def docx_to_pdf(infilename, outfilename):
# Extract the text from the DOCX file object infile and write it to
# a PDF file.
try:
infil = opendocx(infilename)
except:
print("Error opening infilename")
#print "Exception: " + repr(e) + "\n"
sys.exit(1)
paragraphs = getdocumenttext(infil)
pw = PDFWriter(outfilename)
pw.setFont("Courier", 12)
pw.setHeader("DOCXtoPDF - convert text in DOCX file to PDF")
pw.setFooter("Generated by xtopdf and python-docx")
wrapper = TextWrapper(width=70, drop_whitespace=False)
# For Unicode handling.
new_paragraphs = []
for paragraph in paragraphs:
new_paragraphs.append(paragraph.encode("utf-8"))
for paragraph in new_paragraphs:
lines = wrapper.wrap(paragraph)
for line in lines:
pw.writeLine(line)
pw.writeLine("")
pw.savePage()
pw.close()
def text_to_pdf(txt_filename):
pw = PDFWriter(txt_filename + '.pdf')
pw.setFont('Courier', 12)
pw.setHeader('{} converted to PDF'.format(txt_filename))
pw.setFooter('PDF conversion by xtopdf: https://google.com/search?q=xtopdf')
with open(txt_filename) as txt_fil:
for line in txt_fil:
pw.writeLine(line.strip('\n'))
pw.savePage()
def text_to_pdf(txt_filename):
pw = PDFWriter(txt_filename + '.pdf')
pw.setFont('Courier', 12)
pw.setHeader('{} converted to PDF'.format(txt_filename))
pw.setFooter(
'PDF conversion by xtopdf: https://google.com/search?q=xtopdf')
with open(txt_filename) as txt_fil:
for line in txt_fil:
pw.writeLine(line.strip('\n'))
pw.savePage()
def pdf_book():
if request.method == 'GET':
# Display the PDF book creation form.
return '''
<form action="/pdf_book" method="post">
PDF file name: <input type="text" name="pdf_file_name" />
Header: <input type="text" name="header" />
Footer: <input type="text" name="footer" />
Content:
<textarea name="content" rows="15" cols="50"></textarea>
<input type="submit" value="Submit" />
</form>
'''
else:
# Create the PDF book from the posted form content.
try:
# Get the needed fields from the form.
pdf_file_name = request.form['pdf_file_name']
header = request.form['header']
footer = request.form['footer']
content = request.form['content']
# Create a PDFWriter instance and set some of its fields.
pw = PDFWriter(pdf_file_name)
pw.setFont("Courier", 12)
pw.setHeader(header)
pw.setFooter(footer)
# Get the content field.
# Split it into paragraphs delimited by newlines.
# Convert each paragraph into a list of lines of
# maximum width 70 characters.
# Print each line to the PDF file.
paragraphs = content.split('\n')
wrapper = TextWrapper(width=70, drop_whitespace=False)
for paragraph in paragraphs:
lines = wrapper.wrap(paragraph)
for line in lines:
pw.writeLine(line)
pw.savePage()
pw.close()
return "OK. PDF book created in file " + pdf_file_name + ".\n"
except Exception, e:
traceback.print_stack()
return "Error: PDF book not created.\n" + repr(e) + ".\n"
def pdf_book():
if request.method == 'GET':
# Display the PDF book creation form.
return '''
<form action="/pdf_book" method="post">
PDF file name: <input type="text" name="pdf_file_name" />
Header: <input type="text" name="header" />
Footer: <input type="text" name="footer" />
Content:
<textarea name="content" rows="15" cols="50"></textarea>
<input type="submit" value="Submit" />
</form>
'''
else:
# Create the PDF book from the posted form content.
try:
# Get the needed fields from the form.
pdf_file_name = request.form['pdf_file_name']
header = request.form['header']
footer = request.form['footer']
content = request.form['content']
# Create a PDFWriter instance and set some of its fields.
pw = PDFWriter(pdf_file_name)
pw.setFont("Courier", 12)
pw.setHeader(header)
pw.setFooter(footer)
