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 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:
outfp = open(outfile, 'w', encoding=encoding)
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)
fname.write(page)
device.close()
outfp.close()
return
def extract_text(
files=[],
outfile='-',
_py2_no_more_posargs=None, # Bloody Python2 needs a shim
no_laparams=False,
all_texts=None,
detect_vertical=None, # LAParams
word_margin=None,
char_margin=None,
line_margin=None,
boxes_flow=None, # LAParams
output_type='text',
codec='utf-8',
strip_control=False,
maxpages=0,
page_numbers=None,
password="",
scale=1.0,
rotation=0,
layoutmode='normal',
output_dir=None,
debug=False,
disable_caching=False,
**other):
if _py2_no_more_posargs is not None:
raise ValueError("Too many positional arguments passed.")
if not files:
raise ValueError("Must provide files to work upon!")
# If any LAParams group arguments were passed, create an LAParams object and
# populate with given args. Otherwise, set it to None.
if not no_laparams:
laparams = pdfminer.layout.LAParams()
for param in ("all_texts", "detect_vertical", "word_margin",
"char_margin", "line_margin", "boxes_flow"):
paramv = locals().get(param, None)
if paramv is not None:
setattr(laparams, param, paramv)
else:
laparams = None
imagewriter = None
if output_dir:
imagewriter = ImageWriter(output_dir)
if output_type == "text" and outfile != "-":
for override, alttype in ((".htm", "html"), (".html", "html"),
(".xml", "xml"), (".tag", "tag")):
if outfile.endswith(override):
output_type = alttype
if outfile == "-":
outfp = sys.stdout
if outfp.encoding is not None:
codec = 'utf-8'
else:
outfp = open(outfile, "wb")
for fname in files:
with open(fname, "rb") as fp:
pdfminer.high_level.extract_text_to_fp(fp, **locals())
return outfp
def extract_text(
files=[],
outfile='-',
no_laparams=False,
all_texts=None,
detect_vertical=None, # LAParams
word_margin=None,
char_margin=None,
line_margin=None,
boxes_flow=None, # LAParams
output_type='text',
codec='utf-8',
strip_control=False,
maxpages=0,
page_numbers=None,
password="",
scale=1.0,
rotation=0,
layoutmode='normal',
output_dir=None,
debug=False,
disable_caching=False,
**kwargs):
if '_py2_no_more_posargs' in kwargs is not None:
raise DeprecationWarning(
'The `_py2_no_more_posargs will be removed on January, 2020. At '
'that moment pdfminer.six will stop supporting Python 2. Please '
'upgrade to Python 3. For more information see '
'https://github.com/pdfminer/pdfminer .six/issues/194')
if not files:
raise ValueError("Must provide files to work upon!")
# If any LAParams group arguments were passed, create an LAParams object and
# populate with given args. Otherwise, set it to None.
if not no_laparams:
laparams = pdfminer.layout.LAParams()
for param in ("all_texts", "detect_vertical", "word_margin",
"char_margin", "line_margin", "boxes_flow"):
paramv = locals().get(param, None)
if paramv is not None:
setattr(laparams, param, paramv)
else:
laparams = None
imagewriter = None
if output_dir:
imagewriter = ImageWriter(output_dir)
if output_type == "text" and outfile != "-":
for override, alttype in ((".htm", "html"), (".html", "html"),
(".xml", "xml"), (".tag", "tag")):
if outfile.endswith(override):
output_type = alttype
if outfile == "-":
outfp = sys.stdout
if outfp.encoding is not None:
codec = 'utf-8'
else:
outfp = open(outfile, "wb")
for fname in files:
with open(fname, "rb") as fp:
pdfminer.high_level.extract_text_to_fp(fp, **locals())
return outfp
def main(args=None):
import argparse
P = argparse.ArgumentParser(description=__doc__)
P.add_argument("files",
type=str,
default=None,
nargs="+",
help="Files to process.")
P.add_argument("-d",
"--debug",
default=False,
action="store_true",
help="Debug output.")
P.add_argument(
"-p",
"--pagenos",
type=str,
help=
"Comma-separated list of page numbers to parse. Included for legacy applications, use -P/--page-numbers for more idiomatic argument entry."
