{
 "variants": {
  "markitdown": {
   "version": "0.1.9",
   "setup_seconds": null,
   "pages": {
    "docs-python-classes": {
     "seconds": 0.261,
     "error": null,
     "type": "docs",
     "tokens": 10290,
     "chars": 43197,
     "h_found": 18,
     "h_total": 18,
     "leaked_pct": 7.32,
     "leaked_tokens": 461,
     "word_tokens": 6295,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "docs-requests": {
     "seconds": 0.173,
     "error": null,
     "type": "docs",
     "tokens": 5193,
     "chars": 21535,
     "h_found": 16,
     "h_total": 16,
     "leaked_pct": 3.67,
     "leaked_tokens": 111,
     "word_tokens": 3021,
     "recall_pct": 99.93,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "docs-flask": {
     "seconds": 0.134,
     "error": null,
     "type": "docs",
     "tokens": 8905,
     "chars": 37849,
     "h_found": 25,
     "h_total": 25,
     "leaked_pct": 3.07,
     "leaked_tokens": 154,
     "word_tokens": 5015,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 1,
      "src_rows": 5,
      "src_cells_with_text": 10,
      "md_pipe_tables": 1,
      "md_pipe_rows": 5,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "table-wiki-markup": {
     "seconds": 0.061,
     "error": "HTTPError: 403 Client Error: Forbidden for url: https://en.wikipedia.org/wiki/Comparison_of_lightweight_markup_languages",
     "type": "table-heavy",
     "tokens": 0,
     "failed": true,
     "h_found": 0,
     "h_total": 22
    },
    "table-python-functions": {
     "seconds": 0.284,
     "error": null,
     "type": "table-heavy",
     "tokens": 29457,
     "chars": 116144,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 1.26,
     "leaked_tokens": 181,
     "word_tokens": 14348,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 2,
      "src_rows": 10,
      "src_cells_with_text": 21,
      "md_pipe_tables": 2,
      "md_pipe_rows": 10,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "blog-fowler": {
     "seconds": 0.482,
     "error": null,
     "type": "blog",
     "tokens": 13861,
     "chars": 60403,
     "h_found": 25,
     "h_total": 25,
     "leaked_pct": 2.34,
     "leaked_tokens": 205,
     "word_tokens": 8751,
     "recall_pct": 99.87,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "blog-joel": {
     "seconds": 0.133,
     "error": null,
     "type": "blog",
     "tokens": 6080,
     "chars": 26419,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 12.83,
     "leaked_tokens": 565,
     "word_tokens": 4405,
     "recall_pct": 99.97,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "js-quotes": {
     "seconds": 0.389,
     "error": null,
     "type": "js-heavy",
     "tokens": 60,
     "chars": 172,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 53.33,
     "leaked_tokens": 8,
     "word_tokens": 15,
     "recall_pct": 2.72,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": true
    },
    "pdf-attention": {
     "seconds": 2.777,
     "error": null,
     "type": "pdf",
     "tokens": 12175,
     "chars": 40174,
     "h_found": 10,
     "h_total": 24,
     "pipe_tables": 13,
     "failed": false
    },
    "messy-guardian": {
     "seconds": 0.255,
     "error": null,
     "type": "messy",
     "tokens": 7591,
     "chars": 23794,
     "h_found": 62,
     "h_total": 66,
     "leaked_pct": 44.55,
     "leaked_tokens": 891,
     "word_tokens": 2000,
     "recall_pct": 99.16,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    }
   },
   "web_pages": 9,
   "web_failures": [
    "table-wiki-markup",
    "js-quotes"
   ],
   "heading_recall_pct": 85.1,
   "leaked_pct_pooled": 5.9,
   "heading_recall_excl_messy_pct": 79.8,
   "leaked_pct_excl_messy": 4.0,
   "word_recall_mean_pct": 77.7,
   "median_tokens": 8905,
   "median_seconds": 0.255,
   "pdf": {
    "failed": false,
    "heading_found": 10,
    "heading_total": 24,
    "pipe_tables": 13,
    "seconds": 2.777,
    "error": null
   }
  },
  "markitdown-file": {
   "version": "0.1.9",
   "setup_seconds": null,
   "pages": {
    "docs-python-classes": {
     "seconds": 0.126,
     "error": null,
     "type": "docs",
     "tokens": 10290,
     "chars": 43197,
     "h_found": 18,
     "h_total": 18,
     "leaked_pct": 7.32,
     "leaked_tokens": 461,
     "word_tokens": 6295,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "docs-requests": {
     "seconds": 0.093,
     "error": null,
     "type": "docs",
     "tokens": 5237,
     "chars": 21208,
     "h_found": 16,
     "h_total": 16,
     "leaked_pct": 3.67,
     "leaked_tokens": 111,
     "word_tokens": 3021,
