{
  "feed_url": "https://gbilder.com/tags/scraping/feed.json",
  "home_page_url": "https://gbilder.com/tags/scraping/",
  "items": [
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://linux.slashdot.org/story/26/08/30/2235224/ais-creepy-crawlers-criticized-by-linux-foundations-it-infrastructure-director\"\u003ehttps://linux.slashdot.org/story/26/08/30/2235224/ais-creepy-crawlers-criticized-by-linux-foundations-it-infrastructure-director\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-09-02T08:48:20+02:00",
      "external_url": "https://linux.slashdot.org/story/26/08/30/2235224/ais-creepy-crawlers-criticized-by-linux-foundations-it-infrastructure-director",
      "id": "https://gbilder.com/bookmarks/01M4EHSNCGABQF0YPX22YM6EYW/",
      "tags": [
        "scraping"
      ],
      "title": "AI's 'Creepy' Crawlers Criticized by Linux Foundation's IT Infrastructure Director - Slashdot",
      "url": "https://gbilder.com/bookmarks/01M4EHSNCGABQF0YPX22YM6EYW/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://github.com/0xchasercat/draco/\"\u003ehttps://github.com/0xchasercat/draco/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-08-03T06:54:09+02:00",
      "external_url": "https://github.com/0xchasercat/draco/",
      "id": "https://gbilder.com/bookmarks/01M4EHSMYKRK73ZBQGB5Y3X9FF/",
      "tags": [
        "scraping",
        "tryme"
      ],
      "title": "GitHub - 0xchasercat/draco: Draco is a faster, cheaper and lighter firecrawl drop-in replacement that you own entirely, running on your machine, with a built in MCP, free websearch, and browserless JavaScript console. · GitHub",
      "url": "https://gbilder.com/bookmarks/01M4EHSMYKRK73ZBQGB5Y3X9FF/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://tilion.dev/blog/cloudflare-blocks-agents\"\u003ehttps://tilion.dev/blog/cloudflare-blocks-agents\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-07-11T15:17:30+02:00",
      "external_url": "https://tilion.dev/blog/cloudflare-blocks-agents",
      "id": "https://gbilder.com/bookmarks/01M4EHSMG2CK5PFEBNJKPB8QMY/",
      "tags": [
        "scraping"
      ],
      "title": "Cloudflare blocks AI agents by default | Blog",
      "url": "https://gbilder.com/bookmarks/01M4EHSMG2CK5PFEBNJKPB8QMY/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://usefeyn.com/blog/pulpie-pareto-optimal-models-for-cleaning-the-web/\"\u003ehttps://usefeyn.com/blog/pulpie-pareto-optimal-models-for-cleaning-the-web/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-07-06T22:09:05+02:00",
      "external_url": "https://usefeyn.com/blog/pulpie-pareto-optimal-models-for-cleaning-the-web/",
      "id": "https://gbilder.com/bookmarks/01M4EHSMEG974SPTRHSKJ9CJAH/",
      "tags": [
        "scraping"
      ],
      "title": "Pulpie: Pareto-Optimal Models for Cleaning the Web | Feyn",
      "url": "https://gbilder.com/bookmarks/01M4EHSMEG974SPTRHSKJ9CJAH/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://www.firecrawl.dev/\"\u003ehttps://www.firecrawl.dev/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-07-04T08:48:26+02:00",
      "external_url": "https://www.firecrawl.dev/",
      "id": "https://gbilder.com/bookmarks/01M4EHSMCTX9FXS1DNR6387TA8/",
      "tags": [
        "scraping"
      ],
      "title": "Firecrawl - The context API to search, scrape, and interact with the web at scale. 🔥",
      "url": "https://gbilder.com/bookmarks/01M4EHSMCTX9FXS1DNR6387TA8/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://kage.tamnd.com/\"\u003ehttps://kage.tamnd.com/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-06-20T22:27:18+02:00",
      "external_url": "https://kage.tamnd.com/",
      "id": "https://gbilder.com/bookmarks/01M4EHSM96RPRHYB3H4EYQE3FK/",
      "tags": [
        "scraping"
      ],
      "title": "kage",
      "url": "https://gbilder.com/bookmarks/01M4EHSM96RPRHYB3H4EYQE3FK/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://github.com/saffron-health/libretto\"\u003ehttps://github.com/saffron-health/libretto\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-04-15T19:08:35+02:00",
      "external_url": "https://github.com/saffron-health/libretto",
      "id": "https://gbilder.com/bookmarks/01M4EHSKJCC9Y12K3E2HVH8XXS/",
      "tags": [
        "scraping"
      ],
      "title": "GitHub - saffron-health/libretto: The AI toolkit for building and maintaining browser automations · GitHub",
