def getPDFReferencesTitle():
import sys
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice, TagExtractor
from pdfminer.pdfpage import PDFPage
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.cmapdb import CMapDB
from pdfminer.layout import LAParams
from pdfminer.image import ImageWriter
import re
import codecs
# debug option
debug = 0
# input option
password = ''
pagenos = set()
maxpages = 0
srcFile = "E:\\论文\\SNP\\学位论文\\基于Relief和SVM-RFE的组合式SNP特征选择.pdf".decode(
"utf8").encode("gbk")
# output option
outfile = "E:\\论文\\SNP\\学位论文\\基于Relief和SVM-RFE的组合式SNP特征选择.txt".decode(
"utf8").encode("gbk")
outtype = None
imagewriter = None
rotation = 0
layoutmode = 'normal'
codec = 'utf-8'
pageno = 1
scale = 1
caching = True
showpageno = True
laparams = LAParams()
#
PDFDocument.debug = debug
PDFParser.debug = debug
CMapDB.debug = debug
PDFResourceManager.debug = debug
PDFPageInterpreter.debug = debug
PDFDevice.debug = debug
#
rsrcmgr = PDFResourceManager(caching=caching)
if not outtype:
outtype = 'text'
if outfile:
if outfile.endswith('.htm') or outfile.endswith('.html'):
outtype = 'html'
elif outfile.endswith('.xml'):
outtype = 'xml'
elif outfile.endswith('.tag'):
outtype = 'tag'
if outfile:
outfp = file(outfile, 'w')
else:
outfp = sys.stdout
if outtype == 'text':
device = TextConverter(rsrcmgr,
outfp,
codec=codec,
laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'xml':
device = XMLConverter(rsrcmgr,
outfp,
codec=codec,
laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'html':
device = HTMLConverter(rsrcmgr,
outfp,
codec=codec,
scale=scale,
layoutmode=layoutmode,
laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'tag':
device = TagExtractor(rsrcmgr, outfp, codec=codec)
fp = file(srcFile, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.get_pages(fp,
pagenos,
maxpages=maxpages,
password=password,
caching=caching,
check_extractable=True):
page.rotate = (page.rotate + rotation) % 360
interpreter.process_page(page)
fp.close()
device.close()
outfp.close()
fp = open(outfile, "r")
data = fp.read()
fp.close()
if data[:3] == codecs.BOM_UTF8:
data = data[3:]
'''英文论文'''
position = find_last(data, "REFERENCES")
refstr = data[position + 10:]
#refstr = open("ref.txt", "r").read()
'''英文论文'''
references = re.split("\n\d+.", refstr)
'''中文论文'''
'''
position = find_last(data, "参考文献")
refstr = data[position + 13:]
references = re.split("\[\d+\]", refstr)
fp = open("ref.txt", "w")
fp.write(refstr)
fp.close()
'''
'''
for ref in references :
print ref.decode("utf8").encode("gbk")
print "\n"
print len(references)
'''
fp = open("title.txt", "w")
num = 0
for ref in references:
'''
str = ref.split(".")
if len(str) > 1 :
str[1] = str[1].replace("\n", " ")
str[1] = re.subn("\[\w\]", "", str[1])
fp.write(str[1][0].strip())
fp.write("\n")
#num += 1
'''
str = re.split("\(\d+\)", ref)
if len(str) > 1:
str = str[1].split(".")
