PDF文档-电子发票信息提取

发表于 分类于 阅读次数： 本文字数： 373 阅读时长 ≈ 1 分钟

用 pymupdf 提取电子发票中的信息

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
# %%
import re
import fitz  # pip install PyMuPDF
from rich.pretty import pprint


def fapiao_txt_reg(text=""):
    # 正则规则
    regs = dict(
        type=r"(电子发票.*[普通发票|增值税专用发票].*)",
        numb=r"发票号码\s*[:：]\s*(\d{20})",
        date=r"开票日期\s*[:：]\s*(\d{4}年\d{2}月\d{2}日)",
        item=r"(\*[\u4e00-\u9fff]+\*[\u4e00-\u9fff|\w]+)",
        totl=r"价税合计[\s\S]*[¥￥](\d+\.\d+)",
    )
    result = {}
    for key, reg in regs.items():
        match = re.search(reg, text)
        if match:
            result[key] = match.group(1)
    return result


# 1. 获取页面中的文字，从文字中正则提取
fapiao = "digital_12345678901234567890.pdf"
print(f"filename: {fapiao}")

src_pdf = fitz.open(fapiao)
for p, page in enumerate(src_pdf):
    blks = page.get_text("words", sort=True)
    text = "\n".join(blk[4] for blk in blks)
    print(f"- page {p}")
    pprint(text.split('\n'))
src_pdf.close()

fapiao_infos = fapiao_txt_reg(text)
pprint(fapiao_infos)


# %%
from PIL import Image
from io import BytesIO
from pyzbar import pyzbar


# 2. 获取页面中的二维码图片-解析二维码
src_pdf = fitz.open(fapiao)
print(f"filename: {fapiao}")

for p, page in enumerate(src_pdf):
    img_list = page.get_images()
    for img in img_list:
        print(f"- page {p}, ", img)
        
        # 跳过长宽不等的图片
        if img[2] != img[3]:
            continue
        
        # 转为 pillow 图片
        pixmap = src_pdf.extract_image(img[0])
        pprint(pixmap)

        qr_img = Image.open(BytesIO(pixmap["image"]))
        # qr_img.show()

        qr_decoded = pyzbar.decode(qr_img)
        pprint(qr_decoded)

        if qr_decoded:
            qr_data = qr_decoded[0].data.decode("utf-8")
            pprint(qr_data)

src_pdf.close()

# 二维码的字段定义不太确定 ？
keys = ["type", "aera", "x", "numb", "totl", "date", "y", "code"]
fapiao_infos = dict(zip(keys, qr_data.split(",")))
pprint(fapiao_infos)

# %%

# 3. 获取页面中的表格

src_pdf = fitz.open(fapiao)

page = src_pdf[0]

tabs = page.find_tables().tables

table  = tabs[0].extract()

for row in table:
    pprint(row)

for row in table:
    for col in row:
        if col:
            print(col.replace("\n", ""), end='\n')
    print()

# %%