      "url": "https://gbilder.com/bookmarks/01M4EHSKJCC9Y12K3E2HVH8XXS/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://gitflic.ru/project/magnolia1234/bypass-paywalls-chrome-clean#list-of-supported-websites\"\u003ehttps://gitflic.ru/project/magnolia1234/bypass-paywalls-chrome-clean#list-of-supported-websites\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-04-14T09:17:50+02:00",
      "external_url": "https://gitflic.ru/project/magnolia1234/bypass-paywalls-chrome-clean#list-of-supported-websites",
      "id": "https://gbilder.com/bookmarks/01M4EHSKHXCA8Z65GA40TVMMDQ/",
      "tags": [
        "scraping"
      ],
      "title": "magnolia1234/bypass-paywalls-chrome-clean",
      "url": "https://gbilder.com/bookmarks/01M4EHSKHXCA8Z65GA40TVMMDQ/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://www.buchodi.com/chatgpt-wont-let-you-type-until-cloudflare-reads-your-react-state-i-decrypted-the-program-that-does-it/\"\u003ehttps://www.buchodi.com/chatgpt-wont-let-you-type-until-cloudflare-reads-your-react-state-i-decrypted-the-program-that-does-it/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-03-30T07:49:23+02:00",
      "external_url": "https://www.buchodi.com/chatgpt-wont-let-you-type-until-cloudflare-reads-your-react-state-i-decrypted-the-program-that-does-it/",
      "id": "https://gbilder.com/bookmarks/01M4EHSKA79VCHH3S740ERMPAT/",
      "tags": [
        "cloudflare",
        "securityn",
        "scraping"
      ],
      "title": "ChatGPT Won't Let You Type Until Cloudflare Reads Your React State. I Decrypted the Program That Does It.",
      "url": "https://gbilder.com/bookmarks/01M4EHSKA79VCHH3S740ERMPAT/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://github.com/D4Vinci/Scrapling\"\u003ehttps://github.com/D4Vinci/Scrapling\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2026-02-26T08:42:02+02:00",
      "external_url": "https://github.com/D4Vinci/Scrapling",
      "id": "https://gbilder.com/bookmarks/01M4EHSJXP7XRAK7JQGCZVKJVT/",
      "tags": [
        "scraping",
        "python",
        "tryme"
      ],
      "title": "D4Vinci/Scrapling: 🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!",
      "url": "https://gbilder.com/bookmarks/01M4EHSJXP7XRAK7JQGCZVKJVT/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://github.com/internetarchive/brozzler\"\u003ehttps://github.com/internetarchive/brozzler\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-12-21T13:19:36+02:00",
      "external_url": "https://github.com/internetarchive/brozzler",
      "id": "https://gbilder.com/bookmarks/01M4EHSJ3APHW2H4PYX7MH3KEC/",
      "tags": [
        "scraping",
        "tryme",
        "vraix"
      ],
      "title": "internetarchive/brozzler: brozzler - distributed browser-based web crawler",
      "url": "https://gbilder.com/bookmarks/01M4EHSJ3APHW2H4PYX7MH3KEC/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://www.theatlantic.com/technology/2025/11/common-crawl-ai-training-data/684567/\"\u003ehttps://www.theatlantic.com/technology/2025/11/common-crawl-ai-training-data/684567/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-11-04T17:40:38+02:00",
      "external_url": "https://www.theatlantic.com/technology/2025/11/common-crawl-ai-training-data/684567/",
      "id": "https://gbilder.com/bookmarks/01M4EHSHCZDNXSK8TQAXPF3FS7/",
      "tags": [
        "scraping",
        "ml",
        "fauxpen",
        "mitp"
      ],
      "title": "Common Crawl Is Doing the AI Industry’s Dirty Work - The Atlantic",
      "url": "https://gbilder.com/bookmarks/01M4EHSHCZDNXSK8TQAXPF3FS7/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://cryptography.dog/blog/AI-scrapers-request-commented-scripts/\"\u003ehttps://cryptography.dog/blog/AI-scrapers-request-commented-scripts/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-11-01T12:46:54+02:00",
      "external_url": "https://cryptography.dog/blog/AI-scrapers-request-commented-scripts/",
      "id": "https://gbilder.com/bookmarks/01M4EHSHB6KQ3SJBWG4QZQXGY1/",
      "tags": [
        "scraping",
        "understandme"
      ],
      "title": "AI scrapers request commented scripts",
      "url": "https://gbilder.com/bookmarks/01M4EHSHB6KQ3SJBWG4QZQXGY1/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://herman.bearblog.dev/agressive-bots/\"\u003ehttps://herman.bearblog.dev/agressive-bots/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-10-29T16:50:14+02:00",
