Reputation: 807
I've tried to manipulate the 'word_margin' with python using the following code but it throws me an error TypeError: get_pages() got an unexpected keyword argument 'word_margin'
. PDFminer reads the document fine if I remove the word_margin=word_margin
from the arguments.
Code:
def convert_pdf_to_txt(path):
rsrcmgr = PDFResourceManager()
retstr = StringIO()
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()
word_margin = 1
for page in PDFPage.get_pages(fp, pagenos, word_margin=word_margin,maxpages=maxpages,password=password,caching=caching, check_extractable=True):
interpreter.process_page(page)
text = retstr.getvalue()
fp.close()
device.close()
retstr.close()
return text
Upvotes: 2
Views: 1961
Reputation: 9937
word_margin
is a parameter of LAParams
class. If I understand correctly, the code should look like this:
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.layout import LAParams
from pdfminer.converter import TextConverter
from StringIO import StringIO
def convert_pdf_to_txt(path):
rsrcmgr = PDFResourceManager()
retstr = StringIO()
codec = 'utf-8'
word_margin = 1
laparams = LAParams(word_margin=word_margin)
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
Upvotes: 1