str[0] = str[0].replace("\n", "")
fp.write(str[0].strip())
fp.write("\n")
#num += 1
fp.close()
def main(argv):
import getopt
def usage():
print ('usage: %s [-d] [-p pagenos] [-m maxpages] [-P password] [-o output]'
' [-C] [-n] [-A] [-V] [-M char_margin] [-L line_margin] [-W word_margin]'
' [-F boxes_flow] [-Y layout_mode] [-O output_dir] [-R rotation]'
' [-t text|html|xml|tag] [-c codec] [-s scale]'
' file ...' % argv[0])
return 100
try:
(opts, args) = getopt.getopt(argv[1:], 'dp:m:P:o:CnAVM:L:W:F:Y:O:R:t:c:s:')
except getopt.GetoptError:
return usage()
if not args: return usage()
# debug option
debug = 0
# input option
password = ''
pagenos = set()
maxpages = 0
# output option
outfile = None
outtype = None
imagewriter = None
rotation = 0
layoutmode = 'normal'
codec = 'utf-8'
pageno = 1
scale = 1
caching = True
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 == '-C': caching = False
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': imagewriter = ImageWriter(v)
elif k == '-R': rotation = int(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(caching=caching)
if not outtype:
outtype = 'text'
if outfile:
if outfile.endswith('.htm') or outfile.endswith('.html'):
outtype = 'html'
elif outfile.endswith('.xml'):
outtype = 'xml'
elif outfile.endswith('.tag'):
outtype = 'tag'
if outfile:
outfp = file(outfile, 'w')
else:
outfp = sys.stdout
if outtype == 'text':
device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'xml':
device = XMLConverter(rsrcmgr, outfp, codec=codec, laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'html':
device = HTMLConverter(rsrcmgr, outfp, codec=codec, scale=scale,
layoutmode=layoutmode, laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'tag':
device = TagExtractor(rsrcmgr, outfp, codec=codec)
else:
return usage()
for fname in args:
fp = file(fname, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.get_pages(fp, pagenos,
maxpages=maxpages, password=password,
caching=caching, check_extractable=True):
page.rotate = (page.rotate+rotation) % 360
interpreter.process_page(page)
fp.close()
device.close()
outfp.close()
return
def get_paper_content(fname, pages=2, outdir="data"):
debug = 0
# input option
password = ''
pagenos = set()
maxpages = 0
# output option
basename = os.path.basename(fname)
basename = basename.replace(".pdf", "")
outfile = os.path.join(outdir, basename + ".html")
outtype = None
imagewriter = None
rotation = 0
stripcontrol = False
layoutmode = 'normal'
codec = 'utf-8'
pageno = 1
scale = 1
caching = True
showpageno = True
laparams = LAParams()
PDFDocument.debug = debug
PDFParser.debug = debug
CMapDB.debug = debug
PDFPageInterpreter.debug = debug
#
rsrcmgr = PDFResourceManager(caching=caching)
if not outtype:
outtype = 'text'
if outfile:
if outfile.endswith('.htm') or outfile.endswith('.html'):
outtype = 'html'
elif outfile.endswith('.xml'):
outtype = 'xml'
elif outfile.endswith('.tag'):
outtype = 'tag'
if outfile:
outfp = file(outfile, 'w')
else:
outfp = sys.stdout
if outtype == 'text':
device = TextConverter(rsrcmgr,
outfp,
codec=codec,
laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'xml':
device = XMLConverter(rsrcmgr,
outfp,
codec=codec,
laparams=laparams,
imagewriter=imagewriter,
stripcontrol=stripcontrol)
elif outtype == 'html':
device = HTMLConverter(rsrcmgr,
outfp,
codec=codec,
scale=scale,
layoutmode=layoutmode,
laparams=laparams,
imagewriter=imagewriter,
debug=debug)
elif outtype == 'tag':
device = TagExtractor(rsrcmgr, outfp, codec=codec)
else:
return
fp = file(fname, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
interpreter.debug = True
try:
for index, page in enumerate(
PDFPage.get_pages(fp,
pagenos,
maxpages=maxpages,
password=password,
caching=caching,
check_extractable=True)):
if index > pages:
break
page.rotate = (page.rotate + rotation) % 360
interpreter.process_page(page)
except:
print(fname)
return
fp.close()
device.close()
outfp.close()
return
def main(argv):
def usage():
print(('usage: %s [-d] [-p pagenos] [-m maxpages] [-P password] [-o output] [-C] '
'[-n] [-A] [-V] [-M char_margin] [-L line_margin] [-W word_margin] [-F boxes_flow] '
'[-Y layout_mode] [-O output_dir] [-t text|html|xml|tag] [-c codec] [-s scale] file ...' % argv[0]))
return 100
try:
(opts, args) = getopt.getopt(argv[1:], 'dp:m:P:o:CnAVM:L:W:F:Y:O:t:c:s:')
except getopt.GetoptError:
return usage()
if not args: return usage()
debug = False
# input option
password = ''
