&/g, "&");
|
||||
el.setAttribute("srcset", srcset);
|
||||
} catch(e) {}
|
||||
});
|
||||
document.querySelectorAll('[style*="url("]').forEach(function(el) {
|
||||
el.style.cssText = el.style.cssText.replace(/url\\(['"]?([^'"\\)\\s]+)['"]?\\)/g, function(_, url) {
|
||||
try { return "url('" + new URL(url, location.href).href + "')"; } catch(e) { return "url('" + url + "')"; }
|
||||
});
|
||||
});
|
||||
})()`);
|
||||
|
||||
// Step 3b: Convert cross-origin images to data URLs
|
||||
// Some CDNs (Contentful, etc.) block direct access but images are already
|
||||
// loaded in the browser. We convert loaded images to data URLs via canvas.
|
||||
await page.evaluate(`(async () => {
|
||||
var imgs = Array.from(document.querySelectorAll("img"));
|
||||
for (var i = 0; i < imgs.length; i++) {
|
||||
var img = imgs[i];
|
||||
try {
|
||||
if (!img.src || img.src.startsWith("data:")) continue;
|
||||
if (img.naturalWidth < 10 || img.naturalHeight < 10) continue;
|
||||
// Only convert cross-origin images (same-origin ones will load fine)
|
||||
var imgUrl = new URL(img.src);
|
||||
if (imgUrl.origin === location.origin) continue;
|
||||
// Try to draw to canvas — will fail if CORS blocks it
|
||||
var canvas = document.createElement("canvas");
|
||||
canvas.width = img.naturalWidth;
|
||||
canvas.height = img.naturalHeight;
|
||||
var ctx = canvas.getContext("2d");
|
||||
ctx.drawImage(img, 0, 0);
|
||||
var dataUrl = canvas.toDataURL("image/png");
|
||||
if (dataUrl.length > 100) {
|
||||
img.setAttribute("src", dataUrl);
|
||||
img.removeAttribute("srcset");
|
||||
}
|
||||
} catch(e) {
|
||||
// Canvas CORS failed — try fetch + blob as fallback
|
||||
try {
|
||||
var resp = await fetch(img.src, { mode: "cors" });
|
||||
if (resp.ok) {
|
||||
var blob = await resp.blob();
|
||||
var reader = new FileReader();
|
||||
var dataUrl2 = await new Promise(function(resolve) {
|
||||
reader.onloadend = function() { resolve(reader.result); };
|
||||
reader.readAsDataURL(blob);
|
||||
});
|
||||
if (dataUrl2 && typeof dataUrl2 === "string" && dataUrl2.length > 100) {
|
||||
img.setAttribute("src", dataUrl2);
|
||||
img.removeAttribute("srcset");
|
||||
}
|
||||
}
|
||||
} catch(e2) {
|
||||
// Both methods failed — image stays as original URL
|
||||
}
|
||||
}
|
||||
}
|
||||
})()`);
|
||||
|
||||
// Step 4: Extract everything
|
||||
const result = (await page.evaluate(`(() => {
|
||||
// Capture styles AND scripts from head separately then combine
|
||||
// Scripts include Three.js, animation libraries that we want to preserve
|
||||
var styles = Array.from(document.head.querySelectorAll("style")).map(function(s) { return s.outerHTML; }).join("\\n");
|
||||
var scripts = Array.from(document.head.querySelectorAll("script")).map(function(s) { return s.outerHTML; }).join("\\n");
|
||||
var headHtml = styles + "\\n" + scripts;
|
||||
var bodyHtml = document.body.innerHTML;
|
||||
|
||||
var cssomRules = [];
|
||||
for (var i = 0; i < document.styleSheets.length; i++) {
|
||||
var sheet = document.styleSheets[i];
