MacBook M2运行Camelot提取PDF表格遇Ghostscript依赖错误

问题场景 #

在MacBook M2设备上，因Tabula无法提取PDF全页文本，转而使用Camelot处理PDF表格，运行时触发Ghostscript相关错误。

错误日志 #

Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/camelot/ext/ghostscript/_gsprint.py", line 260, in <module>
    libgs = cdll.LoadLibrary("libgs.so")
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/ctypes/__init__.py", line 454, in LoadLibrary
    return self._dlltype(name)
           ^^^^^^^^^^^^^^^^^^^
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/ctypes/__init__.py", line 376, in __init__
    self._handle = _dlopen(self._name, mode)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^
OSError: dlopen(libgs.so, 0x0006): tried: 'libgs.so' (no such file), '/System/Volumes/Preboot/Cryptexes/OSlibgs.so' (no such file), '/usr/lib/libgs.so' (no such file, not in dyld cache), 'libgs.so' (no such file), '/usr/lib/libgs.so' (no such file, not in dyld cache)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/Users/xxx/Desktop/xx/test.py", line 117, in <module>
    extracted_data =  extract_pdf_camelot()
                      ^^^^^^^^^^^^^^^^^^^^^
  File "/Users/xxx/Desktop/xx/test.py", line 106, in extract_pdf_camelot
    tables = camelot.read_pdf(pdf_path)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/camelot/io.py", line 113, in read_pdf
    tables = p.parse(
             ^^^^^^^^
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/camelot/handlers.py", line 173, in parse
    t = parser.extract_tables(
        ^^^^^^^^^^^^^^^^^^^^^^
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/camelot/parsers/lattice.py", line 402, in extract_tables
    self._generate_image()
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/camelot/parsers/lattice.py", line 211, in _generate_image
    from ..ext.ghostscript import Ghostscript
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/camelot/ext/ghostscript/__init__.py", line 24, in <module>
    from . import _gsprint as gs
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/camelot/ext/ghostscript/_gsprint.py", line 267, in <module>
    raise RuntimeError("Please make sure that Ghostscript is installed")
RuntimeError: Please make sure that Ghostscript is installed

运行代码 #

import os
import sys
import PyPDF2
from openpyxl import Workbook
import os
import PyPDF2
import tabula
import pandas as pd
from openpyxl import load_workbook
import camelot


pdf_paths =[]
BatchList = []
university = "xx"
college = "xx"
Batch= "2022"
# Program / Degree:row[3]
# Roll No,.:row[1]
# Name:row[2]
# Branch:row[4]
file_add="xxx"
univ_res = "https://convocation.ccc.ac.in/index.php/convocation/Information_page/degree_recipients"

shet = "Batch:" + Batchexcel_path = 'ExcelDatabase/Ix.xlsx'
tracker_path = "ExcelDatabase/tracker.xlsx"



def extract_pdf_data_tabula(pdf_path):# Specify the path to the main folder
    main_folder_path = "./EducationDatabase2/xxC"
    df_list = []
    for root, dirs, files in os.walk(main_folder_path):
     if len(dirs) > 0:
        for no, dir in enumerate(dirs, start =1):
         if no==1:continue
         for filename in os.listdir(main_folder_path+'/'+dir):
            if filename.endswith(".pdf"):
                print(filename)
                pdf_path =  main_folder_path+'/'+dir + '/'+ filename
                batch=""
                batch+=dir[len(dir)-1]
                batch+=dir[len(dir)-2]
                batch+=dir[len(dir)-3]
                batch+=dir[len(dir)-4]
                batch  =  batch[::-1]
                BatchList.append(batch)
                with open(pdf_path, "rb") as pdf_file:
                    pdf_paths.append(pdf_path)
                    readpdf = PyPDF2.PdfReader(pdf_file)
                    totalpages = len(readpdf.pages)
                    df_list.extend( tabula.read_pdf(pdf_path, pages='1-32',stream=True, lattice=True, guess=False, multiple_tables=True))
                    # df_list[len(df_list)-1].dropna(subset=['Discipline'], inplace=True)
                    # print(batch)
                    # print(df_list[len(df_list)-1])
                    # print()
                    return df_list
                    sys.exit(1)


def save_data_to_excel(data, excel_path):
    cnt =2
    # workbook = load_workbook(excel_path)
    shet = "Batch_2022"
    # sheet = workbook[shet]
    for no, df in enumerate(data, start = 1):
        print("Dataframe:", no)
        df2=df.dropna(axis=1)
        # df2=df.dropna(axis=1,thresh=0)
        print(df2.head(1))
        print()
    #     for i in range(len(df)):
    #         row =  df.iloc[i].to_list()
    #         sno =  str(cnt+1)
    #         row =  [university, college, Batch, row[3], row[1], row[2], row[4], file_add,univ_res ]
    #         for i in range(len(row)):
    #           sheet.cell(row= cnt+1, column = i+1).value = row[i]
    #         cnt+=1
    # workbook.save(excel_path)



def extract_pdf_camelot():
    main_folder_path = "./EducationDatabase2/Indian Institute of Technology - Guwahati"
    df_list = []
    for root, dirs, files in os.walk(main_folder_path):
     if len(dirs) > 0:
        for no, dir in enumerate(dirs, start =1):
         if no==1:continue
         for filename in os.listdir(main_folder_path+'/'+dir):
            if filename.endswith(".pdf"):
                print(filename)
                pdf_path =  main_folder_path+'/'+dir + '/'+ filename
                batch=""
                batch+=dir[len(dir)-1]
                batch+=dir[len(dir)-2]
                batch+=dir[len(dir)-3]
                batch+=dir[len(dir)-4]
                batch  =  batch[::-1]
                BatchList.append(batch)
                # extract all the tables in the PDF file
                tables = camelot.read_pdf(pdf_path)
                cntdf =0
                for table in tables:
                   print("Df no:", cntdf+1)
                   df_list.append(table.df)
                   print(table.df.head(2))
                return 



# extracted_data = extract_pdf_data_tabula(pdf_path)
extracted_data =  extract_pdf_camelot()
cnt =2
save_data_to_excel(extracted_data, excel_path)

已尝试无效方案 #

• 通过pip3 install ghostscript==0.7安装Python的ghostscript库
• 从Ghostscript官网下载源码包手动编译安装
• 查阅GitHub及Stack Overflow相关问题未找到适配M2的有效方案

适配MacBook M2的解决步骤 #

1. 清理现有安装

   • 卸载Python的ghostscript库：pip3 uninstall -y ghostscript
   • 删除源码安装的Ghostscript文件（若有），默认安装路径为/usr/local，可直接删除相关文件夹

2. 用Homebrew安装Ghostscript

   • 确保已安装Homebrew，未安装则先完成Homebrew安装
   • 执行安装命令：brew install ghostscript

3. 验证安装

   • 终端执行gs --version，能正常输出版本号则安装成功

4. 创建软链接让Camelot找到库文件
   MacBook M2为ARM架构，Homebrew安装的libgs路径为/opt/homebrew/lib/libgs.dylib，而Camelot默认查找Linux风格的libgs.so，因此创建软链接：

   sudo ln -s /opt/homebrew/lib/libgs.dylib /usr/local/lib/libgs.so
   

   （Intel Mac的libgs路径为/usr/local/lib/libgs.dylib，对应软链接命令为sudo ln -s /usr/local/lib/libgs.dylib /usr/local/lib/libgs.so）

5. 测试代码
   重新运行Camelot处理代码，错误即可消除，可正常提取PDF表格。

内容的提问来源于stack exchange，提问作者MAYANK GARG