pymupdf-cmd/4llm.py at main · amirlogic/pymupdf-cmd · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177

import pymupdf4llm

from pathlib import Path

def doRapOCR(img):
    from rapidocr import RapidOCR

    engine = RapidOCR()

    result, _ = engine(img)

    ocr_output = []
    for line in result:
        box, text, conf = line
        # Convert polygon -> bounding box
        x_coords = [p[0] for p in box]
        y_coords = [p[1] for p in box]
        bbox = [min(x_coords), min(y_coords), max(x_coords), max(y_coords)]

        ocr_output.append((bbox, text, conf))

    return ocr_output

def mdImages():

    pass

def main():

    print("\n\tPyMuPDF4LLM Command Line App\n")

    print("\n\n","Whole file(s) to MD:\t\t|","\tfilemd","\tdirmd","\tnohdft",)

    print("\n\n","To MD with Images:\t\t|","\tfilemdi","\tfilemdi64",)

    print("\n\n","Force OCR:\t\t|","\tfullocr",)

    print("\n\n","Table strategy:\t\t|",)

    #print("\n\n","Images:\t\t|",)

    #print("\n\n","Forms:\t|",)

    #print("\n\n","Transform:\t|",)

    #print("\n\n","Export:\t|",)

    print("\n\n","Multiple parameters:\t\t|","\tcombine", )

    print("\n")

    goto = input("\nFunction: ")

    print("\n")

    if(goto == "filemd"):

        print("Single File to Markdown\n")

        filename = input("Filename: ")
        md = pymupdf4llm.to_markdown(filename,show_progress=True)
        #print("Processing...")

        if input("Write MD file? (y/n): ").lower() == "y":
            output_path = Path(filename).with_suffix(".md")
            output_path.write_text(md, encoding="utf-8")
            print(f"Wrote markdown to: {output_path}")
        else:
            print("\n", md, "\n")


    elif(goto == "dirmd"):

        print("Directory to Markdown\n")

        wdir = input("Directory (defaults to CWD): ") or Path.cwd()

        wlkpath = Path(wdir)

        for file_path in wlkpath.iterdir():

            if(file_path.suffix == ".pdf"):

                print(file_path.name)

                try:

                    md = pymupdf4llm.to_markdown(file_path,show_progress=True)


                except:

                    print("Error")

        print("All files have been processed")

    elif(goto == "nohdft"):

        print("Single File to Markdown (Header and Footer Removed)\n")

        filename = input("Filename: ")
        md = pymupdf4llm.to_markdown(filename, header=False, footer=False, show_progress=True)
        #print("Processing...")

        if input("Write MD file? (y/n): ").lower() == "y":
            output_path = Path(filename).with_suffix(".md")
            output_path.write_text(md, encoding="utf-8")
            print(f"Wrote markdown to: {output_path}")
        else:
            print("\n", md, "\n")


    elif(goto == "filemdi"):

        print("Single File to Markdown (Images included in folder)\n")

        filename = input("Filename: ")
        img_path = Path(filename).parent or Path.cwd()
        mdi = pymupdf4llm.to_markdown(filename,show_progress=True,write_images=True,image_path=img_path)

        if input("Write MD file? (y/n): ").lower() == "y":
            output_path = Path(filename).with_suffix(".md")
            output_path.write_text(mdi, encoding="utf-8")
            print(f"Wrote markdown to: {output_path}")
        else:
            print("\n", mdi, "\n")


    elif(goto == "filemdi64"):

        print("Single File to Markdown (Images included in file as base64)\n")

        filename = input("Filename: ")
        mdi = pymupdf4llm.to_markdown(filename,show_progress=True,embed_images=True)

        output_path = Path(filename).with_suffix(".md")
        output_path.write_text(mdi, encoding="utf-8")
        print(f"Wrote markdown to: {output_path}")


    elif(goto == "fullocr"):

        pass

        print("Single File to Markdown (Force OCR)\n")

        #from rapidocr import RapidOCR

        filename = input("Filename: ")
        md = pymupdf4llm.to_markdown(filename,show_progress=True,ocr_function=doRapOCR,force_ocr=True)    #force_ocr=True, ,ocr_function=doRapOCR
        # ocr_function needs to be provided


    elif(goto == "quit" or goto == "exit"):

        print("Exiting...")
        quit()


    more = input("Continue? (y/n): ")

    if(more.strip().lower() == "y"):

        main()

    else:

        print("Exiting...")


if __name__ == "__main__":

    main()