用PDFMiner從PDF中提取文本文字

1、下載並安裝PDFMiner

　　從https://pypi.python.org/pypi/pdfminer/下載PDFMineer

wget https://pypi.python.org/packages/57/4f/e1df0437858188d2d36466a7bb89aa024d252bd0b7e3ba90cbc567c6c0b8/pdfminer-20140328.tar.gz#md5=dfe3eb1b7b7017ab514aad6751a7c2ea

　　加壓並安裝

tar -zxvf pdfminer-20140328.tar.gz
cd pdfminer-20140328/
make cmap　　#防止中文亂碼，否則處理中文會出現一大堆（CID:xxx）
sudo python setup.py install

2、提取文本文字

from cStringIO import StringIO
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
import sys
import string

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

text = convert_pdf_2_text(sys.argv[1])
open('real?.txt','wb').write(text)

3、測試結果

 

【1】http://www.unixuser.org/~euske/python/pdfminer/#source

【2】https://www.zhihu.com/question/31586273