|
||||
try {
|
||||
var ownerNode = sheet.ownerNode;
|
||||
if (ownerNode && ownerNode.textContent && ownerNode.textContent.trim()) continue;
|
||||
if (sheet.href) continue;
|
||||
for (var j = 0; j < sheet.cssRules.length; j++) {
|
||||
cssomRules.push(sheet.cssRules[j].cssText);
|
||||
}
|
||||
} catch(e) {}
|
||||
}
|
||||
|
||||
var htmlEl = document.documentElement;
|
||||
var attrParts = [];
|
||||
for (var i = 0; i < htmlEl.attributes.length; i++) {
|
||||
var attr = htmlEl.attributes[i];
|
||||
if (attr.name === "lang" || attr.name === "class" || attr.name === "style" || attr.name === "dir" || attr.name.startsWith("data-")) {
|
||||
attrParts.push(attr.name + '="' + attr.value.replace(/"/g, """) + '"');
|
||||
}
|
||||
}
|
||||
|
||||
return {
|
||||
headHtml: headHtml,
|
||||
bodyHtml: bodyHtml,
|
||||
cssomRules: cssomRules.join("\\n"),
|
||||
htmlAttrs: attrParts.join(" "),
|
||||
viewportWidth: Math.max(window.innerWidth, document.documentElement.scrollWidth),
|
||||
viewportHeight: window.innerHeight,
|
||||
fullPageHeight: document.body.scrollHeight
|
||||
};
|
||||
})()`)) as ExtractedHtml;
|
||||
|
||||
// Post-process in Node.js (more reliable than browser-side fixing):
|
||||
// 1. Decode & in image src/srcset attributes
|
||||
// 2. Make relative image URLs absolute using the page's origin
|
||||
const pageOrigin = new URL(page.url()).origin;
|
||||
|
||||
result.bodyHtml = result.bodyHtml.replace(
|
||||
/(<img\b[^>]*\bsrc=")([^"]*?)(")/g,
|
||||
(_match: string, pre: string, url: string, post: string) => {
|
||||
let fixed = url.replace(/&/g, "&");
|
||||
// Make relative URLs absolute
|
||||
if (fixed.startsWith("/") && !fixed.startsWith("//")) {
|
||||
fixed = pageOrigin + fixed;
|
||||
}
|
||||
return pre + fixed + post;
|
||||
},
|
||||
);
|
||||
result.bodyHtml = result.bodyHtml.replace(
|
||||
/(<img\b[^>]*\bsrcset=")([^"]*?)(")/g,
|
||||
(_match: string, pre: string, urls: string, post: string) => {
|
||||
const fixed = urls
|
||||
.replace(/&/g, "&")
|
||||
.replace(
|
||||
/(^|,\s*)(\/[^\s,]+)/g,
|
||||
(_m: string, sep: string, path: string) => sep + pageOrigin + path,
|
||||
);
|
||||
return pre + fixed + post;
|
||||
},
|
||||
);
|
||||
|
||||
// Also fix video src/poster URLs
|
||||
result.bodyHtml = result.bodyHtml.replace(
|
||||
/(<video\b[^>]*\bsrc=")([^"]*?)(")/g,
|
||||
(_match: string, pre: string, url: string, post: string) => {
|
||||
let fixed = url.replace(/&/g, "&");
|
||||
if (fixed.startsWith("/") && !fixed.startsWith("//")) fixed = pageOrigin + fixed;
|
||||
return pre + fixed + post;
|
||||
},
|
||||
);
|
||||
result.bodyHtml = result.bodyHtml.replace(
|
||||
/(<video\b[^>]*\bposter=")([^"]*?)(")/g,
|
||||
(_match: string, pre: string, url: string, post: string) => {
|
||||
let fixed = url.replace(/&/g, "&");
|
||||
if (fixed.startsWith("/") && !fixed.startsWith("//")) fixed = pageOrigin + fixed;
|
||||
return pre + fixed + post;
|
||||
},
|
||||
);
|
||||
|
||||
return result;
|
||||
}
|
||||
Reference in New Issue
Block a user