pagenos = set()
maxpages = 0
# output option
outfile = None
outtype = None
outdir = None
layoutmode = 'normal'
codec = 'utf-8'
pageno = 1
scale = 1
caching = True
showpageno = True
laparams = LAParams()
for (k, v) in opts:
if k == '-d': debug = True
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 == '-C': caching = False
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)
if debug:
set_debug_logging()
rsrcmgr = PDFResourceManager(caching=caching)
if not outtype:
outtype = 'text'
if outfile:
if outfile.endswith('.htm') or outfile.endswith('.html'):
outtype = 'html'
elif outfile.endswith('.xml'):
outtype = 'xml'
elif outfile.endswith('.tag'):
outtype = 'tag'
if outfile:
outfp = io.open(outfile, 'wt', encoding=codec, errors='ignore')
close_outfp = True
else:
outfp = sys.stdout
close_outfp = False
if outtype == 'text':
device = TextConverter(rsrcmgr, outfp, laparams=laparams)
elif outtype == 'xml':
device = XMLConverter(rsrcmgr, outfp, laparams=laparams, outdir=outdir)
elif outtype == 'html':
device = HTMLConverter(rsrcmgr, outfp, scale=scale, layoutmode=layoutmode,
laparams=laparams, outdir=outdir, debug=debug)
elif outtype == 'tag':
device = TagExtractor(rsrcmgr, outfp)
else:
return usage()
for fname in args:
fp = io.open(fname, 'rb')
process_pdf(rsrcmgr, device, fp, pagenos, maxpages=maxpages, password=password,
caching=caching, check_extractable=True)
fp.close()
device.close()
if close_outfp:
outfp.close()
def convertPDF(outfile, pdfFile):
# 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
caching = True
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 == '-C': caching = False
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(caching=caching)
if not outtype:
outtype = 'text'
if outfile:
if outfile.endswith('.htm') or outfile.endswith('.html'):
outtype = 'html'
elif outfile.endswith('.xml'):
outtype = 'xml'
elif outfile.endswith('.tag'):
outtype = 'tag'
if outfile:
outfp = file(outfile, 'w')
else:
outfp = sys.stdout
if outtype == 'text':
device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams)
elif outtype == 'xml':
device = XMLConverter(rsrcmgr,
outfp,
codec=codec,
laparams=laparams,
outdir=outdir)
elif outtype == 'html':
device = HTMLConverter(rsrcmgr,
outfp,
codec=codec,
scale=scale,
layoutmode=layoutmode,
laparams=laparams,
outdir=outdir)
elif outtype == 'tag':
device = TagExtractor(rsrcmgr, outfp, codec=codec)
else:
pass #return usage()
fname = pdfFile #for fname in args:
fp = file(fname, 'rb')
process_pdf(rsrcmgr,
device,
fp,
pagenos,
maxpages=maxpages,
password=password,
caching=caching,
check_extractable=True)
fp.close()
device.close()
outfp.close()
return
def main(argv):
import getopt
def usage():
print(f'usage: {argv[0]} [-P password] [-o output] [-t text|html|xml|tag]'
' [-O output_dir] [-c encoding] [-s scale] [-R rotation]'
' [-Y normal|loose|exact] [-p pagenos] [-m maxpages]'
' [-S] [-C] [-n] [-A] [-V] [-M char_margin] [-L line_margin]'
' [-W word_margin] [-F boxes_flow] [-d] input.pdf ...')
return 100
try:
(opts, args) = getopt.getopt(argv[1:], 'dP:o:t:O:c:s:R:Y:p:m:SCnAVM:W:L:F:')
except getopt.GetoptError:
return usage()
if not args: return usage()
# debug option
debug = 0
# input option
password = b''
pagenos = set()
maxpages = 0
# output option
outfile = None
outtype = None
imagewriter = None
rotation = 0
stripcontrol = False
layoutmode = 'normal'
encoding = 'utf-8'
pageno = 1
scale = 1
caching = True
showpageno = True
laparams = LAParams()
for (k, v) in opts:
if k == '-d': debug += 1
elif k == '-P': password = v.encode('ascii')
elif k == '-o': outfile = v
elif k == '-t': outtype = v
elif k == '-O': imagewriter = ImageWriter(v)
elif k == '-c': encoding = v
elif k == '-s': scale = float(v)
elif k == '-R': rotation = int(v)
elif k == '-Y': layoutmode = v
elif k == '-p': pagenos.update( int(x)-1 for x in v.split(',') )
elif k == '-m': maxpages = int(v)
elif k == '-S': stripcontrol = True
elif k == '-C': caching = False
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 == '-W': laparams.word_margin = float(v)
elif k == '-L': laparams.line_margin = float(v)
elif k == '-F': laparams.boxes_flow = float(v)
#
PDFDocument.debug = debug
PDFParser.debug = debug
CMapDB.debug = debug
PDFPageInterpreter.debug = debug
#
rsrcmgr = PDFResourceManager(caching=caching)
if not outtype:
outtype = 'text'
if outfile:
if outfile.endswith('.htm') or outfile.endswith('.html'):
outtype = 'html'
