29 lines
873 B
Python
29 lines
873 B
Python
import fitz # PyMuPDF
|
|
|
|
def extract_answers_from_pdf(pdf_file):
|
|
# 打开PDF文件
|
|
doc = fitz.open(pdf_file)
|
|
answers = []
|
|
|
|
# 遍历每一页
|
|
for page in doc:
|
|
# 提取当前页的文本
|
|
text = page.get_text()
|
|
# 分割文本为行
|
|
lines = text.split('\n')
|
|
for line in lines:
|
|
if line.strip(): # 排除空白行
|
|
# 分割等号，提取答案
|
|
parts = line.split('=')
|
|
if len(parts) > 1:
|
|
answer = parts[-1].strip() # 取等号后的部分为答案
|
|
answers.append(answer)
|
|
|
|
return answers
|
|
|
|
# 假设你的文件名是'math_problems.pdf'
|
|
pdf_file = '/Users/lxc/Desktop/calculus.pdf'
|
|
answers = extract_answers_from_pdf(pdf_file)
|
|
for i, answer in enumerate(answers, 1):
|
|
print(f"题目{i}的答案是: {answer}")
|