问题
I am trying to get text data from a pdf using pdfminer. I am able to extract this data to a .txt file successfully with the pdfminer command line tool pdf2txt.py. I currently do this and then use a python script to clean up the .txt file. I would like to incorporate the pdf extract process into the script and save myself a step.
I thought I was on to something when I found this link, but I didn\'t have success with any of the solutions. Perhaps the function listed there needs to be updated again because I am using a newer version of pdfminer.
I also tried the function shown here, but it also did not work.
Another approach I tried was to call the script within a script using os.system. This was also unsuccessful.
I am using Python version 2.7.1 and pdfminer version 20110227.
回答1:
Here is a cleaned up version I finally produced that worked for me. The following just simply returns the string in a PDF, given its filename. I hope this saves someone time.
from pdfminer.pdfinterp import PDFResourceManager, process_pdf
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from cStringIO import StringIO
def convert_pdf(path):
rsrcmgr = PDFResourceManager()
retstr = StringIO()
codec = 'utf-8'
laparams = LAParams()
device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
fp = file(path, 'rb')
process_pdf(rsrcmgr, device, fp)
fp.close()
device.close()
str = retstr.getvalue()
retstr.close()
return str
This solution was valid until API changes in November 2013.
回答2:
Here is a new solution that works with the latest version:
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from cStringIO import StringIO
def convert_pdf_to_txt(path):
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()
return str
回答3:
I know it is poor taste to answer your own question, but I think I may have figured this out and I don't want anyone else to waste their time looking for a solution to my problem.
I followed the suggestion in a one of the links posted in my question and re-purposed the current pdf2txt.py script included with pdfminer. Here is the function in case it is useful to anyone else. Thanks to the user skyl for posting that answer, all I had to to was make a couple of changes to make it work with the current version of pdfminer.
This function take a pdf and creates a .txt file in the same directory with the same name.
def convert_pdf(path, outtype='txt', opts={}):
import sys
from pdfminer.pdfparser import PDFDocument, PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, process_pdf
from pdfminer.pdfdevice import PDFDevice, TagExtractor
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.cmapdb import CMapDB
from pdfminer.layout import LAParams
import getopt
outfile = path[:-3] + outtype
outdir = '/'.join(path.split('/')[:-1])
# debug option
debug = 0
# input option
password = ''
pagenos = set()
maxpages = 0
# output option
# ?outfile = None
# ?outtype = None
outdir = None
#layoutmode = 'normal'
codec = 'utf-8'
pageno = 1
scale = 1
showpageno = True
laparams = LAParams()
for (k, v) in opts:
if k == '-d': debug += 1
elif k == '-p': pagenos.update( int(x)-1 for x in v.split(',') )
elif k == '-m': maxpages = int(v)
elif k == '-P': password = v
elif k == '-o': outfile = v
elif k == '-n': laparams = None
elif k == '-A': laparams.all_texts = True
elif k == '-V': laparams.detect_vertical = True
elif k == '-M': laparams.char_margin = float(v)
elif k == '-L': laparams.line_margin = float(v)
elif k == '-W': laparams.word_margin = float(v)
elif k == '-F': laparams.boxes_flow = float(v)
elif k == '-Y': layoutmode = v
elif k == '-O': outdir = v
elif k == '-t': outtype = v
elif k == '-c': codec = v
elif k == '-s': scale = float(v)
#
#PDFDocument.debug = debug
#PDFParser.debug = debug
CMapDB.debug = debug
PDFResourceManager.debug = debug
PDFPageInterpreter.debug = debug
PDFDevice.debug = debug
#
rsrcmgr = PDFResourceManager()
outtype = 'text'
if outfile:
outfp = file(outfile, 'w')
else:
outfp = sys.stdout
device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams)
fp = file(path, 'rb')
process_pdf(rsrcmgr, device, fp, pagenos, maxpages=maxpages, password=password,
check_extractable=True)
fp.close()
device.close()
outfp.close()
return
回答4:
This worked for me using the most recent version of pdfminer (as of September 2014):
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfpage import PDFTextExtractionNotAllowed
from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
import unicodedata, codecs
from io import StringIO
def getPDFText(pdfFilenamePath):
retstr = StringIO()
parser = PDFParser(open(pdfFilenamePath,'r'))
try:
document = PDFDocument(parser)
except Exception as e:
print(pdfFilenamePath,'is not a readable pdf')
return ''
if document.is_extractable:
rsrcmgr = PDFResourceManager()
device = TextConverter(rsrcmgr,retstr, codec='ascii' , laparams = LAParams())
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.create_pages(document):
interpreter.process_page(page)
return retstr.getvalue()
else:
print(pdfFilenamePath,"Warning: could not extract text from pdf file.")