elif outfile.endswith('.xml'):
outtype = 'xml'
elif outfile.endswith('.tag'):
outtype = 'tag'
if outfile:
if sys.platform == 'linux':
outfp = open(outfile, 'w', encoding=encoding)
elif sys.platform == 'win32':
outfp = open(outfile, 'wb')
else:
outfp = sys.stdout
if outtype == 'text':
device = TextConverter(rsrcmgr, outfp, laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'xml':
device = XMLConverter(rsrcmgr, outfp, laparams=laparams,
imagewriter=imagewriter,
stripcontrol=stripcontrol)
elif outtype == 'html':
device = HTMLConverter(rsrcmgr, outfp, scale=scale,
layoutmode=layoutmode, laparams=laparams,
imagewriter=imagewriter, debug=debug)
elif outtype == 'tag':
device = TagExtractor(rsrcmgr, outfp)
else:
return usage()
for fname in args:
with open(fname, 'rb') as fp:
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.get_pages(fp, pagenos,
maxpages=maxpages, password=password,
caching=caching, check_extractable=True):
page.rotate = (page.rotate+rotation) % 360
interpreter.process_page(page)
device.close()
outfp.close()
return
def parsepdf_pdfminer_formal(path, outtype='txt'):
# debug option
debug = 0
# input option
password = b''
pagenos = set()
maxpages = 0
# output option
outfile = r'C:\Users\Administrator\Desktop\parseRes_demo.' + outtype
imagewriter = None
rotation = 0
stripcontrol = False
layoutmode = 'normal'
encoding = 'utf-8'
pageno = 1
scale = 1
caching = True
showpageno = True
laparams = LAParams()
laparams.all_texts = True
laparams.detect_vertical = True
# for (k, v) in opts:
# if k == '-d': debug += 1
# elif k == '-P': password = v.encode('ascii')
# elif k == '-o': outfile = v
# elif k == '-t': outtype = v
# elif k == '-O': imagewriter = ImageWriter(v)
# elif k == '-c': encoding = v
# elif k == '-s': scale = float(v)
# elif k == '-R': rotation = int(v)
# elif k == '-Y': layoutmode = v
# elif k == '-p': pagenos.update( int(x)-1 for x in v.split(',') )
# elif k == '-m': maxpages = int(v)
# elif k == '-S': stripcontrol = True
# elif k == '-C': caching = False
# 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 == '-W': laparams.word_margin = float(v)
# elif k == '-L': laparams.line_margin = float(v)
# elif k == '-F': laparams.boxes_flow = float(v)
#
PDFDocument.debug = debug
PDFParser.debug = debug
CMapDB.debug = debug
PDFPageInterpreter.debug = debug
#
rsrcmgr = PDFResourceManager(caching=caching)
if not outtype:
outtype = 'text'
if outfile:
if outfile.endswith('.htm') or outfile.endswith('.html'):
outtype = 'html'
elif outfile.endswith('.xml'):
outtype = 'xml'
elif outfile.endswith('.tag'):
outtype = 'tag'
if outfile:
outfp = open(outfile, 'w', encoding=encoding)
if outtype == 'txt':
device = TextConverter(rsrcmgr, outfp, laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'xml':
device = XMLConverter(rsrcmgr, outfp, laparams=laparams,
imagewriter=imagewriter,
stripcontrol=stripcontrol)
elif outtype == 'html':
device = HTMLConverter(rsrcmgr, outfp, scale=scale,
layoutmode=layoutmode, laparams=laparams,
imagewriter=imagewriter, debug=debug)
elif outtype == 'tag':
device = TagExtractor(rsrcmgr, outfp)
# else:
# return usage()
# for fname in args:
with open(path, 'rb') as fp:
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.get_pages(fp, pagenos,
maxpages=maxpages, password=password,
caching=caching, check_extractable=True):
page.rotate = (page.rotate+rotation) % 360
interpreter.process_page(page)
device.close()
outfp.close()
return
def main(argv):
# debug option
debug = 0
# input option
password = ''
pagenos = set()
maxpages = 0
# output option
outfile = None
outtype = None
imagewriter = None
rotation = 0
stripcontrol = False
layoutmode = 'normal'
codec = 'utf-8'
pageno = 1
scale = 1
caching = True
showpageno = False
laparams = LAParams()
using_optparse = False
parser = ArgumentParser(prog='pdf2txt.py',
description='Convert pdf to txt',
formatter_class=ArgumentDefaultsHelpFormatter)
if using_optparse:
DEBUG(3, 'using optparse')
parser.add_argument = parser.add_option
parser.parse_known_args = parser.parse_args
parser.disable_interspersed_args()
parser.add_argument('-d',
dest='debuglevel',
action='count',
default=0,
help='Debug (repeat for more verbose debugging)')
parser.add_argument(
'-p',
'--pages',
dest='pagenos',
action='store',
type=str,
default='',
help=
'Specifies the comma-separated list of the page numbers to be extracted. Page numbers start at one. By default, it extracts text from all the pages.'
