Scrapeless Weekly Changelog: October 12–18, 2026 Updates

TL;DR:

• ChatGPT Scraper now returns citation frequency and position metadata. The new cited_count and index fields add context to citation analysis.
• Copilot Scraper can return page HTML. Set should_fetch_html to true to request HTML in the html response field.
• AI Scraper task execution is faster overall. This week also improves Gemini parsing and output formatting, plus Copilot context handling.
• The TikTok Scraper product page is live. Developers can explore supported profile, post, and Shop product collection workflows from a dedicated entry point.
• The free Scrapeless Anti-bot Detector is available. The Chrome extension identifies supported anti-bot, CAPTCHA, and browser fingerprinting signals with evidence to inspect.

---

AI-answer review needs both structured data and enough context to inspect the original result. The October 12–18 release adds citation metadata to ChatGPT Scraper and optional HTML output to Copilot Scraper. The week also brings faster AI Scraper task execution, parsing improvements, a dedicated TikTok Scraper page, and a free browser diagnostic extension.

ChatGPT Adds Citation Frequency and Position

ChatGPT Scraper responses now include cited_count and index for citation analysis.

Field	Meaning	How teams can use it
cited_count	How many times a referenced source is cited	Compare repeated source use within an answer
index	The citation’s position index in the answer body	Locate a citation when reviewing the response

These fields help AI visibility teams retain more context than a flat list of source URLs. Store the metadata alongside the answer it describes so a reviewer can connect citation frequency and placement to the same result. Repeated citation is a useful signal to examine; it does not establish that a source is accurate.

The ChatGPT Scraper reference covers the broader request and response surface. The JSON data interchange standard defines the structured format used to store such fields; their meaning belongs to the scraper’s response contract.

Copilot Adds Optional Page HTML

Copilot Scraper now accepts should_fetch_html: true and returns the requested page HTML through the html field.

This option is useful when a team wants to retain page markup alongside parsed answer data for inspection or its own processing. The HTML Living Standard defines the document syntax applications work with when parsing or transforming that markup.

Direction	Field	Behavior
Request	should_fetch_html	Set to true to request page HTML
Response	html	Contains the returned HTML

Review the Copilot Scraper reference for the surrounding actor contract when adding the option to an integration.

Start Scraping with Scrapeless

Power up your web scraping and automation workflow with Scrapeless!
Sign up today and get $5 in free credit — no credit card required.

Claim your free credit now in the Scrapeless Dashboard.

AI Scraper Execution and Output Improve

AI Scraper received an overall task-execution speed improvement this week. No fixed latency reduction is attached to this release; completion time still varies with the engine and request.

Two engine-specific changes improve result handling:

• Gemini: data parsing and output formatting have been refined.
• Copilot: context-related handling has been improved.

Together with the new output fields, these updates improve the data teams receive and the task flow that delivers it.

A Dedicated TikTok Scraper Page Is Live

The new TikTok Scraper product page provides one entry point for supported public profile, creator-post, and TikTok Shop product workflows.

The page brings the existing collection capabilities together for developers evaluating TikTok data for creator research or commerce analysis. For implementation details, the TikTok Scraper API guide explains the supported collection tasks.

Free Anti-bot Detector Helps Inspect Page Protection

Scrapeless Anti-bot Detector is a free Chrome extension that identifies supported anti-bot and WAF systems, CAPTCHA providers, and browser fingerprinting activity. It requires no account and shows matched technologies with supporting evidence.

Use the extension to inspect a page before choosing a collection approach. Detection details help distinguish a provider match from observed API activity and give a developer concrete signals to investigate. The Chrome extensions platform provides the browser integration model for tools that add this kind of browsing functionality.

The detector is a diagnostic tool: a match reflects the available signals, and no match does not prove that a website has no protection. The extension identifies technologies rather than solving challenges.

Conclusion

This week’s main additions give AI-answer workflows more context: ChatGPT gains citation frequency and position data, while Copilot can return page HTML. Faster task execution and refined engine handling support those workflows. The TikTok Scraper page and free Anti-bot Detector add clearer starting points for collection planning and page inspection.

Explore AI Scraper through the Universal Scraping API, and review Scrapeless pricing when planning production usage.

Ready to Build With Scrapeless?

Join developers building AI-answer and web-data workflows in the Scrapeless community: Discord · Telegram.

Sign up at app.scrapeless.com to get started.

FAQ

Q: What citation fields were added to ChatGPT Scraper?

ChatGPT Scraper adds cited_count for citation frequency and index for the citation’s position index in the answer body.

Q: How do I request HTML from Copilot Scraper?

Set should_fetch_html to true. The requested page HTML is returned in the html response field.

Q: Is Scrapeless Anti-bot Detector free?

Yes. Scrapeless Anti-bot Detector is a free Chrome extension that requires no account. It reports supported protection and fingerprinting signals with detection evidence.