     "recall_pct": 99.93,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "docs-flask": {
     "seconds": 0.133,
     "error": null,
     "type": "docs",
     "tokens": 8563,
     "chars": 35743,
     "h_found": 25,
     "h_total": 25,
     "leaked_pct": 2.76,
     "leaked_tokens": 138,
     "word_tokens": 4999,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 1,
      "src_rows": 5,
      "src_cells_with_text": 10,
      "md_pipe_tables": 1,
      "md_pipe_rows": 6,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "table-wiki-markup": {
     "seconds": 0.435,
     "error": null,
     "type": "table-heavy",
     "tokens": 23143,
     "chars": 79522,
     "h_found": 22,
     "h_total": 22,
     "leaked_pct": 9.34,
     "leaked_tokens": 642,
     "word_tokens": 6874,
     "recall_pct": 99.86,
     "table": {
      "src_tables": 23,
      "src_rows": 200,
      "src_cells_with_text": 1650,
      "md_pipe_tables": 23,
      "md_pipe_rows": 209,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "table-python-functions": {
     "seconds": 0.544,
     "error": null,
     "type": "table-heavy",
     "tokens": 29457,
     "chars": 116144,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 1.26,
     "leaked_tokens": 181,
     "word_tokens": 14348,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 2,
      "src_rows": 10,
      "src_cells_with_text": 21,
      "md_pipe_tables": 2,
      "md_pipe_rows": 10,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "blog-fowler": {
     "seconds": 0.075,
     "error": null,
     "type": "blog",
     "tokens": 13861,
     "chars": 60403,
     "h_found": 25,
     "h_total": 25,
     "leaked_pct": 2.34,
     "leaked_tokens": 205,
     "word_tokens": 8751,
     "recall_pct": 99.87,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "blog-joel": {
     "seconds": 0.058,
     "error": null,
     "type": "blog",
     "tokens": 6080,
     "chars": 26419,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 12.83,
     "leaked_tokens": 565,
     "word_tokens": 4405,
     "recall_pct": 99.97,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "js-quotes": {
     "seconds": 0.07,
     "error": null,
     "type": "js-heavy",
     "tokens": 392,
     "chars": 1603,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 3.32,
     "leaked_tokens": 10,
     "word_tokens": 301,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "pdf-attention": {
     "seconds": 2.663,
     "error": null,
     "type": "pdf",
     "tokens": 12175,
     "chars": 40174,
     "h_found": 10,
     "h_total": 24,
     "pipe_tables": 13,
     "failed": false
    },
    "messy-guardian": {
     "seconds": 0.114,
     "error": null,
     "type": "messy",
     "tokens": 7591,
     "chars": 23794,
     "h_found": 62,
     "h_total": 66,
     "leaked_pct": 44.4,
     "leaked_tokens": 888,
     "word_tokens": 2000,
     "recall_pct": 99.26,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    }
   },
   "web_pages": 9,
   "web_failures": [],
   "heading_recall_pct": 97.7,
   "leaked_pct_pooled": 6.3,
   "heading_recall_excl_messy_pct": 100.0,
   "leaked_pct_excl_messy": 4.7,
   "word_recall_mean_pct": 99.9,
   "median_tokens": 8563,
   "median_seconds": 0.114,
   "pdf": {
    "failed": false,
    "heading_found": 10,
    "heading_total": 24,
    "pipe_tables": 13,
    "seconds": 2.663,
    "error": null
   }
  },
  "docling": {
   "version": "2.145.0",
   "setup_seconds": 0.18,
   "pages": {
    "docs-python-classes": {
     "seconds": 0.281,
     "error": null,
     "type": "docs",
     "tokens": 9595,
     "chars": 41332,
     "h_found": 18,
     "h_total": 18,
     "leaked_pct": 7.35,
     "leaked_tokens": 463,
     "word_tokens": 6297,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "docs-requests": {
     "seconds": 0.222,
     "error": null,
     "type": "docs",
     "tokens": 5060,
     "chars": 20251,
     "h_found": 16,
     "h_total": 16,
     "leaked_pct": 3.61,
     "leaked_tokens": 109,
     "word_tokens": 3021,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "docs-flask": {
     "seconds": 0.337,
     "error": null,
     "type": "docs",
     "tokens": 7919,
     "chars": 33703,
     "h_found": 25,
     "h_total": 25,
     "leaked_pct": 2.76,
     "leaked_tokens": 138,
     "word_tokens": 4999,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 1,
      "src_rows": 5,
      "src_cells_with_text": 10,
      "md_pipe_tables": 1,
      "md_pipe_rows": 5,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "table-wiki-markup": {
     "seconds": 0.749,
     "error": null,
     "type": "table-heavy",
     "tokens": 22617,
