38 lines
1.4 KiB
Python
38 lines
1.4 KiB
Python
from typing import List
|
||
from langchain.document_loaders.unstructured import UnstructuredFileLoader
|
||
|
||
|
||
class RapidOCRPDFLoader(UnstructuredFileLoader):
|
||
def _get_elements(self) -> List:
|
||
def pdf2text(filepath):
|
||
import fitz # pyMuPDF里面的fitz包，不要与pip install fitz混淆
|
||
from rapidocr_onnxruntime import RapidOCR
|
||
import numpy as np
|
||
ocr = RapidOCR()
|
||
doc = fitz.open(filepath)
|
||
resp = ""
|
||
for page in doc:
|
||
# TODO: 依据文本与图片顺序调整处理方式
|
||
text = page.get_text("")
|
||
resp += text + "\n"
|
||
|
||
img_list = page.get_images()
|
||
for img in img_list:
|
||
pix = fitz.Pixmap(doc, img[0])
|
||
img_array = np.frombuffer(pix.samples, dtype=np.uint8).reshape(pix.height, pix.width, -1)
|
||
result, _ = ocr(img_array)
|
||
if result:
|
||
ocr_result = [line[1] for line in result]
|
||
resp += "\n".join(ocr_result)
|
||
return resp
|
||
|
||
text = pdf2text(self.file_path)
|
||
from unstructured.partition.text import partition_text
|
||
return partition_text(text=text, **self.unstructured_kwargs)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
loader = RapidOCRPDFLoader(file_path="../tests/samples/ocr_test.pdf")
|
||
docs = loader.load()
|
||
print(docs)
|