python爬取pdf内容_如何利用Python抓取PDF中的某些内容

展开全部

可以转2113换成5261TXT再抓4102取1653from cStringIO import StringIO

from pdfminer.pdfinterp

import PDFResourceManager, PDFPageInterpreter

from pdfminer.converter import TextConverter

from pdfminer.layout import LAParamsfrom pdfminer.pdfpage

import PDFPage

def convert_pdf_2_text(path):

rsrcmgr = PDFResourceManager()

retstr = StringIO()

device = TextConverter(rsrcmgr, retstr, codec='utf-8', laparams=LAParams())

interpreter = PDFPageInterpreter(rsrcmgr, device)

with open(path, 'rb') as fp:

for page in PDFPage.get_pages(fp, set()):

interpreter.process_page(page)

text = retstr.getvalue()

device.close()

retstr.close()

return text