     "chars": 144860,
     "h_found": 22,
     "h_total": 22,
     "leaked_pct": 11.64,
     "leaked_tokens": 821,
     "word_tokens": 7054,
     "recall_pct": 99.94,
     "table": {
      "src_tables": 23,
      "src_rows": 200,
      "src_cells_with_text": 1650,
      "md_pipe_tables": 23,
      "md_pipe_rows": 194,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "table-python-functions": {
     "seconds": 0.798,
     "error": null,
     "type": "table-heavy",
     "tokens": 26155,
     "chars": 105105,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 2.38,
     "leaked_tokens": 324,
     "word_tokens": 13589,
     "recall_pct": 93.68,
     "table": {
      "src_tables": 2,
      "src_rows": 10,
      "src_cells_with_text": 21,
      "md_pipe_tables": 2,
      "md_pipe_rows": 10,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "blog-fowler": {
     "seconds": 0.499,
     "error": null,
     "type": "blog",
     "tokens": 12686,
     "chars": 59437,
     "h_found": 25,
     "h_total": 25,
     "leaked_pct": 2.24,
     "leaked_tokens": 196,
     "word_tokens": 8758,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "blog-joel": {
     "seconds": 0.125,
     "error": null,
     "type": "blog",
     "tokens": 5187,
     "chars": 22991,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 5.02,
     "leaked_tokens": 203,
     "word_tokens": 4044,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "js-quotes": {
     "seconds": 0.42,
     "error": null,
     "type": "js-heavy",
     "tokens": 25,
     "chars": 62,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 0.0,
     "leaked_tokens": 0,
     "word_tokens": 5,
     "recall_pct": 1.95,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": true
    },
    "pdf-attention": {
     "seconds": 61.26,
     "error": null,
     "type": "pdf",
     "tokens": 10060,
     "chars": 48951,
     "h_found": 24,
     "h_total": 24,
     "pipe_tables": 4,
     "failed": false
    },
    "messy-guardian": {
     "seconds": 0.352,
     "error": null,
     "type": "messy",
     "tokens": 3066,
     "chars": 12562,
     "h_found": 65,
     "h_total": 66,
     "leaked_pct": 36.26,
     "leaked_tokens": 635,
     "word_tokens": 1751,
     "recall_pct": 99.89,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    }
   },
   "web_pages": 9,
   "web_failures": [
    "js-quotes"
   ],
   "heading_recall_pct": 99.4,
   "leaked_pct_pooled": 5.8,
   "heading_recall_excl_messy_pct": 100.0,
   "leaked_pct_excl_messy": 4.7,
   "word_recall_mean_pct": 88.2,
   "median_tokens": 8757.0,
   "median_seconds": 0.352,
   "pdf": {
    "failed": false,
    "heading_found": 24,
    "heading_total": 24,
    "pipe_tables": 4,
    "seconds": 61.26,
    "error": null
   }
  },
  "docling-file": {
   "version": "2.145.0",
   "setup_seconds": 0.18,
   "pages": {
    "docs-python-classes": {
     "seconds": 0.198,
     "error": null,
     "type": "docs",
     "tokens": 9595,
     "chars": 41332,
     "h_found": 18,
     "h_total": 18,
     "leaked_pct": 7.35,
     "leaked_tokens": 463,
     "word_tokens": 6297,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "docs-requests": {
     "seconds": 0.123,
     "error": null,
     "type": "docs",
     "tokens": 5060,
     "chars": 20251,
     "h_found": 16,
     "h_total": 16,
     "leaked_pct": 3.61,
     "leaked_tokens": 109,
     "word_tokens": 3021,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "docs-flask": {
     "seconds": 0.211,
     "error": null,
     "type": "docs",
     "tokens": 7919,
     "chars": 33703,
     "h_found": 25,
     "h_total": 25,
     "leaked_pct": 2.76,
     "leaked_tokens": 138,
     "word_tokens": 4999,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 1,
      "src_rows": 5,
      "src_cells_with_text": 10,
      "md_pipe_tables": 1,
      "md_pipe_rows": 5,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "table-wiki-markup": {
     "seconds": 0.593,
     "error": null,
     "type": "table-heavy",
     "tokens": 22617,
     "chars": 144860,
     "h_found": 22,
     "h_total": 22,
     "leaked_pct": 11.64,
     "leaked_tokens": 821,
     "word_tokens": 7054,
     "recall_pct": 99.94,
     "table": {
      "src_tables": 23,
      "src_rows": 200,
      "src_cells_with_text": 1650,
      "md_pipe_tables": 23,
      "md_pipe_rows": 194,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "table-python-functions": {
     "seconds": 0.768,
     "error": null,
     "type": "table-heavy",
     "tokens": 26155,
     "chars": 105105,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 2.38,