# Get the content field.
# Split it into paragraphs delimited by newlines.
# Convert each paragraph into a list of lines of
# maximum width 70 characters.
# Print each line to the PDF file.
paragraphs = content.split('\n')
wrapper = TextWrapper(width=70, drop_whitespace=False)
for paragraph in paragraphs:
lines = wrapper.wrap(paragraph)
for line in lines:
pw.writeLine(line)
pw.savePage()
pw.close()
return "OK. PDF book created in file " + pdf_file_name + ".\n"
except Exception, e:
traceback.print_stack()
return "Error: PDF book not created.\n" + repr(e) + ".\n"
def main():
if len(sys.argv) < 3:
usage(sys.argv[0])
sys.exit(0)
try:
pw = PDFWriter(sys.argv[1])
pw.setFont('Courier', 12)
pw.setFooter('xtopdf: https://google.com/search?q=xtopdf')
for line in fileinput.input(sys.argv[2:]):
if fileinput.filelineno() == 1:
pw.setHeader(fileinput.filename())
if fileinput.lineno() != 1:
pw.savePage()
pw.writeLine(line.strip('\n'))
pw.savePage()
pw.close()
except Exception as e:
print("Caught Exception: type: {}, message: {}".format(\
e.__class__, str(e)))
def main():
# Create some HTML for testing conversion of its text to PDF.
html_doc = """
<html>
<head>
<title>
Test file for HTMLTextToPDF
</title>
</head>
<body>
This is text within the body element but outside any paragraph.
<p>
This is a paragraph of text. Hey there, how do you do?
The quick red fox jumped over the slow blue cow.
</p>
<p>
This is another paragraph of text.
Don't mind what it contains.
What is mind? Not matter.
What is matter? Never mind.
</p>
This is also text within the body element but not within any paragraph.
</body>
</html>
"""
pw = PDFWriter("HTMLTextTo.pdf")
pw.setFont("Courier", 10)
pw.setHeader("Conversion of HTML text to PDF")
pw.setFooter("Generated by xtopdf: http://slid.es/vasudevram/xtopdf")
# Use method chaining this time.
for line in BeautifulSoup(html_doc).get_text().split("\n"):
pw.writeLine(line)
pw.savePage()
pw.close()
def main():
# Create some HTML for testing conversion of its text to PDF.
html_doc = """
<html>
<head>
<title>
Test file for HTMLTextToPDF
</title>
</head>
<body>
This is text within the body element but outside any paragraph.
<p>
This is a paragraph of text. Hey there, how do you do?
The quick red fox jumped over the slow blue cow.
</p>
<p>
This is another paragraph of text.
Don't mind what it contains.
What is mind? Not matter.
What is matter? Never mind.
</p>
This is also text within the body element but not within any paragraph.
</body>
</html>
"""
pw = PDFWriter("HTMLTextTo.pdf")
pw.setFont("Courier", 10)
pw.setHeader("Conversion of HTML text to PDF")
pw.setFooter("Generated by xtopdf: http://slid.es/vasudevram/xtopdf")
# Use method chaining this time.
for line in BeautifulSoup(html_doc).get_text().split("\n"):
pw.writeLine(line)
pw.savePage()
pw.close()
pw.setHeader("DOCXtoPDF - convert text in DOCX file to PDF")
pw.setFooter("Generated by xtopdf and python-docx")
wrapper = TextWrapper(width=70, drop_whitespace=False)
# For Unicode handling.
new_paragraphs = []
for paragraph in paragraphs:
new_paragraphs.append(paragraph.encode("utf-8"))
for paragraph in new_paragraphs:
lines = wrapper.wrap(paragraph)
for line in lines:
pw.writeLine(line)
pw.writeLine("")
pw.savePage()
pw.close()
def usage():
return "Usage: python DOCXtoPDF.py infile.docx outfile.txt\n"
def main():
try:
# Check for correct number of command-line arguments.
if len(sys.argv) != 3:
print "Wrong number of arguments"
print usage()
sys.exit(1)
infilename = sys.argv[1]
def main():
'''Main program to test DBFReader class.