)
parser.add_argument('-c',
'--codec',
dest='codec',
action='store',
type=str,
default='utf-8',
help='Specifies the output codec.')
parser.add_argument(
'-t',
'--type',
dest='outtype',
action='store',
type=str,
default='shape',
choices=['text', 'html', 'xml', 'tag', 'shape'],
help='Specifies the output format, one of: shape, text, html, xml, tag'
)
parser.add_argument(
'-m',
dest='maxpages',
action='store',
type=int,
default=0,
help=
'Specifies the maximum number of pages to extract. By default (0), it extracts all the pages in a document.'
)
parser.add_argument(
'-P',
'--password',
dest='password',
action='store',
type=str,
default='',
help='Provides the user password to access PDF contents.')
parser.add_argument(
'-o',
'--output',
dest='outfile',
action='store',
type=str,
default=None,
help=
'Specifies the output file name. By default, it prints the extracted contents to stdout in text format.'
)
parser.add_argument(
'-C',
'--no-caching',
dest='caching',
action='store_false',
default=True,
help=
'Suppress object caching. This will reduce the memory consumption but also slows down the process.'
)
parser.add_argument('-n',
'--no-layout',
dest='layout',
action='store_false',
default=True,
help='Suppress layout analysis.')
parser.add_argument('--show-pageno',
dest='show_pageno',
action='store_true',
default=False,
help='Show page numbers.')
parser.add_argument(
'-A',
'--analyze-all',
dest='all_texts',
action='store_true',
default=False,
help=
'Forces to perform layout analysis for all the text strings, including text contained in figures.'
)
parser.add_argument('-V',
'--detect-vertical',
dest='detect_vertical',
action='store_true',
default=False,
help='Allows vertical writing detection.')
parser.add_argument(
'-M',
dest='char_margin',
action='store',
type=float,
default=2.0,
help=
'Two text chunks whose distance is closer than the char_margin (shown as M) is considered continuous and get grouped into one.'
)
parser.add_argument(
'-L',
dest='line_margin',
action='store',
type=float,
default=0.5,
help=
'Two lines whose distance is closer than the line_margin (L) is grouped as a text box, which is a rectangular area that contains a "cluster" of text portions.'
)
parser.add_argument(
'-W',
dest='word_margin',
action='store',
type=float,
default=0.1,
help=
'It may be required to insert blank characters (spaces) as necessary if the distance between two words is greater than the word_margin (W), as a blank between words might not be represented as a space, but indicated by the positioning of each word.'
)
parser.add_argument(
'-F',
dest='boxes_flow',
action='store',
type=float,
default=0.5,
help=
'Specifies how much a horizontal and vertical position of a text matters when determining a text order. The value should be within the range of -1.0 (only horizontal position matters) to +1.0 (only vertical position matters).'
)
parser.add_argument(
'-Y',
'--layout-mode',
dest='layoutmode',
action='store',
type=str,
default='normal',
choices=['exact', 'normal', 'loose'],
help=
'Specifies how the page layout should be preserved. (Currently only applies to HTML format.) One of: exact, normal, loose.'
)
parser.add_argument('-O',
'--image-writer',
dest='imagewriter',
action='store',
type=str,
default=None,
help='imagewriter')
parser.add_argument('-R',
'--rotation',
dest='rotation',
action='store',
type=int,
default=0,
help='rotation')
parser.add_argument('-S',
'--strip-control',
dest='stripcontrol',
action='store_true',
default=False,
help='stripcontrol')
parser.add_argument(
'-s',
dest='scale',
action='store',
type=float,
default=1,
help='Specifies the output scale. Can be used in HTML format only.')
parser.add_argument(
'--draw-lines',
dest='draw_lines',
action='store_true',
help=
"Draw crude page representation, coloured TextLines (= short pieces of text). Valid only for the `shape' output."
)
parser.add_argument(
'--draw-boxes',
dest='draw_boxes',
action='store_true',
help=
"Draw crude page representation, coloured TextBoxes (= grouped text lines). Valid only for the `shape' output."
)
parser.add_argument(
'--draw-blocks',
dest='draw_blocks',
action='store_true',
help=
"Draw crude page representation, coloured TextBlocks (= grouped TextBoxes). Valid only for the `shape' output."
