目录
一、PyMuPDF
1.安装PyMuPDF
pip install pymupdf
2.pdf转txt样例
import os
import datetime
import fitz # fitz就是pip install PyMuPDF
def pyMuPDF_fitz(pdfPath):
startTime_pdf2img = datetime.datetime.now() # 开始时间
text_list = []
pdfDoc = fitz.open(pdfPath)
for page in pdfDoc:
text = page.get_text()
text_list.append(text)
text_list = "\n".join(text_list)
try:
with open("/home/bingxing2/ailab/group/ai4agr/wzf/LLM/txt/test.txt", 'a+') as neirong:
neirong.write(text_list)
except IOError as e:
print("An error occurred while writing the file:", e)
endTime_pdf2img = datetime.datetime.now() # 结束时间
print('pdf2img时间=', (endTime_pdf2img - startTime_pdf2img).seconds)
def process_all_pdfs_in_directory(directory):
for filename in os.listdir(directory):
if filename.endswith('.pdf'):
pdf_path = os.path.join(directory, filename)
pyMuPDF_fitz(pdf_path)
if __name__ == "__main__":
# 指定PDF所在的目录
pdf_directory = r'/home/bingxing2/ailab/group/ai4agr/wzf/LLM/pdf/'
process_all_pdfs_in_directory(pdf_directory)
注:
pymupdf不能直接提取表格,要使用pdfplumber来实现
提取图片使用img=page.getImageList()
提取后发现,文字可以正常提取但是数字不能正常提取
原因:数字在PDF文件中以图像形式呈现,而不是文本形式。这种情况下,提取数字就需要进行OCR(光学字符识别)处理
因此先将pdf转为图片,在对图片提取文字(采用cnocr、paddleocr、tesseract)
pdf转图片:
import os
import datetime
import fitz # fitz就是pip install PyMuPDF
def pdf_to_images(directory, filename, output_folder):
pdf_path = os.path.join(directory, filename)
pdf_doc = fitz.open(pdf_path)
for page_number in range(len(pdf_doc)):
page = pdf_doc[page_number]
image = page.get_pixmap(matrix=fitz.Matrix(4, 4), alpha=False)
image_path = os.path.join(output_folder, f"{filename[:-4]}_page_{page_number + 1}.png")
image.save(image_path)
pdf_doc.close()
def process_all_pdfs_in_directory(directory, output_folder):
#pdf to img
for filename in os.listdir(directory):
if filename.endswith('.pdf'):
pdf_to_images(directory, filename, output_folder)
if __name__ == "__main__":
# 指定PDF所在的目录
pdf_directory = r'/home/bingxing2/ailab/group/ai4agr/wzf/LLM/pdf/books/'
# 指定输出图片的目录
output_folder = r'/home/bingxing2/ailab/group/ai4agr/wzf/LLM/images/books/'
process_all_pdfs_in_directory(pdf_directory, output_folder)
二、CNOCR
1.安装cnocr
pip install cnocr
2.图片转文字,存入同一个txt文件
import cnocr
import os
import datetime
def recognize_text(txt_directory, image_directory):
# 初始化 cnocr
ocr = cnocr.CnOcr()
text = []
for filename in os.listdir(image_directory):
if filename.endswith('.png'):
startTime_pdf2img = datetime.datetime.now() # 开始时间
image_path = os.path.join(image_directory, filename)
# 读取图片并识别文字
results = ocr.ocr(image_path)
# text = [result['text'] for result in results]
text = ''.join([result['text'].replace('\n', '') for result in results])
# print(text)
# sys
# 读取一张写入一张
with open(txt_directory, 'a+', encoding='utf-8') as f:
f.write(text + '\n')
endTime_pdf2img = datetime.datetime.now() # 结束时间
print('img2txt时间 =', (endTime_pdf2img - startTime_pdf2img).seconds, ",", filename, "已写入")
return text
if __name__ == "__main__":
# 图片文件路径
image_directory = '/home/bingxing2/ailab/group/ai4agr/wzf/LLM/images/books'
# txt文件路径
txt_directory = "/home/bingxing2/ailab/group/ai4agr/wzf/LLM/txt/test.txt"
# 识别文字
recognize_text(txt_directory, image_directory)
三、PaddleOCR
步骤:
1.安装PaddleOCR
2.准备pdf文件
3.将pdf转为图片,在对图片提取文字
安装:
1.安装PaddleOCR
pip install "paddleocr>=2.0.1"
2.安装paddlepaddle (默认安装cpu版本,gpu版本目前似乎不支持arm64架构?安装指南-使用文档-PaddlePaddle深度学习平台)
gpu版本安装官网:开始使用_飞桨-源于产业实践的开源深度学习平台
pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple
验证paddlepaddle是否安装成功
进入python环境验证paddle是否安装成功
python
import paddle
paddle.utils.run_check()
-
图片转文字,存入同一个txt文件
import paddleocr
import os
import datetime
import fitzdef recognize_text(txt_directory, image_directory, pdf_directory):