     "leaked_tokens": 324,
     "word_tokens": 13589,
     "recall_pct": 93.68,
     "table": {
      "src_tables": 2,
      "src_rows": 10,
      "src_cells_with_text": 21,
      "md_pipe_tables": 2,
      "md_pipe_rows": 10,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "blog-fowler": {
     "seconds": 0.144,
     "error": null,
     "type": "blog",
     "tokens": 12686,
     "chars": 59437,
     "h_found": 25,
     "h_total": 25,
     "leaked_pct": 2.24,
     "leaked_tokens": 196,
     "word_tokens": 8758,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "blog-joel": {
     "seconds": 0.085,
     "error": null,
     "type": "blog",
     "tokens": 5187,
     "chars": 22991,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 5.02,
     "leaked_tokens": 203,
     "word_tokens": 4044,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "js-quotes": {
     "seconds": 0.029,
     "error": null,
     "type": "js-heavy",
     "tokens": 357,
     "chars": 1503,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 0.0,
     "leaked_tokens": 0,
     "word_tokens": 291,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "pdf-attention": {
     "seconds": 36.451,
     "error": null,
     "type": "pdf",
     "tokens": 10060,
     "chars": 48951,
     "h_found": 24,
     "h_total": 24,
     "pipe_tables": 4,
     "failed": false
    },
    "messy-guardian": {
     "seconds": 0.167,
     "error": null,
     "type": "messy",
     "tokens": 3066,
     "chars": 12562,
     "h_found": 65,
     "h_total": 66,
     "leaked_pct": 36.09,
     "leaked_tokens": 632,
     "word_tokens": 1751,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    }
   },
   "web_pages": 9,
   "web_failures": [],
   "heading_recall_pct": 99.4,
   "leaked_pct_pooled": 5.8,
   "heading_recall_excl_messy_pct": 100.0,
   "leaked_pct_excl_messy": 4.7,
   "word_recall_mean_pct": 99.3,
   "median_tokens": 7919,
   "median_seconds": 0.167,
   "pdf": {
    "failed": false,
    "heading_found": 24,
    "heading_total": 24,
    "pipe_tables": 4,
    "seconds": 36.451,
    "error": null
   }
  },
  "jina": {
   "version": null,
   "setup_seconds": null,
   "pages": {
    "docs-python-classes": {
     "seconds": 2.159,
     "error": null,
     "type": "docs",
     "tokens": 9008,
     "chars": 40366,
     "h_found": 18,
     "h_total": 18,
     "leaked_pct": 0.24,
     "leaked_tokens": 14,
     "word_tokens": 5776,
     "recall_pct": 98.77,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "docs-requests": {
     "seconds": 0.74,
     "error": null,
     "type": "docs",
     "tokens": 4251,
     "chars": 17889,
     "h_found": 14,
     "h_total": 16,
     "leaked_pct": 1.46,
     "leaked_tokens": 37,
     "word_tokens": 2539,
     "recall_pct": 86.37,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "docs-flask": {
     "seconds": 0.932,
     "error": null,
     "type": "docs",
     "tokens": 8796,
     "chars": 37727,
     "h_found": 25,
     "h_total": 25,
     "leaked_pct": 1.41,
     "leaked_tokens": 69,
     "word_tokens": 4905,
     "recall_pct": 99.46,
     "table": {
      "src_tables": 1,
      "src_rows": 5,
      "src_cells_with_text": 10,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "table-wiki-markup": {
     "seconds": 2.594,
     "error": null,
     "type": "table-heavy",
     "tokens": 20174,
     "chars": 72692,
     "h_found": 10,
     "h_total": 22,
     "leaked_pct": 2.65,
     "leaked_tokens": 165,
     "word_tokens": 6223,
     "recall_pct": 96.79,
     "table": {
      "src_tables": 23,
      "src_rows": 200,
      "src_cells_with_text": 1650,
      "md_pipe_tables": 16,
      "md_pipe_rows": 192,
      "cell_text_found_pct": 99.64
     },
     "failed": false
    },
    "table-python-functions": {
     "seconds": 2.525,
     "error": null,
     "type": "table-heavy",
     "tokens": 31426,
     "chars": 125901,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 0.15,
     "leaked_tokens": 21,
     "word_tokens": 14020,
     "recall_pct": 98.86,
     "table": {
      "src_tables": 2,
      "src_rows": 10,
      "src_cells_with_text": 21,
      "md_pipe_tables": 2,
      "md_pipe_rows": 10,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "blog-fowler": {
     "seconds": 0.782,
     "error": null,
     "type": "blog",
     "tokens": 7258,
     "chars": 37087,
     "h_found": 12,
     "h_total": 25,
     "leaked_pct": 0.41,
     "leaked_tokens": 24,
     "word_tokens": 5819,
     "recall_pct": 69.22,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "blog-joel": {
     "seconds": 0.82,
     "error": null,
