import pdfplumber import pandas as pd from PIL import Image ##加载带密码的pdf需要传入参数password, ##例如:pdfplumber.open("file.pdf", password = "test") pdf = pdfplumber.open("daan.pdf") #Load page_0 #读取表格 p0 = pdf.pages[0] table = p0.extract_table() ##df = pd.DataFrame(table[1:], columns=table[0]) ##print(df.infer_objects) ##for column in ["Effective", "Received"]: ## df[column] = df[column].str.replace(" ", "") #读取PDF文件每页内容 with pdfplumber.open("daan.pdf") as pdf: # 读取每一页 for page in pdf.pages: page_text = page.extract_text() print(page_text) #提取图片 page=pdf.pages[0] for image in page.images: imgag1=image.get_image_content()