)
parser.add_argument(
'--shear-limit',
dest='shear_limit',
action='store',
default=0.1,
type=float,
help=
"If the text is sheared above this limit, reject it. Valid only for the `shape' output."
)
parser.add_argument(
'--rotation-limit',
dest='rotation_limit',
action='store',
default=2,
type=float,
help=
"If the text is rotated above this angle (in degrees), reject it. Valid only for the `shape' output."
)
parser.add_argument(
'--line-height-diff',
dest='line_height_diff',
action='store',
type=float,
default=0.1,
help=
'Two lines whose vertical sizes differ more than this ratio are not to be considered of the same paragraph (but e.g. one of them is a heading).'
)
parser.add_argument('--heading-before',
dest='heading_before',
action='store',
type=str,
default='',
help='String to put before each heading, e.g. <h1>')
parser.add_argument('--heading-after',
dest='heading_after',
action='store',
type=str,
default='',
help='String to put after each heading, e.g. </h1>')
parser.add_argument(
'--box-separator',
dest='box_separator',
action='store',
type=str,
default=r'\n\n',
help=
r'Separate boxes with this string. Use \n for new line, \t for TAB, other escape sequences are not recognized.'
)
parser.add_argument(
'--block-separator',
dest='block_separator',
action='store',
type=str,
default=r'\n\n',
help=
r'Separate blocks with this string. Use \n for new line, \t for TAB, other escape sequences are not recognized.'
)
parser.add_argument(
'--indent-separator',
dest='indent_separator',
action='store',
type=str,
default=r'\n\n',
help=
r'Separate indented lines with this string. Use \n for new line, \t for TAB, other escape sequences are not recognized.'
)
parser.add_argument(
'--indent-string',
dest='indent_string',
action='store',
type=str,
default=r'\t',
help=
r'Put this string in front of indented lines. Use \n for new line, \t for TAB, other escape sequences are not recognized.'
)
parser.add_argument(
'--indent-limit',
dest='indent_limit',
action='store',
type=float,
default=3,
help=
'If the line is indented more then this (approximately characters), it will separated by --indent-separator from the previous one.'
)
parser.add_argument(
'--page-separator',
dest='page_separator',
action='store',
type=str,
default=r'\n\n',
help=
r'Separate pages with this string. Use \n for new line, \t for TAB, other escape sequences are not recognized.'
)
parser.add_argument(
'--norm-whitespace',
dest='norm_whitespace',
action='store_true',
default=False,
help=
'Normalize whitespace (remove duplicate spaces, replace end of lines with spaces).'
)
parser.add_argument(
'--print-stats',
dest='print_stats',
action='store_true',
default=False,
help=
'Instead of the text, output some simple statistics about the file.')
parser.add_argument(
'--max-blocks',
dest='max_blocks',
action='store',
default=0,
type=int,
help=
'If there is more than this blocks per page, do not return any text. Use to discriminate abnormal files (run --print-stats first to find out the number of boxes per "normal" file). 0 means no limit. 50 is maybe a good value.'
)
parser.add_argument(
'--max-textlines',
dest='max_textlines',
action='store',
default=0,
type=int,
help=
'If there is more than this textlines per any block, do not return any text. Use to discriminate abnormal files (run --print-stats first to find out the number of boxes per "normal" page). 0 means no limit. 18 is maybe a good value.'
)
parser.add_argument(
'--line-height-method',
dest='line_height_method',
action='store',
type=str,
default='bbox',
choices=['bbox', 'mean', 'median'],
help=
'Method to calculate height of line (relevant if there are characters with uneven height). bbox takes the bounding box (rectangle encompassing the line), mean the arithmetic mean of the height of all the characters, median is the median of the height of all the characters. Use mean or median if there are outlier characters, e.g. one big character at the beginning of line.'
