I'm using the code below to read a pdf document, and it has no line feeds
or carriage returns in the imported text. I'm therefore trying to just
replace the symbol that looks like it would be an end of line (found by
examining the characters in the "for loop") unichr(167).
Unfortunately, the replace isn't working, does anyone know what I'm
doing wrong? I tried a number of things so I left comments in place as a
subset of the bunch of things I tried to no avail.
Any help?
Kurt
#!/usr/bin/python
# -*- coding: utf-8 -+-
from pyPdf import PdfFileWriter, PdfFileReader
import unicodedata
fileencoding = "utf-16-LE" #"iso-8859-1" # "utf-8"
doc = PdfFileReader(file(r"C:\Documents and Settings\kpeters\My Documents
\SUA.pdf", "rb")
# print the title of document1.pdf
print "title = %s" % (doc.getDocumentInfo().title)
print "Subject:", doc.getDocumentInfo().subject
print "PDF Version:", doc.getDocumentInfo().producer
page4 = doc.getPage(3)
textu= page4.extractText()
#textu=textu.decode(fileencoding)
print type(textu)
#print type(textu.encode(fileencoding))
#textu=textu.encode(fileencoding) #Converts to str
fn = unichr(167)
print('The char is %s' % fn)
textu.replace(unichr(167),'\n')
#print unicodedata.bidirectional(fn) unichr(167)
for i, c in enumerate(textu):
if (i!=302):
print('# %d has char %s, ord: %d , char: %s, category %s, and
Name: %s' % (i, c, ord(c), unichr(ord(c)), unicodedata.category(c),
unicodedata.name(c)))
#if (ord(c)==167):
# print('Found it!')
#textu[i]='\n'
print('----------------------------------------------------')
print textu
print textu.encode(fileencoding)
--
http://mail.python.org/mailman/listinfo/python-list