'''
# check for right num. of args
if (len(sys.argv) != 3):
usage()
sys.exit(1)
# extract dbf and pdf filenames from args
dbf_fn = sys.argv[1]
pdf_fn = sys.argv[2]
# create and open the DBFReader instance
dr = DBFReader(dbf_fn)
dr.open()
# create the PDFWriter instance
pw = PDFWriter(pdf_fn)
# and set some of its fields
# set the font
pw.setFont("Courier", 10)
# set the page header
gen_datetime = time.asctime()
pw.setHeader("Generated by DBFtoPDF: Input: " + dbf_fn + \
" At: " + gen_datetime)
# set the page footer
pw.setFooter("Generated by DBFtoPDF: Input: " + dbf_fn + \
" At: " + gen_datetime)
# create the separator for logical grouping of output
sep = "=" * 60
# get the DBF file header
file_header = dr.read_dbf_file_header()
# print a separator line
pw.writeLine(sep)
# print title for the overall output
pw.writeLine("Information for DBF file: %s" % (dbf_fn))
# print a separator line
pw.writeLine(sep)
# print the file header section title
pw.writeLine("")
pw.writeLine("File Header Information:")
# print a separator line
pw.writeLine(sep)
# setup labels for file header output
lbl_dbf_ver = \
"DBF version (signature) : "
lbl_last_update = \
"Date of last update (YY/MM/DD): "
lbl_num_recs = \
"Number of data records : "
lbl_hdr_len = \
"DBF header length in bytes : "
lbl_rec_len = \
"DBF record length in bytes : "
lbl_num_flds = \
"Number of fields in DBF file : "
# print the file header metadata with labels
pw.writeLine(lbl_dbf_ver + str(file_header['ver']))
pw.writeLine(lbl_last_update + file_header['last_update'])
pw.writeLine(lbl_num_recs + str(file_header['num_recs']))
pw.writeLine(lbl_hdr_len + str(file_header['hdr_len']))
pw.writeLine(lbl_rec_len + str(file_header['rec_len']))
pw.writeLine(lbl_num_flds + str(file_header['num_flds']))
# print a separator line
pw.writeLine(sep)
# save current page
pw.savePage()
# print the field headers section title
pw.writeLine("Field Header Information:")
# print a separator line
pw.writeLine(sep)
# print labels for field headers output
pw.writeLine("%3s%13s%7s%8s%10s" % \
("#", "Field name", "Type", "Length", "Decimals"))
# print a separator line
pw.writeLine(sep)
# get num. of fields from file header
num_flds = file_header["num_flds"]
# get the field headers
field_headers = dr.read_dbf_field_headers()
# extract individual lists from the field headers list of lists
fld_nam, fld_typ, fld_len, fld_dec = (
field_headers[0],
field_headers[1],
field_headers[2],
field_headers[3] )
fld_num = 0
# print the field headers metadata
while (fld_num < num_flds):
s1 = "%3s" % (fld_num + 1)
s2 = "%13s" % (fld_nam[fld_num])
#s3 = "%4s" % (string.replace(fld_typ[fld_num], '\0', ' ')) ,
s3 = "%4s" % (fld_typ[fld_num])
s4 = "%5s" % (fld_len[fld_num])
s5 = "%7s" % (fld_dec[fld_num])
s = s1 + " " + s2 + " " + s3 + " " + s4 + " " + s5
pw.writeLine(s)
fld_num = fld_num + 1
# print a separator line
pw.writeLine(sep)
# save current page
pw.savePage()
# position the DBFReader instance to start reading data records
dr.reset()
# print the data records section title
pw.writeLine("DBF Data Records:")
# print a separator line
pw.writeLine(sep)
# print the data records
rec_num = 0
while (dr.has_next_record()):
rec_num = rec_num + 1
# get next data record from the DBFReader
r = dr.next_record()
# convert it from a list to a human-friendly string
fr = dbf_record_to_string(r)
# the serial num. of the record
s1 = "%7d:" % (rec_num)
# the record itself
s2 = "%s" % (fr)
# serial num. + record
s = s1 + " " + s2
# print the record
pw.writeLine(s)
# print a separator line
pw.writeLine(sep)
# save current page
pw.savePage()
# close the DBFReader
dr.close()
# close the PDFWriter
pw.close()
def XMLtoPDFBook():
debug("Entered XMLtoPDFBook()")
global sysargv
# Get command-line arguments.
xml_filename = get_xml_filename(sysargv)
debug("xml_filename: " + xml_filename)
pdf_filename = get_pdf_filename(sysargv)
debug("pdf_filename: " + pdf_filename)
# Parse the XML file.
try:
tree = ET.ElementTree(file=xml_filename)
debug("tree = " + repr(tree))
except Exception:
sys.stderr.write("Error: caught exception in ET.ElementTree(file)")
sys.exit(1)
# Get the tree root.
root = tree.getroot()
debug("root.tag = " + root.tag)
if root.tag != "book":
debug("Error: Root tag is not 'book'")
sys.exit(1)
# Initialize the table of contents list.
toc = []
# Initialize the chapters list.
chapters = []
# Traverse the tree, extracting needed data into variables.
debug("-" * 60)
for root_child in root:
if root_child.tag != "chapter":
debug("Error: root_child tag is not 'chapter'")
sys.exit(1)
chapter = root_child
#debug(chapter.text)
chapters.append(chapter.text)
try:
chapter_name = chapter.attrib['name']
except KeyError:
chapter_name = ""
toc.append(chapter_name)
debug("-" * 60)
# Create and set some fields of a PDFWriter.
pw = PDFWriter(pdf_filename)
pw.setFont("Courier", 12)
pw.setFooter("Generated by XMLtoPDFBook. Copyright 2013 Vasudev Ram")
# Write the TOC.
pw.setHeader("Table of Contents")
chapter_num = 0
debug("Chapter names")
for chapter_name in toc:
debug(chapter_name)
chapter_num += 1
pw.writeLine(str(chapter_num) + ": " + chapter_name)
pw.savePage()
# Write the chapters.
chapter_num = 0
for chapter in chapters:
chapter_num += 1
pw.setHeader("Chapter " + str(chapter_num) + ": " +
toc[chapter_num - 1])
lines = chapter.split("\n")
for line in lines:
pw.writeLine(line)
pw.savePage()
pw.close()
debug("Exiting XMLtoPDFBook()")
def main():
'''Main program to test DBFReader class.