return ''
if __name__ == '__main__':
words = getPDFText(path)
回答5:
Here's my solution
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 os
def convert_pdf_to_txt(path, pages=None):
if not pages:
pagenums = set()
else:
pagenums = set(pages)
output = StringIO()
manager = PDFResourceManager()
converter = TextConverter(manager, output, laparams=LAParams())
interpreter = PDFPageInterpreter(manager, converter)
infile = open(path, 'rb')
for page in PDFPage.get_pages(infile, pagenums):
interpreter.process_page(page)
infile.close()
converter.close()
text = output.getvalue()
output.close()
return text
For example you just want to read the first 3 pages of a pdf file:
text = convert('../Data/EN-FINAL Table 9.pdf', pages=[0,1,2])
pdfminer.six==20160614
python: 3.x
回答6:
The following modification of the non-process_pdf answers pulls the text straight from a URL string name and works with version 20140328 and Python 2.7:
from urllib2 import urlopen
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from cStringIO import StringIO
def convert_pdf_to_txt(url):
rsrcmgr = PDFResourceManager()
retstr = StringIO()
codec = 'utf-8'
laparams = LAParams()
device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
scrape = urlopen(url).read()
fp = StringIO(scrape)
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()
textstr = retstr.getvalue()
retstr.close()
return textstr
回答7:
If you are working with scraped data via urllib2, try this (which is developed and explained here):
def pdf_to_text(scraped_pdf_data):
from pdfminer.pdfinterp import PDFResourceManager, process_pdf
from pdfminer.pdfdevice import PDFDevice
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
import StringIO
fp = StringIO.StringIO()
fp.write(scraped_pdf_data)
fp.seek(0)
outfp = StringIO.StringIO()
rsrcmgr = PDFResourceManager()
device = TextConverter(rsrcmgr, outfp, laparams=LAParams())
process_pdf(rsrcmgr, device, fp)
device.close()
t = outfp.getvalue()
outfp.close()
fp.close()
return t
Like the other answers, the code here adapts the pdf2txt utility that PDFMiner itself provides. You can thus also convert to html or xml -- just sub HTMLConverter or XMLConverter for TextConverter everywhere above.
回答8:
The following code works for me with latest version of PDFMiner it takes path of pdf and return text in .txt format.
P.S: This is a modification of above answer.
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from cStringIO import StringIO
def convert_pdf_to_txt(path, outtype='txt'):
outfile = path[:-3] + outtype
rsrcmgr = PDFResourceManager()
codec = 'utf-8'
laparams = LAParams()
if outfile:
outfp = file(outfile, 'w')
else:
outfp = sys.stdout
device = TextConverter(rsrcmgr, outfp, 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()
outfp.close()
return
回答9:
just in case anyone still needs this, got it working with requests and python 3.4. thanks to @bahmait for his answer above :)
import requests
from io import StringIO
from pdfminer.pdfinterp import PDFResourceManager, process_pdf
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
def pdf_to_text(url=None):
text = None
pdf = requests.get(url)
if pdf.ok:
fp = StringIO(str(pdf.content, 'utf-8'))
outfp = StringIO()
rsrcmgr = PDFResourceManager()
device = TextConverter(rsrcmgr, outfp, laparams=LAParams())
process_pdf(rsrcmgr, device, fp)
device.close()
text = outfp.getvalue()
outfp.close()
fp.close()
return text
if __name__ == "__main__":
hello_world_text = pdf_to_text("https://bytebucket.org/hsoft/pdfminer3k/raw/28edfc91caed830674ca0b928f42571f7dee6091/samples/simple1.pdf")
no_pdf = pdf_to_text('http://www.google.com/404')
print(hello_world_text)
print(no_pdf)
回答10:
Here's an answer that works with pdfminer.six running python 3.6. It uses the pdfminer.high_level module that abstracts away a lot of the underlying detail if you just want to get out the raw text from a simple PDF file.