      "external_url": "https://herman.bearblog.dev/agressive-bots/",
      "id": "https://gbilder.com/bookmarks/01M4EHSHADNEQTMW3V88PEPW42/",
      "tags": [
        "scraping",
        "mitp"
      ],
      "title": "Aggressive bots ruined my weekend | Herman's blog",
      "url": "https://gbilder.com/bookmarks/01M4EHSHADNEQTMW3V88PEPW42/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://www.theregister.com/2025/08/21/ai_crawler_traffic/\"\u003ehttps://www.theregister.com/2025/08/21/ai_crawler_traffic/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-08-21T21:39:23+02:00",
      "external_url": "https://www.theregister.com/2025/08/21/ai_crawler_traffic/",
      "id": "https://gbilder.com/bookmarks/01M4EHSG5RZ24NP5PPR8G2R6CR/",
      "tags": [
        "ml",
        "scraping",
        "ml-abuse"
      ],
      "title": "Fastly warns AI bots can hit sites 39K times per minute • The Register",
      "url": "https://gbilder.com/bookmarks/01M4EHSG5RZ24NP5PPR8G2R6CR/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://www.perplexity.ai/hub/blog/agents-or-bots-making-sense-of-ai-on-the-open-web\"\u003ehttps://www.perplexity.ai/hub/blog/agents-or-bots-making-sense-of-ai-on-the-open-web\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-08-06T12:50:44+02:00",
      "external_url": "https://www.perplexity.ai/hub/blog/agents-or-bots-making-sense-of-ai-on-the-open-web",
      "id": "https://gbilder.com/bookmarks/01M4EHSFV8XH15V6NDPZ1CTDQV/",
      "tags": [
        "ml",
        "scraping",
        "mitp"
      ],
      "title": "Agents or Bots? Making Sense of AI on the Open Web",
      "url": "https://gbilder.com/bookmarks/01M4EHSFV8XH15V6NDPZ1CTDQV/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://blog.cloudflare.com/perplexity-is-using-stealth-undeclared-crawlers-to-evade-website-no-crawl-directives/\"\u003ehttps://blog.cloudflare.com/perplexity-is-using-stealth-undeclared-crawlers-to-evade-website-no-crawl-directives/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-08-04T18:43:09+02:00",
      "external_url": "https://blog.cloudflare.com/perplexity-is-using-stealth-undeclared-crawlers-to-evade-website-no-crawl-directives/",
      "id": "https://gbilder.com/bookmarks/01M4EHSFSZXSHGDQ6PSD1FYMHG/",
      "tags": [
        "ml",
        "scraping",
        "mitp"
      ],
      "title": "Perplexity is using stealth, undeclared crawlers to evade website no-crawl directives",
      "url": "https://gbilder.com/bookmarks/01M4EHSFSZXSHGDQ6PSD1FYMHG/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://github.com/trymeka/agent\"\u003ehttps://github.com/trymeka/agent\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-07-31T07:51:34+02:00",
      "external_url": "https://github.com/trymeka/agent",
      "id": "https://gbilder.com/bookmarks/01M4EHSFPNH1YR351RVKDS4WX7/",
      "tags": [
        "scraping",
        "tryme"
      ],
      "title": "trymeka/agent: state of the art browsing agent (WebArena 72.7%)",
      "url": "https://gbilder.com/bookmarks/01M4EHSFPNH1YR351RVKDS4WX7/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://iocaine.madhouse-project.org/\"\u003ehttps://iocaine.madhouse-project.org/\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-07-25T14:34:50+02:00",
      "external_url": "https://iocaine.madhouse-project.org/",
      "id": "https://gbilder.com/bookmarks/01M4EHSFMF4G5SRJCPXGHRCCFD/",
      "tags": [
        "mitp",
        "scraping",
        "bots"
      ],
      "title": "iocaine - the deadliest poison known to AI",
      "url": "https://gbilder.com/bookmarks/01M4EHSFMF4G5SRJCPXGHRCCFD/"
    },
    {
      "content_html": "\n  \u003cp class=\"bafflegab-bookmark\"\u003eBookmarked \u003ca class=\"u-bookmark-of\" href=\"https://git.madhouse-project.org/iocaine/iocaine\"\u003ehttps://git.madhouse-project.org/iocaine/iocaine\u003c/a\u003e\u003c/p\u003e\n",
      "date_published": "2025-07-12T09:31:17+02:00",
      "external_url": "https://git.madhouse-project.org/iocaine/iocaine",
      "id": "https://gbilder.com/bookmarks/01M4EHSFARKPK11XRG2EFPXCBN/",
      "tags": [
        "mitp",
        "AI",
        "scraping",
        "bots"
      ],
      "title": "iocaine/iocaine: The deadliest poison known to AI. - MadHouse Git Repositories",
      "url": "https://gbilder.com/bookmarks/01M4EHSFARKPK11XRG2EFPXCBN/"
    }
  ],
  "language": "en",
  "title": "#scraping · Louche Cannon",
  "version": "https://jsonfeed.org/version/1.1"
}