30 lines
1014 B
Python
30 lines
1014 B
Python
"""文字抽取：原生页按词取 bbox，扫描页留 OCR 接口。"""
|
||
|
||
from typing import Dict, List
|
||
|
||
import fitz # PyMuPDF
|
||
|
||
Word = Dict # {"text": str, "bbox": (x0, y0, x1, y1)}
|
||
|
||
|
||
def extract_page_words(page: "fitz.Page") -> List[Word]:
|
||
"""抽取单页所有词及 bbox 坐标（PDF 坐标系，原点左上，单位 pt）。"""
|
||
words = page.get_text("words") # [x0, y0, x1, y1, word, block, line, word_no]
|
||
return [
|
||
{"text": w[4], "bbox": (w[0], w[1], w[2], w[3])}
|
||
for w in words
|
||
]
|
||
|
||
|
||
def extract_pdf_words(pdf_bytes: bytes) -> List[List[Word]]:
|
||
"""抽取整个 PDF，外层按页。扫描页抛 NotImplementedError。"""
|
||
from .splitter import classify_page
|
||
|
||
result: List[List[Word]] = []
|
||
with fitz.open(stream=pdf_bytes, filetype="pdf") as doc:
|
||
for page in doc:
|
||
if classify_page(page) == "scanned":
|
||
raise NotImplementedError("OCR 待接入 PaddleOCR")
|
||
result.append(extract_page_words(page))
|
||
return result
|