使用pdfminer
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from io import BytesIO
def convert_pdf_to_txt(path):
rsrcmgr = PDFResourceManager()
retstr = BytesIO()
codec = 'utf-8'
laparams = LAParams()
device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
fp = open(path, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
password = ""
maxpages = 0
caching = True
pagenos=set()
for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,caching=caching, check_extractable=True):
interpreter.process_page(page)
text = retstr.getvalue()
fp.close()
device.close()
retstr.close()
return text
使用PyPDF2
^{pr2}$但是即使在尝试了两个api之后,我还是得到了pdf的harcoded值,但没有在空框中的值,而空框是pdf的可编辑部分?在
示例:-船舶名称:salil
我能读懂“船名”,但我得到的不是salil,而是“空字符串”。关键是要能读懂萨利尔。在
下面是我想解析的pdf文件,请帮忙。在
目前没有回答
相关问题 更多 >
编程相关推荐