import pdfminer
import io
def extract_raw_text(pdf_filename):
output = io.StringIO()
laparams = pdfminer.layout.LAParams() # Using the defaults seems to work fine
with open(pdf_filename, "rb") as pdffile:
pdfminer.high_level.extract_text_to_fp(pdffile, output, laparams=laparams)
return output.getvalue()
回答11:
Here is a cleaned up version I finally produced that worked for me. The following just simply returns the string in a PDF, given its filename. I hope this saves someone time.
from pdfminer.pdfinterp import PDFResourceManager, process_pdf
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from cStringIO import StringIO
def convert_pdf(path):
rsrcmgr = PDFResourceManager()
retstr = StringIO()
codec = 'utf-8'
laparams = LAParams()
device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
fp = file(path, 'rb')
process_pdf(rsrcmgr, device, fp)
fp.close()
device.close()
str = retstr.getvalue()
retstr.close()
return str
can anybody say me : is there any specific place where the pdf file is to be placed??
回答12:
Only if someone still needs it: How to print the HTML from a PDF using PDFMiner:
import sys
import getopt
from Core.Interfaces.IReader import IReader
from pdfminer.pdfparser import PDFDocument, PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, process_pdf
from pdfminer.pdfdevice import PDFDevice, TagExtractor
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.cmapdb import CMapDB
from pdfminer.layout import LAParams
from cStringIO import StringIO
class PdfReader(object):
def __init__(self):
pass
def readText(self,path, outtype='text', opts={}):
outfile = path[:-3] + outtype
outdir = '/'.join(path.split('/')[:-1])
# debug option
debug = 0
# input option
password = ''
pagenos = set()
maxpages = 0
# output option
# ?outfile = None
# ?outtype = None
outdir = None
#layoutmode = 'normal'
codec = 'utf-8'
pageno = 1
scale = 1
showpageno = True
laparams = LAParams()
for (k, v) in opts:
if k == '-d': debug += 1
elif k == '-p': pagenos.update( int(x)-1 for x in v.split(',') )
elif k == '-m': maxpages = int(v)
elif k == '-P': password = v
elif k == '-o': outfile = v
elif k == '-n': laparams = None
elif k == '-A': laparams.all_texts = True
elif k == '-V': laparams.detect_vertical = True
elif k == '-M': laparams.char_margin = float(v)
elif k == '-L': laparams.line_margin = float(v)
elif k == '-W': laparams.word_margin = float(v)
elif k == '-F': laparams.boxes_flow = float(v)
elif k == '-Y': layoutmode = v
elif k == '-O': outdir = v
elif k == '-t': outtype = v
elif k == '-c': codec = v
elif k == '-s': scale = float(v)
print laparams
#
#PDFDocument.debug = debug
#PDFParser.debug = debug
CMapDB.debug = debug
PDFResourceManager.debug = debug
PDFPageInterpreter.debug = debug
PDFDevice.debug = debug
#
rsrcmgr = PDFResourceManager()
#outtype = 'text'
outfp = StringIO()
device = HTMLConverter(rsrcmgr, outfp, codec=codec, laparams=laparams)
fp = file(path, 'rb')
process_pdf(rsrcmgr, device, fp, pagenos, maxpages=maxpages, password=password,
check_extractable=True)
fp.close()
device.close()
print outfp.getvalue()
outfp.close()
return
reader = PdfReader()
opt = map(None,['-W','-L','-t'],[0.5,0.4,'html'])
reader.readText("/test_data/test.pdf","html",opt)
回答13:
This one worked for me in python 3. It requires the PDFMiner.six package
pip install pdfminer.six
The code is as follows (same code as everyone, with minor fixes):
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from six import StringIO
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()
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()
return str.replace("\\n","\n")
回答14:
The following code snippets is able to extract plain text from pdf documents using the latest version of pdfminer(as of 23-Mar-2016). Hope this helps.
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from cStringIO import StringIO
def convert_pdf_to_txt(path):
rsrcmgr = PDFResourceManager()
retstr = StringIO()
codec = 'utf-8'
laparams = LAParams()
device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
fp = file(path, 'rb')
parser = PDFParser(fp)
doc = PDFDocument(parser)
parser.set_document(doc)
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()
print text
return text
convert_pdf_to_txt(<path_of_the_pdf_file>)
来源：https://stackoverflow.com/questions/5725278/how-do-i-use-pdfminer-as-a-library