def convert(self, data):
# convert binary pdf data into a file like structure
pdfdata = StringIO(data)
# I have no idea why this is needed
CMapDB.initialize('CMap', 'CDBCMap')
# create the converter and resource manager
rsrc = PDFResourceManager()
converter = TextConverter(rsrc)
# setup the parser
doc = PDFDocument()
parser = PDFParser(doc, pdfdata)
# initialize the pdf
try:
# use empty password
doc.initialize('')
except PDFPasswordIncorrect:
return ''
# check if we can extract the contents of this file
if not doc.is_extractable:
return ''
# do the conversion
interpreter = PDFPageInterpreter(rsrc, converter)
for page in doc.get_pages():
interpreter.process_page(page)
converter.close()
pdfdata.close()
return converter.get_text()
def convert(self, data):
# convert binary pdf data into a file like structure
pdfdata = StringIO(data)
# I have no idea why this is needed
CMapDB.initialize('CMap', 'CDBCMap')
# create the converter and resource manager
rsrc = PDFResourceManager()
converter = TextConverter(rsrc)
# setup the parser
doc = PDFDocument()
parser = PDFParser(doc, pdfdata)
# initialize the pdf
try:
# use empty password
doc.initialize('')
except PDFPasswordIncorrect:
return ''
# check if we can extract the contents of this file
if not doc.is_extractable:
return ''
# do the conversion
interpreter = PDFPageInterpreter(rsrc, converter)
for page in doc.get_pages():
interpreter.process_page(page)
converter.close()
pdfdata.close()
return converter.get_text()
def main(argv):
import getopt
def usage():
print 'usage: %s [-d] [-p pagenos] [-P password] [-c codec] [-t html|sgml|tag] [-o output] file ...' % argv[
0]
return 100
try:
(opts, args) = getopt.getopt(argv[1:], 'dp:P:c:t:o:C:D:m:')
except getopt.GetoptError:
return usage()
if not args: return usage()
debug = 0
cmapdir = 'CMap'
cdbcmapdir = 'CDBCMap'
codec = 'ascii'
pagenos = set()
maxpages = 0
outtype = 'html'
password = ''
outfp = stdout
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 == '-P': password = v
elif k == '-c': codec = v
elif k == '-m': maxpages = int(v)
elif k == '-C': cmapdir = v
elif k == '-D': cdbcmapdir = v
elif k == '-t': outtype = v
elif k == '-o': outfp = file(v, 'wb')
#
CMapDB.debug = debug
PDFResourceManager.debug = debug
PDFDocument.debug = debug
PDFParser.debug = debug
PDFPageInterpreter.debug = debug
#
CMapDB.initialize(cmapdir, cdbcmapdir)
rsrc = PDFResourceManager()
if outtype == 'sgml':
device = SGMLConverter(rsrc, outfp, codec)
elif outtype == 'html':
device = HTMLConverter(rsrc, outfp, codec)
elif outtype == 'tag':
device = TagExtractor(rsrc, outfp, codec)
else:
return usage()
for fname in args:
convert(rsrc,
device,
fname,
pagenos,
maxpages=maxpages,
password=password)
return
def main(argv):
import getopt
def usage():
print 'usage: %s [-d] [-p pagenos] [-P password] [-c codec] [-t html|sgml|tag] [-o output] file ...' % argv[0]
return 100
try:
(opts, args) = getopt.getopt(argv[1:], 'dp:P:c:t:o:C:D:m:')
except getopt.GetoptError:
return usage()
if not args: return usage()
debug = 0
cmapdir = 'CMap'
cdbcmapdir = 'CDBCMap'
codec = 'ascii'
pagenos = set()
maxpages = 0
outtype = 'html'
password = ''
outfp = stdout
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 == '-P': password = v
elif k == '-c': codec = v
elif k == '-m': maxpages = int(v)
elif k == '-C': cmapdir = v
elif k == '-D': cdbcmapdir = v
elif k == '-t': outtype = v
elif k == '-o': outfp = file(v, 'wb')
#
CMapDB.debug = debug
PDFResourceManager.debug = debug
PDFDocument.debug = debug
PDFParser.debug = debug
PDFPageInterpreter.debug = debug
#
CMapDB.initialize(cmapdir, cdbcmapdir)
rsrc = PDFResourceManager()
if outtype == 'sgml':
device = SGMLConverter(rsrc, outfp, codec)
elif outtype == 'html':
device = HTMLConverter(rsrc, outfp, codec)
elif outtype == 'tag':
device = TagExtractor(rsrc, outfp, codec)
else:
return usage()
for fname in args:
convert(rsrc, device, fname, pagenos,
maxpages=maxpages, password=password)
return