     "type": "blog",
     "tokens": 4790,
     "chars": 21467,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 1.54,
     "leaked_tokens": 60,
     "word_tokens": 3887,
     "recall_pct": 99.73,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "js-quotes": {
     "seconds": 0.434,
     "error": null,
     "type": "js-heavy",
     "tokens": 118,
     "chars": 432,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 76.74,
     "leaked_tokens": 33,
     "word_tokens": 43,
     "recall_pct": 3.89,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": true
    },
    "pdf-attention": {
     "seconds": 0.411,
     "error": null,
     "type": "pdf",
     "tokens": 10281,
     "chars": 40738,
     "h_found": 23,
     "h_total": 24,
     "pipe_tables": 0,
     "failed": false
    },
    "messy-guardian": {
     "seconds": 1.004,
     "error": null,
     "type": "messy",
     "tokens": 5512,
     "chars": 16954,
     "h_found": 44,
     "h_total": 66,
     "leaked_pct": 54.86,
     "leaked_tokens": 1027,
     "word_tokens": 1872,
     "recall_pct": 76.92,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    }
   },
   "web_pages": 9,
   "web_failures": [
    "js-quotes"
   ],
   "heading_recall_pct": 72.0,
   "leaked_pct_pooled": 3.1,
   "heading_recall_excl_messy_pct": 75.2,
   "leaked_pct_excl_messy": 0.9,
   "word_recall_mean_pct": 80.7,
   "median_tokens": 8027.0,
   "median_seconds": 0.932,
   "pdf": {
    "failed": false,
    "heading_found": 23,
    "heading_total": 24,
    "pipe_tables": 0,
    "seconds": 0.411,
    "error": null
   }
  },
  "crawl4ai": {
   "version": "0.9.5",
   "setup_seconds": null,
   "pages": {
    "docs-python-classes": {
     "seconds": 1.375,
     "error": null,
     "type": "docs",
     "tokens": 11871,
     "chars": 49777,
     "h_found": 18,
     "h_total": 18,
     "leaked_pct": 14.77,
     "leaked_tokens": 1011,
     "word_tokens": 6845,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "docs-requests": {
     "seconds": 1.058,
     "error": null,
     "type": "docs",
     "tokens": 5824,
     "chars": 24196,
     "h_found": 16,
     "h_total": 16,
     "leaked_pct": 3.67,
     "leaked_tokens": 111,
     "word_tokens": 3021,
     "recall_pct": 99.93,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "docs-flask": {
     "seconds": 1.572,
     "error": null,
     "type": "docs",
     "tokens": 10060,
     "chars": 41918,
     "h_found": 25,
     "h_total": 25,
     "leaked_pct": 2.76,
     "leaked_tokens": 138,
     "word_tokens": 4999,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 1,
      "src_rows": 5,
      "src_cells_with_text": 10,
      "md_pipe_tables": 1,
      "md_pipe_rows": 5,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "table-wiki-markup": {
     "seconds": 1.894,
     "error": null,
     "type": "table-heavy",
     "tokens": 27976,
     "chars": 96106,
     "h_found": 22,
     "h_total": 22,
     "leaked_pct": 10.71,
     "leaked_tokens": 747,
     "word_tokens": 6973,
     "recall_pct": 99.78,
     "table": {
      "src_tables": 23,
      "src_rows": 200,
      "src_cells_with_text": 1650,
      "md_pipe_tables": 22,
      "md_pipe_rows": 171,
      "cell_text_found_pct": 99.88
     },
     "failed": false
    },
    "table-python-functions": {
     "seconds": 1.856,
     "error": null,
     "type": "table-heavy",
     "tokens": 34255,
     "chars": 134553,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 5.07,
     "leaked_tokens": 756,
     "word_tokens": 14923,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 2,
      "src_rows": 10,
      "src_cells_with_text": 21,
      "md_pipe_tables": 2,
      "md_pipe_rows": 10,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "blog-fowler": {
     "seconds": 1.497,
     "error": null,
     "type": "blog",
     "tokens": 14041,
     "chars": 64628,
     "h_found": 25,
     "h_total": 25,
     "leaked_pct": 2.34,
     "leaked_tokens": 205,
     "word_tokens": 8751,
     "recall_pct": 99.87,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "blog-joel": {
     "seconds": 1.11,
     "error": null,
     "type": "blog",
     "tokens": 6277,
     "chars": 26767,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 12.85,
     "leaked_tokens": 566,
     "word_tokens": 4406,
     "recall_pct": 99.97,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "js-quotes": {
     "seconds": 1.459,
     "error": null,
     "type": "js-heavy",
     "tokens": 412,
     "chars": 1666,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 3.32,
     "leaked_tokens": 10,
     "word_tokens": 301,