)
P.add_argument(
"--page-numbers",
type=int,
default=None,
nargs="+",
help=
"Alternative to --pagenos with space-separated numbers; supercedes --pagenos where it is used."
)
P.add_argument("-m",
"--maxpages",
type=int,
default=0,
help="Maximum pages to parse")
P.add_argument("-P",
"--password",
type=str,
default="",
help="Decryption password for PDF")
P.add_argument("-o",
"--outfile",
type=str,
default="-",
help="Output file (default/'-' is stdout)")
P.add_argument("-t",
"--output_type",
type=str,
default="text",
help="Output type: text|html|xml|tag (default is text)")
P.add_argument("-c",
"--codec",
type=str,
default="utf-8",
help="Text encoding")
P.add_argument("-s", "--scale", type=float, default=1.0, help="Scale")
P.add_argument("-A",
"--all-texts",
default=None,
action="store_true",
help="LAParams all texts")
P.add_argument("-V",
"--detect-vertical",
default=None,
action="store_true",
help="LAParams detect vertical")
P.add_argument("-W",
"--word-margin",
type=float,
default=None,
help="LAParams word margin")
P.add_argument("-M",
"--char-margin",
type=float,
default=None,
help="LAParams char margin")
P.add_argument("-L",
"--line-margin",
type=float,
default=None,
help="LAParams line margin")
P.add_argument("-F",
"--boxes-flow",
type=float,
default=None,
help="LAParams boxes flow")
P.add_argument("-Y",
"--layoutmode",
default="normal",
type=str,
help="HTML Layout Mode")
P.add_argument("-n",
"--no-laparams",
default=False,
action="store_true",
help="Pass None as LAParams")
P.add_argument("-R", "--rotation", default=0, type=int, help="Rotation")
P.add_argument("-O",
"--output-dir",
default=None,
help="Output directory for images")
P.add_argument("-C",
"--disable-caching",
default=False,
action="store_true",
help="Disable caching")
P.add_argument("-S",
"--strip-control",
default=False,
action="store_true",
help="Strip control in XML mode")
A = P.parse_args(args=args)
if A.page_numbers:
A.page_numbers = set([x - 1 for x in A.page_numbers])
if A.pagenos:
A.page_numbers = set([int(x) - 1 for x in A.pagenos.split(",")])
imagewriter = None
if A.output_dir:
imagewriter = ImageWriter(A.output_dir)
if six.PY2 and sys.stdin.encoding:
A.password = A.password.decode(sys.stdin.encoding)
if A.output_type == "text" and A.outfile != "-":
for override, alttype in ((".htm", "html"), (".html", "html"),
(".xml", "xml"), (".tag", "tag")):
if A.outfile.endswith(override):
A.output_type = alttype
if A.outfile == "-":
outfp = sys.stdout
if outfp.encoding is not None:
# Why ignore outfp.encoding? :-/ stupid cathal?
A.codec = 'utf-8'
else:
outfp = open(A.outfile, "wb")
## Test Code
outfp = extract_text(**vars(A))
outfp.close()
return 0
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 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] [-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 option
debug = 0
# input option
password = ''
pagenos = set()
maxpages = 0
# output option
outfile = None
outtype = None
imagewriter = 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': imagewriter = ImageWriter(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,
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')
process_pdf(rsrcmgr, device, fp, pagenos, maxpages=maxpages, password=password,
caching=caching, check_extractable=True)
fp.close()
device.close()
outfp.close()
return
def get_html_tree(self) -> str:
# Create a temp folder where images are temporarily saved.
dirname = tempfile.mkdtemp()
imagewriter = ImageWriter(dirname)
doc = Document()
self.doc = doc
html = doc.createElement("html")
doc.appendChild(html)
head = doc.createElement("head")
html.appendChild(head)
# meta
meta = doc.createElement("meta")
head.appendChild(meta)
meta.setAttribute("name", "ocr-system")
meta.setAttribute("content",
f"Converted from PDF by pdftotree {__version__}")
meta = doc.createElement("meta")
head.appendChild(meta)
meta.setAttribute("name", "ocr-capabilities")
meta.setAttribute("content",
"ocr_page ocr_table ocrx_block ocrx_line ocrx_word")
meta = doc.createElement("meta")
head.appendChild(meta)
meta.setAttribute("name", "ocr-number-of-pages")
meta.setAttribute("content", f"{len(self.elems.keys())}")
# body
body = doc.createElement("body")
html.appendChild(body)
for page_num in self.elems.keys(): # 1-based
boxes: List[Tuple[str, float, float, float, float]] = []
for clust in self.tree[page_num]:
for (pnum, pwidth, pheight, top, left, bottom,
right) in self.tree[page_num][clust]:
boxes += [(clust.lower().replace(" ", "_"), top, left,
bottom, right)]
page = doc.createElement("div")
page.setAttribute("class", "ocr_page")
page.setAttribute("id", f"page_{page_num}")
width = int(self.elems[page_num].layout.width)
height = int(self.elems[page_num].layout.height)
page.setAttribute(
"title",
f"bbox 0 0 {width} {height}; ppageno {page_num-1}",
)
body.appendChild(page)
# TODO: We need to detect columns and sort acccordingly.
boxes.sort(key=cmp_to_key(column_order))
for box in boxes:
if box[0] == "table":
table = box[1:] # bbox
table_element = self.get_html_table(table, page_num)
page.appendChild(table_element)
elif box[0] == "figure":
elems: List[LTTextLine] = get_mentions_within_bbox(
box, self.elems[page_num].figures)
fig_element = doc.createElement("figure")
page.appendChild(fig_element)
top, left, bottom, right = [int(i) for i in box[1:]]
fig_element.setAttribute(
"title", f"bbox {left} {top} {right} {bottom}")
for img in [img for elem in elems for img in elem]:
if not isinstance(img, LTImage):
continue
filename = imagewriter.export_image(img)
with open(os.path.join(dirname, filename), "rb") as f:
base64 = b64encode(f.read()).decode("ascii")
if filename.endswith("jpg"):
mediatype = "jpeg"
elif filename.endswith("bmp"):
mediatype = "bmp"
else:
logger.info(
f"Skipping an unknown type image: {filename}.")
continue
logger.info(
f"Embedding a known type image: {filename}.")
img_element = doc.createElement("img")
fig_element.appendChild(img_element)
img_element.setAttribute("title", bbox2str(img.bbox))
img_element.setAttribute(
"src", f"data:image/{mediatype};base64,{base64}")
else:
element = self.get_html_others(box[0], box[1:], page_num)
page.appendChild(element)
return doc.toprettyxml()
def convert(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] [-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 = 'inputs/' + sys.argv[1].replace(' ', '')[:-4] + '.txt'
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('pdfs/' + 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()
#read converted file
y = open("inputs/" + sys.argv[1].replace(' ', '')[:-4] + '.txt', "r")
output = brl.translate(y.read())
#convert into Grade 2 Braille unicode
x = brl.toUnicodeSymbols(output, flatten=True)
#save to results folder in .txt format
text_file = open(
"results/" + sys.argv[1].replace(' ', '')[:-4] + "-Braille.txt", "w")
text_file.write(x.encode(codec))
text_file.close()
def main(argv):
import getopt
def usage():
print ('usage: %s [-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 ...' % argv[0])
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()
pages_text = []
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
#
retstr = io.StringIO()
rsrcmgr = PDFResourceManager(caching=caching)
device = TextConverter(rsrcmgr, retstr, laparams=laparams,imagewriter=imagewriter)
data = []
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):
interpreter.process_page(page)
data = retstr.getvalue()
#print(data)
data=data.replace("\xa0", "")
data=data.replace("\uf0da", "")
data=data.replace("\x0c", "")
data=data.replace("• ", "")
data=data.replace("* ", "")
data=data.replace("(LinkedIn)", "")
data=data.replace(" (LinkedIn)", "")
data=data.replace("\uf0a7", "")
data=data.replace("(Mobile)", "")
data=data.replace("- ", "")
result_list=data.split('\n')
#print(result_list)