'''
# check for right num. of args
if (len(sys.argv) != 3):
usage()
sys.exit(1)
# extract dbf and pdf filenames from args
dbf_fn = sys.argv[1]
pdf_fn = sys.argv[2]
# create and open the DBFReader instance
dr = DBFReader(dbf_fn)
dr.open()
# create the PDFWriter instance
pw = PDFWriter(pdf_fn)
# and set some of its fields
# set the font
pw.setFont("Courier", 10)
# set the page header
gen_datetime = time.asctime()
pw.setHeader("Generated by DBFtoPDF: Input: " + dbf_fn + \
" At: " + gen_datetime)
# set the page footer
pw.setFooter("Generated by DBFtoPDF: Input: " + dbf_fn + \
" At: " + gen_datetime)
# create the separator for logical grouping of output
sep = "=" * 60
# get the DBF file header
file_header = dr.read_dbf_file_header()
# print a separator line
pw.writeLine(sep)
# print title for the overall output
pw.writeLine("Information for DBF file: %s" % (dbf_fn))
# print a separator line
pw.writeLine(sep)
# print the file header section title
pw.writeLine("")
pw.writeLine("File Header Information:")
# print a separator line
pw.writeLine(sep)
# setup labels for file header output
lbl_dbf_ver = \
"DBF version (signature) : "
lbl_last_update = \
"Date of last update (YY/MM/DD): "
lbl_num_recs = \
"Number of data records : "
lbl_hdr_len = \
"DBF header length in bytes : "
lbl_rec_len = \
"DBF record length in bytes : "
lbl_num_flds = \
"Number of fields in DBF file : "
# print the file header metadata with labels
pw.writeLine(lbl_dbf_ver + str(file_header['ver']))
pw.writeLine(lbl_last_update + file_header['last_update'])
pw.writeLine(lbl_num_recs + str(file_header['num_recs']))
pw.writeLine(lbl_hdr_len + str(file_header['hdr_len']))
pw.writeLine(lbl_rec_len + str(file_header['rec_len']))
pw.writeLine(lbl_num_flds + str(file_header['num_flds']))
# print a separator line
pw.writeLine(sep)
# save current page
pw.savePage()
# print the field headers section title
pw.writeLine("Field Header Information:")
# print a separator line
pw.writeLine(sep)
# print labels for field headers output
pw.writeLine("%3s%13s%7s%8s%10s" % \
("#", "Field name", "Type", "Length", "Decimals"))
# print a separator line
pw.writeLine(sep)
# get num. of fields from file header
num_flds = file_header["num_flds"]
# get the field headers
field_headers = dr.read_dbf_field_headers()
# extract individual lists from the field headers list of lists
fld_nam, fld_typ, fld_len, fld_dec = (field_headers[0], field_headers[1],
field_headers[2], field_headers[3])
fld_num = 0
# print the field headers metadata
while (fld_num < num_flds):
s1 = "%3s" % (fld_num + 1)
s2 = "%13s" % (fld_nam[fld_num])
#s3 = "%4s" % (string.replace(fld_typ[fld_num], '\0', ' ')) ,
s3 = "%4s" % (fld_typ[fld_num])
s4 = "%5s" % (fld_len[fld_num])
s5 = "%7s" % (fld_dec[fld_num])
s = s1 + " " + s2 + " " + s3 + " " + s4 + " " + s5
pw.writeLine(s)
fld_num = fld_num + 1
# print a separator line
pw.writeLine(sep)
# save current page
pw.savePage()
# position the DBFReader instance to start reading data records
dr.reset()
# print the data records section title
pw.writeLine("DBF Data Records:")
# print a separator line
pw.writeLine(sep)
# print the data records
rec_num = 0
while (dr.has_next_record()):
rec_num = rec_num + 1
# get next data record from the DBFReader
r = dr.next_record()
# convert it from a list to a human-friendly string
fr = dbf_record_to_string(r)
# the serial num. of the record
s1 = "%7d:" % (rec_num)
# the record itself
s2 = "%s" % (fr)
# serial num. + record
s = s1 + " " + s2
# print the record
pw.writeLine(s)
# print a separator line
pw.writeLine(sep)
# save current page
pw.savePage()
# close the DBFReader
dr.close()
# close the PDFWriter
pw.close()