     "recall_pct": 100.0,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "pdf-attention": {
     "seconds": 0.35,
     "error": "None: Unexpected error in _crawl_web at line 779 in _crawl_web (../venv/lib/python3.11/site-packages/crawl4ai/async_crawler_strategy.py):\nError: Failed on navigating ACS-GOTO:\nPage.goto: Download is startin",
     "type": "pdf",
     "tokens": 0,
     "failed": true,
     "h_found": 0,
     "h_total": 24
    },
    "messy-guardian": {
     "seconds": 1.094,
     "error": null,
     "type": "messy",
     "tokens": 9735,
     "chars": 31267,
     "h_found": 62,
     "h_total": 66,
     "leaked_pct": 44.55,
     "leaked_tokens": 891,
     "word_tokens": 2000,
     "recall_pct": 99.16,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    }
   },
   "web_pages": 9,
   "web_failures": [],
   "heading_recall_pct": 97.7,
   "leaked_pct_pooled": 8.5,
   "heading_recall_excl_messy_pct": 100.0,
   "leaked_pct_excl_messy": 7.1,
   "word_recall_mean_pct": 99.9,
   "median_tokens": 10060,
   "median_seconds": 1.459,
   "pdf": {
    "failed": true,
    "heading_found": 0,
    "heading_total": 24,
    "pipe_tables": null,
    "seconds": 0.35,
    "error": "None: Unexpected error in _crawl_web at line 779 in _crawl_web (../venv/lib/python3.11/site-packages/crawl4ai/async_crawler_strategy.py):\nError: Failed on navigating ACS-GOTO:\nPage.goto: Download is startin"
   }
  },
  "crawl4ai-fit": {
   "version": "0.9.5",
   "setup_seconds": null,
   "pages": {
    "docs-python-classes": {
     "seconds": 1.375,
     "error": null,
     "type": "docs",
     "tokens": 10229,
     "chars": 44102,
     "h_found": 18,
     "h_total": 18,
     "leaked_pct": 10.81,
     "leaked_tokens": 691,
     "word_tokens": 6392,
     "recall_pct": 97.82,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "docs-requests": {
     "seconds": 1.058,
     "error": null,
     "type": "docs",
     "tokens": 5539,
     "chars": 23097,
     "h_found": 16,
     "h_total": 16,
     "leaked_pct": 3.27,
     "leaked_tokens": 98,
     "word_tokens": 2995,
     "recall_pct": 99.45,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "docs-flask": {
     "seconds": 1.572,
     "error": null,
     "type": "docs",
     "tokens": 9331,
     "chars": 39250,
     "h_found": 25,
     "h_total": 25,
     "leaked_pct": 4.9,
     "leaked_tokens": 242,
     "word_tokens": 4936,
     "recall_pct": 96.64,
     "table": {
      "src_tables": 1,
      "src_rows": 5,
      "src_cells_with_text": 10,
      "md_pipe_tables": 1,
      "md_pipe_rows": 5,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "table-wiki-markup": {
     "seconds": 1.894,
     "error": null,
     "type": "table-heavy",
     "tokens": 16273,
     "chars": 53535,
     "h_found": 22,
     "h_total": 22,
     "leaked_pct": 3.93,
     "leaked_tokens": 236,
     "word_tokens": 6002,
     "recall_pct": 93.97,
     "table": {
      "src_tables": 23,
      "src_rows": 200,
      "src_cells_with_text": 1650,
      "md_pipe_tables": 22,
      "md_pipe_rows": 186,
      "cell_text_found_pct": 96.3
     },
     "failed": false
    },
    "table-python-functions": {
     "seconds": 1.856,
     "error": null,
     "type": "table-heavy",
     "tokens": 30056,
     "chars": 120760,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 4.07,
     "leaked_tokens": 581,
     "word_tokens": 14268,
     "recall_pct": 96.83,
     "table": {
      "src_tables": 2,
      "src_rows": 10,
      "src_cells_with_text": 21,
      "md_pipe_tables": 2,
      "md_pipe_rows": 10,
      "cell_text_found_pct": 80.95
     },
     "failed": false
    },
    "blog-fowler": {
     "seconds": 1.497,
     "error": null,
     "type": "blog",
     "tokens": 10416,
     "chars": 49532,
     "h_found": 24,
     "h_total": 25,
     "leaked_pct": 0.15,
     "leaked_tokens": 11,
     "word_tokens": 7381,
     "recall_pct": 86.08,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "blog-joel": {
     "seconds": 1.11,
     "error": null,
     "type": "blog",
     "tokens": 4936,
     "chars": 21945,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 2.3,
     "leaked_tokens": 90,
     "word_tokens": 3914,
     "recall_pct": 99.7,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "js-quotes": {
     "seconds": 1.459,
     "error": null,
     "type": "js-heavy",
     "tokens": 348,
     "chars": 1463,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 0.0,
     "leaked_tokens": 0,
     "word_tokens": 289,
     "recall_pct": 99.22,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "pdf-attention": {
     "seconds": 0.35,