skills=[]
languages=[]
summary=[]
certifications=[]
contact=[]
linkedin=[]
experience=[]
education=[]
exp_dict={}
edu_dict={}
for i in result_list:
if i=='Contact':
value=result_list.index(i)
while True:
contact.append(result_list[value].strip())
value=value+1
if result_list[value] =='':
break
if i.__contains__('www.linkedin.com'):
value=result_list.index(i)
while True:
linkedin.append(result_list[value])
value=value+1
if result_list[value] =='':
break
if len(linkedin)>=2:
ln=[]
merged=linkedin[0]+linkedin[1].strip()
ln.append(merged)
linkedin=ln
if i=='Top Skills':
value=result_list.index(i)
while True:
skills.append(result_list[value])
value=value+1
if result_list[value] =='':
break
if i.__contains__('Certifications'):
value=result_list.index(i)
while True:
certifications.append(result_list[value])
value=value+1
if result_list[value] =='':
break
if i.__contains__('Summary'):
value=result_list.index(i)
while True:
summary.append(result_list[value])
value=value+1
if result_list[value] =='':
break
if i=='Languages':
value=result_list.index(i)
while True:
languages.append(result_list[value])
value=value+1
if result_list[value] =='':
break
if i=='Experience':
value=result_list.index(i)
value=value+2
while True:
experience.append(result_list[value])
value=value+1
a=str(result_list[value])
if a.__contains__('-'):
k=a.split('-')
print('start:',k[0],'end:',k[1])
break
elif result_list[value] =='':
break
listOfExp = ["company", "position","period","place","description" ]
zipbObj = zip(listOfExp, experience)
exp_dict = dict(zipbObj)
if i=='Education':
value=result_list.index(i)
value=value+1
while True:
education.append(result_list[value])
value=value+1
# a=str(result_list[value])
# if a.__contains__('-'):
# k=a.split('-')
# print('start:',k[0],'end:',k[1])
# break
if result_list[value] =='':
break
listOfEdu = ["school", "degree" ]
zipbObj = zip(listOfEdu, education)
edu_dict = dict(zipbObj)
# print(languages)
print('###############')
print(contact,'\n',linkedin,'\n',summary,'\n',skills,'\n',certifications,'\n',languages,'\n',exp_dict,'\n',edu_dict)
#print(data.splitlines())
device.close()
retstr.close()
return
def extract_text(
files=[],
outfile='-',
_py2_no_more_posargs=None, # Bloody Python2 needs a shim
no_laparams=False,
all_texts=None,
detect_vertical=None, # LAParams
word_margin=None,
char_margin=None,
line_margin=None,
boxes_flow=None, # LAParams
output_type='text',
codec='utf-8',
strip_control=False,
maxpages=0,
page_numbers=None,
password="",
scale=1.0,
rotation=0,
layoutmode='normal',
output_dir=None,
debug=False,
disable_caching=False,
**other):
if _py2_no_more_posargs is not None:
raise ValueError("Too many positional arguments passed.")
if not files:
raise ValueError("Must provide files to work upon!")
# If any LAParams group arguments were passed, create an LAParams object and
# populate with given args. Otherwise, set it to None.
if not no_laparams:
laparams = pdfminer.layout.LAParams()
for param in ("all_texts", "detect_vertical", "word_margin",
"char_margin", "line_margin", "boxes_flow"):
paramv = locals().get(param, None)
if paramv is not None:
setattr(laparams, param, paramv)
else:
laparams = None
imagewriter = None
if output_dir:
imagewriter = ImageWriter(output_dir)
if output_type == "text" and outfile != "-":
for override, alttype in ((".htm", "html"), (".html", "html"),
(".xml", "xml"), (".tag", "tag")):
if outfile.endswith(override):
output_type = alttype
if outfile == "-":
outfp = sys.stdout
if outfp.encoding is not None:
codec = 'utf-8'
else:
outfp = open(outfile, "wb")
for fname in files:
with open(fname, "rb") as infp:
# pdfminer.high_level.extract_text_to_fp(fp, **locals())
rsrcmgr = PDFResourceManager_new(caching=not disable_caching)
device = TextConverter(rsrcmgr,
outfp,
codec=codec,
laparams=laparams,
imagewriter=imagewriter)
if outfp == sys.stdout:
outfp = sys.stdout.buffer
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.get_pages(infp,
page_numbers,
maxpages=maxpages,
password=password,
caching=not disable_caching,
check_extractable=True):
page.rotate = (page.rotate + rotation) % 360
interpreter.process_page(page)
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.get_pages(infp):
interpreter.process_page(page)
# receive the LTPage object for the page.
layout = device.get_result()
for element in layout:
if isinstance(element, LTTextBoxHorizontal):
print(element.get_text())
return outfp