# 初始化 PaddleOCR
ocr = paddleocr.PaddleOCR(use_angle_cls=True, lang='ch')for filename in os.listdir(pdf_directory): if filename.endswith('.pdf'): pdf_path = os.path.join(pdf_directory, filename) pdf_doc = fitz.open(pdf_path) for page_number in range(len(pdf_doc)): image_path = os.path.join(image_directory, f"{filename[:-4]}_page_{page_number + 1}.png") startTime_pdf2img = datetime.datetime.now() # 开始时间 # 读取图片并识别文字 results = ocr.ocr(image_path, cls=True) text = ''.join([result[1][0] for result in results[0]]) # print(text) # 写入识别结果到文本文件 with open(txt_directory, 'a+', encoding='utf-8') as f: f.write(text + '\n') endTime_pdf2img = datetime.datetime.now() # 结束时间 print('img2txt时间 =', (endTime_pdf2img - startTime_pdf2img).seconds, ",", f"{filename[:-4]}_page_{page_number + 1}.png", "已写入")
if name == "main":
# 图片文件路径
image_directory = '/home/bingxing2/ailab/group/ai4agr/wzf/LLM/images/books'
# txt文件路径
txt_directory = "/home/bingxing2/ailab/group/ai4agr/wzf/LLM/txt/testpaddlepaddleocr.txt"
# 指定PDF所在的目录
pdf_directory = '/home/bingxing2/ailab/group/ai4agr/wzf/LLM/pdf/books/'
# 识别文字
recognize_text(txt_directory, image_directory, pdf_directory)
4.报错:
from paddleocr import PaddleOCR
import re
ocr = PaddleOCR(lang="ch") # 使用中文识别
result = ocr.ocr("/home/bingxing2/ailab/group/ai4agr/wzf/LLM/images/page_1.png")
for line in result:(myenv) [scxlab0069@paraai-n32-h-01-ccs-master-1 wzf]$ python /home/bingxing2/ailab/group/ai4agr/wzf/LLM/ocr/paddleocr/img_to_txt.py
download https://paddleocr.bj.bcebos.com/PP-OCRv4/chinese/ch_PP-OCRv4_det_infer.tar to /home/bingxing2/ailab/scxlab0069/.paddleocr/whl/det/ch/ch_PP-OCRv4_det_infer/ch_PP-OCRv4_det_infer.tar
100%|███████████████████████████████████████████████████████████████████████| 4.89M/4.89M [00:00<00:00, 13.9MiB/s]
--------------------------------------
C++ Traceback (most recent call last):
--------------------------------------
0 inflateReset2
----------------------
Error Message Summary:
----------------------
FatalError: `Segmentation fault` is detected by the operating system.
[TimeInfo: *** Aborted at 1715233076 (unix time) try "date -d @1715233076" if you are using GNU date ***]
[SignalInfo: *** SIGSEGV (@0x4ad7b62366b7a28) received by PID 4127064 (TID 0x40000b615370) from PID 913013288 ***]
Segmentation fault
print(line) # 输出识别结果 报错
解决办法:paddlepaddle2.6版本太高了,重新安装paddlepaddle2.5.2版本 即可, 参考CPU版本下的报错信息:`Segmentation fault` is detected by the operating system · Issue #12075 · PaddlePaddle/PaddleOCR · GitHub
四、Tesseract(没试)
1.安装依赖
> yum install autoconf automake libtool libjpeg-devel libpng-devel libtiff-devel zlib-devel make
报错,没限权。改为pip,报错。原因:libjpeg-devel
、libpng-devel
、libtiff-devel
和 zlib-devel
这些包通常是系统软件包管理器(如 yum)提供的,而不是通过 Python 包管理器(如 pip)安装的。它们是用于开发和编译过程中的依赖库,不是 Python 包。
2.安装依赖的Leptonica库
wget https://github.com/DanBloomberg/leptonica/releases/download/1.80.0/leptonica-1.80.0.tar.gz
tar -xzvf leptonica-1.80.0.tar.gz
cd leptonica-1.80.0
./configure --prefix=/home/tess4j/leptonica-1.80.0 && make && make install
3,将 Leptonica加入环境变量
vim /etc/profile
插入
export LD_LIBRARY_PATH=$LD_LIBRARY_PAYT:/home/tess4j/leptonica-1.80.0/lib
export LIBLEPT_HEADERSDIR=/home/tess4j/leptonica-1.80.0/include
export PKG_CONFIG_PATH=/home/tess4j/leptonica-1.80.0/lib/pkgconfig
退出后让配置生效
source /etc/profile
4.安装Tesseract-OCR
wget https://github.com/tesseract-ocr/tesseract/archive/refs/tags/4.1.1.tar.gz
重名名下压缩包
mv 4.1.1.tar.gz tesseract-4.1.1.tar.gz
tar -xzvf tesseract-4.1.1.tar.gz
cd tesseract-4.1.1/
./autogen.sh
./configure --prefix=/home/tess4j/tesseract-4.1.1 && make && make install
sudo ldconfig
5.配置Tesseract环境变量
vim /etc/profile
PATH=$PATH:/home/tess4j/tesseract-4.1.1/bin
export PATH
export TESSDATA_PREFIX=/home/temp/tessData ##注意:该位置是训练库所在文件目录
export PATH=$PATH:$TESSDATA_PREFIX
source /etc/profile
6.测试安装是否成功
tesseract --version
7.测试
识别图片命令
tesseract 567.png outputteee -l chi_sim+eng
参数说明
tesseract = 命令
567.png=当前目录文件
outputteee=会在当前目录生成outputteee.txt文件
-l chi_sim+eng=中文+英文,如果是单个语言-l chi_sim就可以了
参考:
Linux 最全安装Tesseract_linux安装tesseract-CSDN博客
参考:
PaddleOCR---图片文字识别提取---快速使用教程_paddleocr使用教程-CSDN博客
Paddlepaddle-GPU版本安装_paddlepaddle-gpu 安装版本-CSDN博客
【paddle-gpu2.5版本安装踩坑记录】_paddle2.5-CSDN博客