)
parser.add_argument(dest='pdffile',
help='List of PDF files to go through',
default=None,
nargs='+')
args, rest = parser.parse_known_args()
global debuglevel
debuglevel = debug = args.debuglevel
DEBUG(3, 'args:', str(args))
DEBUG(3, 'rest:', str(rest))
DEBUG(3, 'optparse:', using_optparse)
if args.pagenos:
pagenos.update(int(x) - 1 for x in args.pagenos.split(','))
maxpages = args.maxpages
outfile = args.outfile
password = args.password
caching = args.caching
showpageno = args.show_pageno
if not args.layout:
laparams = None
if laparams and args.all_texts:
laparams.all_texts = True
if laparams and args.detect_vertical:
laparams.detect_vertical = True
if laparams:
laparams.char_margin = args.char_margin
laparams.line_margin = args.line_margin
laparams.word_margin = args.word_margin
laparams.boxes_flow = args.boxes_flow
layoutmode = args.layoutmode
if args.imagewriter:
imagewriter = ImageWriter(args.imagewriter)
rotation = args.rotation
stripcontrol = args.stripcontrol
outtype = args.outtype
codec = args.codec
scale = args.scale
args.box_separator = unescape_string(args.box_separator)
args.block_separator = unescape_string(args.block_separator)
args.indent_separator = unescape_string(args.indent_separator)
args.indent_string = unescape_string(args.indent_string)
args.page_separator = unescape_string(args.page_separator)
global options
options = args
PDFDocument.debug = debug
PDFParser.debug = debug
CMapDB.debug = debug
PDFPageInterpreter.debug = debug
rsrcmgr = PDFResourceManager(caching=caching)
if not outtype:
outtype = 'text'
if outfile:
if outfile.endswith('.htm') or outfile.endswith('.html'):
outtype = 'html'
elif outfile.endswith('.xml'):
outtype = 'xml'
elif outfile.endswith('.tag'):
outtype = 'tag'
if outfile:
outfp = file(outfile, 'w')
DEBUG(2, 'output goes to', outfile)
else:
outfp = sys.stdout
DEBUG(2, 'output goes to stdout')
if outtype == 'shape':
device = ShapeTextConverter(rsrcmgr,
outfp,
codec=codec,
laparams=laparams,
showpageno=showpageno,
imagewriter=imagewriter)
elif outtype == 'text':
device = TextConverter(rsrcmgr,
outfp,
codec=codec,
laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'xml':
device = XMLConverter(rsrcmgr,
outfp,
codec=codec,
laparams=laparams,
imagewriter=imagewriter,
stripcontrol=stripcontrol)
elif outtype == 'html':
device = HTMLConverter(rsrcmgr,
outfp,
codec=codec,
scale=scale,
layoutmode=layoutmode,
laparams=laparams,
imagewriter=imagewriter,
debug=debug)
elif outtype == 'tag':
device = TagExtractor(rsrcmgr, outfp, codec=codec)
else:
return usage()
for fname in options.pdffile:
DEBUG(2, 'processing', fname)
fp = file(fname, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.get_pages(fp,
pagenos,
maxpages=maxpages,
password=password,
caching=caching,
check_extractable=True):
page.rotate = (page.rotate + rotation) % 360
interpreter.process_page(page)
fp.close()
device.close()
outfp.close()
DEBUG(2, 'finished.')
return
def main(argv):
import getopt
def usage():
print 'Syntax:\npdf2htm.exe SourcePDF\n where the parameter is either a file name or\na wildcard spec like\n*.pdf\nEnclose it with quotes if it contains a space\n\nAdditional options are supported with named command line parameters as follows:'
print ('usage: %s [-d] [-p pagenos] [-m maxpages] [-P password] [-o output]'
' [-C] [-n] [-A] [-V] [-M char_margin] [-L line_margin] [-W word_margin]'
' [-F boxes_flow] [-Y layout_mode] [-O output_dir] [-R rotation]'
' [-t text|html|xml|tag] [-c codec] [-s scale]'
' file ...' % argv[0])
return 100
try:
(opts, args) = getopt.getopt(argv[1:], 'dp:m:P:o:CnAVM:L:W:F:Y:O:R:t:c:s:')
except getopt.GetoptError:
return usage()
if not args: return usage()
# debug option
debug = 0
# input option
password = ''
pagenos = set()
maxpages = 0
# output option
outfile = None
outtype = 'tag'
imagewriter = None
rotation = 0
layoutmode = 'normal'
codec = 'utf-8'
pageno = 1
scale = 1
caching = True
showpageno = False
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 == '-C': caching = False
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': imagewriter = ImageWriter(v)
elif k == '-R': rotation = int(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(caching=caching)
if not outtype:
outtype = 'tag'
if outfile:
if outfile.endswith('.htm') or outfile.endswith('.html'):
outtype = 'html'
elif outfile.endswith('.xml'):
outtype = 'xml'
elif outfile.endswith('.tag'):
outtype = 'tag'
if outfile:
outfp = file(outfile, 'w')
else:
outfp = sys.stdout
for fname in args:
l = glob.glob(fname)
