Python module for converting PDF to text
Try PDFMiner. It can extract text from PDF files as HTML, SGML or "Tagged PDF" format.
The Tagged PDF format seems to be the cleanest, and stripping out the XML tags leaves just the bare text.
A Python 3 version is available under:
- https://github.com/pdfminer/pdfminer.six
The PDFMiner package has changed since codeape posted.
EDIT (again):
PDFMiner has been updated again in version 20100213
You can check the version you have installed with the following:
>>> import pdfminer
>>> pdfminer.__version__
'20100213'
Here's the updated version (with comments on what I changed/added):
def pdf_to_csv(filename):
from cStringIO import StringIO #<-- added so you can copy/paste this to try it
from pdfminer.converter import LTTextItem, TextConverter
from pdfminer.pdfparser import PDFDocument, PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
class CsvConverter(TextConverter):
def __init__(self, *args, **kwargs):
TextConverter.__init__(self, *args, **kwargs)
def end_page(self, i):
from collections import defaultdict
lines = defaultdict(lambda : {})
for child in self.cur_item.objs:
if isinstance(child, LTTextItem):
(_,_,x,y) = child.bbox #<-- changed
line = lines[int(-y)]
line[x] = child.text.encode(self.codec) #<-- changed
for y in sorted(lines.keys()):
line = lines[y]
self.outfp.write(";".join(line[x] for x in sorted(line.keys())))
self.outfp.write("\n")
# ... the following part of the code is a remix of the
# convert() function in the pdfminer/tools/pdf2text module
rsrc = PDFResourceManager()
outfp = StringIO()
device = CsvConverter(rsrc, outfp, codec="utf-8") #<-- changed
# becuase my test documents are utf-8 (note: utf-8 is the default codec)
doc = PDFDocument()
fp = open(filename, 'rb')
parser = PDFParser(fp) #<-- changed
parser.set_document(doc) #<-- added
doc.set_parser(parser) #<-- added
doc.initialize('')
interpreter = PDFPageInterpreter(rsrc, device)
for i, page in enumerate(doc.get_pages()):
outfp.write("START PAGE %d\n" % i)
interpreter.process_page(page)
outfp.write("END PAGE %d\n" % i)
device.close()
fp.close()
return outfp.getvalue()
Edit (yet again):
Here is an update for the latest version in pypi, 20100619p1
. In short I replaced LTTextItem
with LTChar
and passed an instance of LAParams to the CsvConverter constructor.
def pdf_to_csv(filename):
from cStringIO import StringIO
from pdfminer.converter import LTChar, TextConverter #<-- changed
from pdfminer.layout import LAParams
from pdfminer.pdfparser import PDFDocument, PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
class CsvConverter(TextConverter):
def __init__(self, *args, **kwargs):
TextConverter.__init__(self, *args, **kwargs)
def end_page(self, i):
from collections import defaultdict
lines = defaultdict(lambda : {})
for child in self.cur_item.objs:
if isinstance(child, LTChar): #<-- changed
(_,_,x,y) = child.bbox
line = lines[int(-y)]
line[x] = child.text.encode(self.codec)
for y in sorted(lines.keys()):
line = lines[y]
self.outfp.write(";".join(line[x] for x in sorted(line.keys())))
self.outfp.write("\n")
# ... the following part of the code is a remix of the
# convert() function in the pdfminer/tools/pdf2text module
rsrc = PDFResourceManager()
outfp = StringIO()
device = CsvConverter(rsrc, outfp, codec="utf-8", laparams=LAParams()) #<-- changed
# becuase my test documents are utf-8 (note: utf-8 is the default codec)
doc = PDFDocument()
fp = open(filename, 'rb')
parser = PDFParser(fp)
parser.set_document(doc)
doc.set_parser(parser)
doc.initialize('')
interpreter = PDFPageInterpreter(rsrc, device)
for i, page in enumerate(doc.get_pages()):
outfp.write("START PAGE %d\n" % i)
if page is not None:
interpreter.process_page(page)
outfp.write("END PAGE %d\n" % i)
device.close()
fp.close()
return outfp.getvalue()
EDIT (one more time):
Updated for version 20110515
(thanks to Oeufcoque Penteano!):
def pdf_to_csv(filename):
from cStringIO import StringIO
from pdfminer.converter import LTChar, TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfparser import PDFDocument, PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
class CsvConverter(TextConverter):
def __init__(self, *args, **kwargs):
TextConverter.__init__(self, *args, **kwargs)
def end_page(self, i):
from collections import defaultdict
lines = defaultdict(lambda : {})
for child in self.cur_item._objs: #<-- changed
if isinstance(child, LTChar):
(_,_,x,y) = child.bbox
line = lines[int(-y)]
line[x] = child._text.encode(self.codec) #<-- changed
for y in sorted(lines.keys()):
line = lines[y]
self.outfp.write(";".join(line[x] for x in sorted(line.keys())))
self.outfp.write("\n")
# ... the following part of the code is a remix of the
# convert() function in the pdfminer/tools/pdf2text module
rsrc = PDFResourceManager()
outfp = StringIO()
device = CsvConverter(rsrc, outfp, codec="utf-8", laparams=LAParams())
# becuase my test documents are utf-8 (note: utf-8 is the default codec)
doc = PDFDocument()
fp = open(filename, 'rb')
parser = PDFParser(fp)
parser.set_document(doc)
doc.set_parser(parser)
doc.initialize('')
interpreter = PDFPageInterpreter(rsrc, device)
for i, page in enumerate(doc.get_pages()):
outfp.write("START PAGE %d\n" % i)
if page is not None:
interpreter.process_page(page)
outfp.write("END PAGE %d\n" % i)
device.close()
fp.close()
return outfp.getvalue()
Since none for these solutions support the latest version of PDFMiner I wrote a simple solution that will return text of a pdf using PDFMiner. This will work for those who are getting import errors with process_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
def pdfparser(data):
fp = file(data, 'rb')
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()
print data
if __name__ == '__main__':
pdfparser(sys.argv[1])
See below code that works for Python 3:
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
import io
def pdfparser(data):
fp = open(data, 'rb')
rsrcmgr = PDFResourceManager()
retstr = io.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()
print(data)
if __name__ == '__main__':
pdfparser(sys.argv[1])