python 读取pdf文本_python pdfminer 读取pdf文本内容

#pip3 install pdfminer tabula-py

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter

from pdfminer.converter import TextConverter

from pdfminer.layout import LAParams

from pdfminer.pdfpage import PDFPage

from io import StringIO

import tabula

def file(path,type):

return open(path,type)

def convert_pdf_to_txt(path,save_name):

rsrcmgr = PDFResourceManager()

retstr = StringIO()

codec = 'utf-8'

laparams = LAParams()

device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)

fp = file(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)

fp.close()

device.close()

str = retstr.getvalue()

retstr.close()

print(str)

# try:

# with open("%s"%save_name,"w") as f:#格式化字符串还能这么用！

# for i in str:

# f.write(i)

# print "%s Writing Succeed!"%save_name

# except:

# print "Writing Failed!"

#convert_pdf_to_txt('C:\\pdf-2020-10-9\\600030_20201009_1_中信证券2020年9月证券变动月报表.pdf',"c.txt")