count = len(l)
print 'Converting ' + str(count) + ' from ' + fname + ' to ' + outtype + ' format'
for pdf in l:
# print pdf
d = {'html' : 'htm', 'tag' : 'tag', 'text' : 'txt', 'xml' : 'xml'}
ext = '.' + d[outtype]
outfile = pdf[0:-4] + ext
print outfile
outfp = file(outfile, 'wb')
if outtype == 'text':
device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams,
imagewriter=imagewriter)
device.showpageno = False
elif outtype == 'xml':
device = XMLConverter(rsrcmgr, outfp, codec=codec, laparams=laparams,
imagewriter=imagewriter)
device.showpageno = False
elif outtype == 'html':
device = HTMLConverter(rsrcmgr, outfp, codec=codec, scale=scale,
layoutmode=layoutmode, laparams=laparams,
imagewriter=imagewriter)
device.showpageno = False
elif outtype == 'tag':
device = TagExtractor(rsrcmgr, outfp, codec=codec)
device.showpageno = False
else:
return usage()
fp = file(pdf, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.get_pages(fp, pagenos,
maxpages=maxpages, password=password,
caching=caching, check_extractable=True):
page.rotate = (page.rotate+rotation) % 360
interpreter.process_page(page)
fp.close()
device.close()
outfp.close()
print 'Done'
return
def ConvertPdf(pdfpath, outfp, opts={}):
import sys
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice, TagExtractor
from pdfminer.pdfpage import PDFPage
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.cmapdb import CMapDB
from pdfminer.layout import LAParams
from pdfminer.image import ImageWriter
debug = 0
# input option
password = ''
pagenos = set()
maxpages = 0
# output option
outfile = None
outtype = None
imagewriter = None
rotation = 0
layoutmode = 'normal'
codec = 'utf-8'
pageno = 1
scale = 1
caching = True
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 == '-C': caching = False
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': imagewriter = ImageWriter(v)
elif k == '-R': rotation = int(v)
elif k == '-t': outtype = v
elif k == '-c': codec = v
elif k == '-s': scale = float(v)
#
CMapDB.debug = debug
PDFResourceManager.debug = debug
PDFDocument.debug = debug
PDFParser.debug = debug
PDFPageInterpreter.debug = debug
PDFDevice.debug = debug
#
rsrcmgr = PDFResourceManager()
if not outtype:
outtype = 'txt'
if outtype == 'txt':
device = TextConverter(rsrcmgr,
outfp,
codec=codec,
laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'xml':
device = XMLConverter(rsrcmgr,
outfp,
codec=codec,
laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'html':
device = HTMLConverter(rsrcmgr,
outfp,
codec=codec,
scale=scale,
layoutmode=layoutmode,
laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'tag':
device = TagExtractor(rsrcmgr, outfp, codec=codec)
fp = file(pdfpath, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.get_pages(fp,
pagenos,
maxpages=maxpages,
password=password,
caching=caching,
check_extractable=True):
page.rotate = (page.rotate + rotation) % 360
interpreter.process_page(page)
fp.close()
device.close()
return True
def translate(output, args):
# debug option
debug = 0
# input option
password = ''
pagenos = set()
maxpages = 0
# output option
outfile = None
outtype = None
imagewriter = None
rotation = 0
stripcontrol = False
layoutmode = 'normal'
codec = 'utf-8'
pageno = 1
scale = 1
caching = True
showpageno = True
laparams = LAParams()
outfile = output
#
PDFDocument.debug = debug
PDFParser.debug = debug
CMapDB.debug = debug
PDFPageInterpreter.debug = debug
#
rsrcmgr = PDFResourceManager(caching=caching)
if not outtype:
outtype = 'text'
if outfile:
if outfile.endswith('.htm') or outfile.endswith('.html'):
outtype = 'html'
elif outfile.endswith('.xml'):
outtype = 'xml'
elif outfile.endswith('.tag'):
outtype = 'tag'
if outfile:
outfp = file(outfile, 'w')
else:
outfp = sys.stdout
if outtype == 'text':
device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'xml':
device = XMLConverter(rsrcmgr, outfp, codec=codec, laparams=laparams,
imagewriter=imagewriter,
stripcontrol=stripcontrol)
elif outtype == 'html':
device = HTMLConverter(rsrcmgr, outfp, codec=codec, scale=scale,
layoutmode=layoutmode, laparams=laparams,
imagewriter=imagewriter, debug=debug)
elif outtype == 'tag':
device = TagExtractor(rsrcmgr, outfp, codec=codec)
else:
return usage()
fp = file(args, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.get_pages(fp, pagenos,
maxpages=maxpages, password=password,
caching=caching, check_extractable=True):
page.rotate = (page.rotate+rotation) % 360
interpreter.process_page(page)
fp.close()
device.close()
outfp.close()
return