     "error": "None: Unexpected error in _crawl_web at line 779 in _crawl_web (../venv/lib/python3.11/site-packages/crawl4ai/async_crawler_strategy.py):\nError: Failed on navigating ACS-GOTO:\nPage.goto: Download is startin",
     "type": "pdf",
     "tokens": 0,
     "failed": true,
     "h_found": 0,
     "h_total": 24
    },
    "messy-guardian": {
     "seconds": 1.094,
     "error": null,
     "type": "messy",
     "tokens": 2282,
     "chars": 8814,
     "h_found": 59,
     "h_total": 66,
     "leaked_pct": 5.63,
     "leaked_tokens": 64,
     "word_tokens": 1136,
     "recall_pct": 96.1,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    }
   },
   "web_pages": 9,
   "web_failures": [],
   "heading_recall_pct": 95.4,
   "leaked_pct_pooled": 4.3,
   "heading_recall_excl_messy_pct": 99.1,
   "leaked_pct_excl_messy": 4.2,
   "word_recall_mean_pct": 96.2,
   "median_tokens": 9331,
   "median_seconds": 1.459,
   "pdf": {
    "failed": true,
    "heading_found": 0,
    "heading_total": 24,
    "pipe_tables": null,
    "seconds": 0.35,
    "error": "None: Unexpected error in _crawl_web at line 779 in _crawl_web (../venv/lib/python3.11/site-packages/crawl4ai/async_crawler_strategy.py):\nError: Failed on navigating ACS-GOTO:\nPage.goto: Download is startin"
   }
  },
  "webcrawlerapi": {
   "version": null,
   "setup_seconds": null,
   "pages": {
    "docs-python-classes": {
     "seconds": 0.623,
     "error": null,
     "type": "docs",
     "tokens": 9380,
     "chars": 41267,
     "h_found": 18,
     "h_total": 18,
     "leaked_pct": 4.44,
     "leaked_tokens": 269,
     "word_tokens": 6059,
     "recall_pct": 99.24,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "docs-requests": {
     "seconds": 0.835,
     "error": null,
     "type": "docs",
     "tokens": 5105,
     "chars": 21059,
     "h_found": 16,
     "h_total": 16,
     "leaked_pct": 3.48,
     "leaked_tokens": 105,
     "word_tokens": 3015,
     "recall_pct": 99.93,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "docs-flask": {
     "seconds": 0.918,
     "error": null,
     "type": "docs",
     "tokens": 8216,
     "chars": 35495,
     "h_found": 25,
     "h_total": 25,
     "leaked_pct": 2.36,
     "leaked_tokens": 117,
     "word_tokens": 4957,
     "recall_pct": 99.55,
     "table": {
      "src_tables": 1,
      "src_rows": 5,
      "src_cells_with_text": 10,
      "md_pipe_tables": 1,
      "md_pipe_rows": 6,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "table-wiki-markup": {
     "seconds": 0.805,
     "error": null,
     "type": "table-heavy",
     "tokens": 22235,
     "chars": 152140,
     "h_found": 22,
     "h_total": 22,
     "leaked_pct": 4.09,
     "leaked_tokens": 262,
     "word_tokens": 6406,
     "recall_pct": 98.36,
     "table": {
      "src_tables": 23,
      "src_rows": 200,
      "src_cells_with_text": 1650,
      "md_pipe_tables": 23,
      "md_pipe_rows": 196,
      "cell_text_found_pct": 99.52
     },
     "failed": false
    },
    "table-python-functions": {
     "seconds": 0.939,
     "error": null,
     "type": "table-heavy",
     "tokens": 28251,
     "chars": 115854,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 2.69,
     "leaked_tokens": 389,
     "word_tokens": 14473,
     "recall_pct": 99.47,
     "table": {
      "src_tables": 2,
      "src_rows": 10,
      "src_cells_with_text": 21,
      "md_pipe_tables": 2,
      "md_pipe_rows": 10,
      "cell_text_found_pct": 100.0
     },
     "failed": false
    },
    "blog-fowler": {
     "seconds": 1.126,
     "error": null,
     "type": "blog",
     "tokens": 10482,
     "chars": 49063,
     "h_found": 24,
     "h_total": 25,
     "leaked_pct": 0.87,
     "leaked_tokens": 65,
     "word_tokens": 7441,
     "recall_pct": 86.13,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "blog-joel": {
     "seconds": 1.326,
     "error": null,
     "type": "blog",
     "tokens": 4906,
     "chars": 21926,
     "h_found": 0,
     "h_total": 1,
     "leaked_pct": 2.62,
     "leaked_tokens": 103,
     "word_tokens": 3924,
     "recall_pct": 99.62,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "js-quotes": {
     "seconds": 3.499,
     "error": null,
     "type": "js-heavy",
     "tokens": 420,
     "chars": 1591,
     "h_found": 1,
     "h_total": 1,
     "leaked_pct": 0.0,
     "leaked_tokens": 0,
     "word_tokens": 290,
     "recall_pct": 99.61,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    },
    "pdf-attention": {
     "seconds": 32.502,
     "error": null,
     "type": "pdf",
     "tokens": 2082760,
     "chars": 2953660,
     "h_found": 0,
