Read pdf file horizontally with pdfminer
I would like to extract the pdf from pdfminer
(version 20140328).
This is the code to extract the pdf:
import sys
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFPage
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.layout import LAParams
from cStringIO import StringIO
import urllib2
def pdf_to_string(data):
fp = StringIO(data)
rsrcmgr = PDFResourceManager()
retstr = StringIO()
codec = 'utf-8'
laparams = LAParams()
device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
# Create a PDF interpreter object.
interpreter = PDFPageInterpreter(rsrcmgr, device)
# Process each page contained in the document.
for page in PDFPage.get_pages(fp):
interpreter.process_page(page)
data = retstr.getvalue()
return data
pdf_url="http://www.consilium.europa.eu/uedocs/cms_data/docs/pressdata/en/ecofin/140836.pdf"
file_object = urllib2.urlopen(urllib2.Request(pdf_url)).read()
string=pdf_to_string(file_object)
This is a pdf screenshot:
The problem is pdfminer
not reading it horizontally (person's position then), but in columns (all faces, i.e. all their respective positions):
Belgium:
Mr Koen GEENS
Bulgaria:
Mr Petar CHOBANOV
Czech Republic:
Mr Radek URBAN
Minister for Finance, with responsibility for the Civil
Service
Minister for Finance
Deputy Minister for Finance
How do I make the pdfminer
text read horizontally?
+3
source to share
1 answer
I found a working solution with : pdftotext
import tempfile, subprocess
def pdf_to_string(file_object):
pdfData = file_object.read()
tf = tempfile.NamedTemporaryFile()
tf.write(pdfData)
tf.seek(0)
outputTf = tempfile.NamedTemporaryFile()
if (len(pdfData) > 0) :
out, err = subprocess.Popen(["pdftotext", "-layout", tf.name, outputTf.name ]).communicate()
return outputTf.read()
else :
return None
pdf_file="files/2014_1.pdf"
file_object = file(pdf_file, 'rb')
print pdf_to_string(file_object)
This gives the correct result, people's names are then positioned :).
Resolved!
0
source to share