MinerU/tests/preproc_2_parasplit_example.json

{
    "page_0":{
        "para_blocks": [
          {
              "block_id": 0,
              "bbox": [39.0, 34.719993591308594, 347.1359558105469, 51.2079963684082],
              "text": "IOP Conference Series: Earth and Environmental Science",
              "dir": [1.0, 0.0],
              "X0": 39.0,
              "X1": 347.1359558105469,
              "avg_char_width": 6.4194990793863935,
              "avg_char_height": 16.48800277709961,
              "block_font_type": "Helvetica",
              "block_font_size": 12.0,
              "is_segmented": 1,
              "paras": [
                  {
                      "para_id": 0,
                      "bbox": [39.0, 34.719993591308594, 347.1359558105469, 51.2079963684082],
                      "text": "IOP Conference Series: Earth and Environmental Science",
                      "is_matched": 1,
                      "is_title": 0,
                      "font_type": "Helvetica",
                      "font_size": 12.0,
                      "font_color": 0,
                      "neighbor_paras": [null, null]
                  }
              ],
              "bboxes_para": [[39.0, 34.719993591308594, 347.1359558105469, 51.2079963684082]]
          },
          {
              "block_id": 1,
              "bbox": [39.0, 111.38001251220703, 143.67001342773438, 123.77301025390625],
              "text": "PAPER •  OPEN ACCESS",
              "dir": [1.0, 0.0],
              "X0": 39.0,
              "X1": 143.67001342773438,
              "avg_char_width": 6.541875839233398,
              "avg_char_height": 12.392997741699219,
              "block_font_type": "Helvetica-Bold",
              "block_font_size": 9.0,
              "is_segmented": 1,
              "paras": [
                  {
                      "para_id": 0,
                      "bbox": [39.0, 111.38001251220703, 143.67001342773438, 123.77301025390625],
                      "text": "PAPER •  OPEN ACCESS",
                      "is_matched": 1,
                      "is_title": 0,
                      "font_type": "Helvetica-Bold",
                      "font_size": 9.0,
                      "font_color": 0,
                      "neighbor_paras": [null, null]
                  },
                  {
                      "para_id": 1,
                      "bbox": [39.0, 111.38001251220703, 143.67001342773438, 123.77301025390625],
                      "text": "PAPER •  OPEN ACCESS",
                      "is_matched": 1,
                      "is_title": 0,
                      "font_type": "Helvetica-Bold",
                      "font_size": 9.0,
                      "font_color": 0,
                      "neighbor_paras": [null, null]
                  }
              ],
              "bboxes_para": [[39.0, 111.38001251220703, 143.67001342773438, 123.77301025390625]]
          }
        ],

        "preproc_blocks":[ //这里已经把重叠，页眉，页脚，垂直，旋转，水印，图片，表格删掉了
            {
              "number": 0,
              "type": 0,
              "bbox": [
                428.93170166015625,
                744.921142578125,
                541.5675048828125,
                757.8131713867188
              ],
              "lines": [
                {
                  "spans": [
                    {
                      "size": 11.0,
                      "flags": 20,
                      "font": "UniversNextPro-BoldCond",
                      "color": 0,
                      "ascender": 0.9490000009536743,
                      "descender": -0.22300000488758087,
                      "text": "3",
                      "origin": [
                        536.37548828125,
                        755.3601684570312
                      ],
                      "bbox": [
                        536.37548828125,
                        744.921142578125,
                        541.5675048828125,
                        757.8131713867188
                      ]
                    }
                  ],
                  "wmode": 0,
                  "dir": [
                    1.0,
                    0.0
                  ],
                  "bbox": [
                    536.37548828125,
                    744.921142578125,
                    541.5675048828125,
                    757.8131713867188
                  ]
                },
                {
                  "spans": [
                    {
                      "size": 8.0,
                      "flags": 20,
                      "font": "UniversNextPro-BoldCond",
                      "color": 0,
                      "ascender": 0.9490000009536743,
                      "descender": -0.22300000488758087,
                      "text": "Spektrum ",
                      "origin": [
                        428.93170166015625,
                        755.3601684570312
                      ],
                      "bbox": [
                        428.93170166015625,
                        747.7681884765625,
                        458.7516174316406,
                        757.1441650390625
                      ]
                    },
                    {
                      "size": 8.0,
                      "flags": 4,
                      "font": "UniversNextPro-Cond",
                      "color": 0,
                      "ascender": 0.9359999895095825,
                      "descender": -0.21400000154972076,
                      "text": "der Wissenschaft ",
                      "origin": [
                        458.431884765625,
                        755.3601684570312
                      ],
                      "bbox": [
                        458.431884765625,
                        747.8721923828125,
                        508.0399169921875,
                        757.0721435546875
                      ]
                    },
                    {
                      "size": 8.0,
                      "flags": 4,
                      "font": "UniversNextPro-Regular",
                      "color": 0,
                      "ascender": 0.9290000200271606,
                      "descender": -0.22200000286102295,
                      "text": "7.21",
                      "origin": [
                        510.2349853515625,
                        755.3601684570312
                      ],
                      "bbox": [
                        510.2349853515625,
                        747.9281616210938,
                        524.5621948242188,
                        757.1361694335938
                      ]
                    }
                  ],
                  "wmode": 0,
                  "dir": [
                    1.0,
                    0.0
                  ],
                  "bbox": [
                    428.93170166015625,
                    747.7681884765625,
                    524.5621948242188,
                    757.1441650390625
                  ]
                }
              ]
            }
        ],

        "images":[
            {
                "bbox":[0,0,1,1],
                "image_path":"path/to/image.jpg"
            },
            {
                "bbox":[1,2,3,4],
                "image_path":"path/to/image.jpg"
            }
        ],

        "tables":[
            {
                "bbox":[0,0,1,1],
                "image_path":"path/to/image.jpg"
            },
            {
                "bbox":[1,2,3,4],
                "image_path":"path/to/image.jpg"
            }
        ],

        "interline_equations":[
            {
                "bbox":[0,0,1,1],
                "image_path":"path/to/equation.jpg"
            },
            {
                "bbox":[1,2,3,4],
                "image_path":"path/to/equation.jpg"
            }
        ],

        "inline_equations":[
            {
                "bbox":[0,0,1,1],
                "image_path":"path/to/equation.jpg"
            },
            {
                "bbox":[1,2,3,4],
                "image_path":"path/to/equation.jpg"
            }
        ],

        "layout_bboxes":[
            {
                "layout_bbox": [0,0, 1,1],
                "layout_label":"V|H|B" //未处理|垂直|水平|BAD_LAYOUT
            },
            {
                "layout_bbox": [1,2,3,4],
                "layout_label":"V|H|B"
            }
        ],
        "pymu_raw_blocks":[], //未删减的pymupdf的block，含文字图片等

        "global_statistic":{//全局性统计信息
            
        },
        "droped_text_block":[//被丢弃的文字


        ],
        "droped_image_block":[
            
        ],
        "droped_table_block":[
            
        ],
        "image_backup":[//暂时不参与处理的图片，例如互相层叠的图片，先放这里，最后组合的时候放到页面开头段落之后。

        ],
        "table_backup":[//同上

        ]
    },
    "page_1":{

    }
}