     "h_total": 24,
     "pipe_tables": 0,
     "failed": true,
     "note": "response markdown field is the PDF file base64-encoded (starts JVBERi0), not text"
    },
    "messy-guardian": {
     "seconds": 0.741,
     "error": null,
     "type": "messy",
     "tokens": 3274,
     "chars": 12513,
     "h_found": 20,
     "h_total": 66,
     "leaked_pct": 54.07,
     "leaked_tokens": 637,
     "word_tokens": 1178,
     "recall_pct": 51.84,
     "table": {
      "src_tables": 0,
      "src_rows": 0,
      "src_cells_with_text": 0,
      "md_pipe_tables": 0,
      "md_pipe_rows": 0,
      "cell_text_found_pct": null
     },
     "failed": false
    }
   },
   "web_pages": 9,
   "web_failures": [],
   "heading_recall_pct": 72.6,
   "leaked_pct_pooled": 4.1,
   "heading_recall_excl_messy_pct": 98.2,
   "leaked_pct_excl_messy": 2.8,
   "word_recall_mean_pct": 92.6,
   "median_tokens": 8216,
   "median_seconds": 0.918,
   "pdf": {
    "failed": true,
    "heading_found": 0,
    "heading_total": 24,
    "pipe_tables": 0,
    "seconds": 32.502,
    "error": null
   }
  }
 },
 "meta": {
  "pages": [
   {
    "id": "docs-python-classes",
    "type": "docs",
    "url": "https://docs.python.org/3/tutorial/classes.html",
    "robots_status": 200,
    "robots_allowed": true,
    "bytes": 108354,
    "fetched_at": "2026-10-30T15:40:10+00:00"
   },
   {
    "id": "docs-requests",
    "type": "docs",
    "url": "https://requests.readthedocs.io/en/latest/user/quickstart/",
    "robots_status": 200,
    "robots_allowed": true,
    "bytes": 60424,
    "fetched_at": "2026-10-30T15:40:14+00:00"
   },
   {
    "id": "docs-flask",
    "type": "docs",
    "url": "https://flask.palletsprojects.com/en/stable/quickstart/",
    "robots_status": 200,
    "robots_allowed": true,
    "bytes": 90801,
    "fetched_at": "2026-10-30T15:40:19+00:00"
   },
   {
    "id": "table-wiki-markup",
    "type": "table-heavy",
    "url": "https://en.wikipedia.org/wiki/Comparison_of_lightweight_markup_languages",
    "robots_status": 200,
    "robots_allowed": true,
    "bytes": 738433,
    "fetched_at": "2026-10-30T15:40:24+00:00"
   },
   {
    "id": "table-python-functions",
    "type": "table-heavy",
    "url": "https://docs.python.org/3/library/functions.html",
    "robots_status": 200,
    "robots_allowed": true,
    "bytes": 330876,
    "fetched_at": "2026-10-30T15:40:27+00:00"
   },
   {
    "id": "blog-fowler",
    "type": "blog",
    "url": "https://martinfowler.com/articles/microservices.html",
    "robots_status": 200,
    "robots_allowed": true,
    "bytes": 86071,
    "fetched_at": "2026-10-30T15:40:32+00:00"
   },
   {
    "id": "blog-joel",
    "type": "blog",
    "url": "https://www.joelonsoftware.com/2000/08/09/the-joel-test-12-steps-to-better-code/",
    "robots_status": 200,
    "robots_allowed": true,
    "bytes": 71444,
    "fetched_at": "2026-10-30T15:40:36+00:00"
   },
   {
    "id": "js-quotes",
    "type": "js-heavy",
    "url": "https://quotes.toscrape.com/js/",
    "robots_status": 404,
    "robots_allowed": true,
    "bytes": 5808,
    "fetched_at": "2026-10-30T15:40:41+00:00"
   },
   {
    "id": "pdf-attention",
    "type": "pdf",
    "url": "https://arxiv.org/pdf/1706.03762",
    "robots_status": 200,
    "robots_allowed": true,
    "bytes": 2215244,
    "fetched_at": "2026-10-30T15:40:45+00:00"
   },
   {
    "id": "messy-guardian",
    "type": "messy",
    "url": "https://www.theguardian.com/technology",
    "robots_status": 200,
    "robots_allowed": true,
    "bytes": 697852,
    "fetched_at": "2026-10-30T15:41:02+00:00"
   }
  ]
 },
 "markers_python_classes": {
  "markitdown": {
   "Previous topic": true,
   "Report a bug": true,
   "Theme": true
  },
  "markitdown-file": {
   "Previous topic": true,
   "Report a bug": true,
   "Theme": true
  },
  "docling": {
   "Previous topic": true,
   "Report a bug": true,
   "Theme": true
  },
  "docling-file": {
   "Previous topic": true,
   "Report a bug": true,
   "Theme": true
  },
  "jina": {
   "Previous topic": false,
   "Report a bug": false,
   "Theme": false
  },
  "crawl4ai": {
   "Previous topic": true,
   "Report a bug": true,
   "Theme": true
  },
  "crawl4ai-fit": {
   "Previous topic": true,
   "Report a bug": false,
   "Theme": true
  },
  "webcrawlerapi": {
   "Previous topic": true,
   "Report a bug": true,
   "Theme": true
  }
 },
 "install": {
  "note": "measured with du -sh after pip install, macOS arm64, Python 3.11.2",
  "venv_markitdown_crawl4ai_mb": 867,
  "playwright_chromium_mb": 572,
  "venv_docling_mb": 1536,
  "docling_model_cache_mb": 506
 }
}