我已经编写了从 PDF 文件中抓取所有数据的 python 代码。这里的问题是,一旦被刮掉,单词就会失去语法。如何解决这些问题?我附上代码。
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from cStringIO import StringIO
def convert_pdf_to_txt(path):
rsrcmgr = PDFResourceManager()
retstr = StringIO()
codec = 'utf-8'
laparams = LAParams()
device = TextConverter(rsrcmgr, retstr, codec=codec,laparams=laparams)
with open(path, 'rb') as fp:
interpreter = PDFPageInterpreter(rsrcmgr, device)
password = ""
caching = True
pagenos = set()
for page in PDFPage.get_pages(fp, pagenos, password=password,caching=caching, check_extractable=True):
interpreter.process_page(page)
text = retstr.getvalue()
device.close()
retstr.close()
return text
print convert_pdf_to_txt("S24A276P001.pdf")