')
@@ -162,9 +183,12 @@ def resolve_dest(dest):
parser.close()
return
+
# extractembedded
LITERAL_FILESPEC = LIT('Filespec')
LITERAL_EMBEDDEDFILE = LIT('EmbeddedFile')
+
+
def extractembedded(outfp, fname, objids, pagenos, password=b'',
dumpall=False, mode=None, extractdir=None):
def extract1(obj):
@@ -177,8 +201,9 @@ def extract1(obj):
(filename))
if fileobj.get('Type') is not LITERAL_EMBEDDEDFILE:
raise PDFValueError(
- 'unable to process PDF: reference for %r is not an EmbeddedFile' %
- (filename))
+ 'unable to process PDF: reference for %r is \
+ not an EmbeddedFile' % filename
+ )
path = os.path.join(extractdir, filename)
if os.path.exists(path):
raise IOError('file exists: %r' % path)
@@ -193,10 +218,14 @@ def extract1(obj):
for xref in doc.xrefs:
for objid in xref.get_objids():
obj = doc.getobj(objid)
- if isinstance(obj, dict) and obj.get('Type') is LITERAL_FILESPEC:
+ if (
+ isinstance(obj, dict) and
+ obj.get('Type') is LITERAL_FILESPEC
+ ):
extract1(obj)
return
+
# dumppdf
def dumppdf(outfp, fname, objids, pagenos, password=b'',
dumpall=False, mode=None, extractdir=None):
@@ -208,7 +237,7 @@ def dumppdf(outfp, fname, objids, pagenos, password=b'',
obj = doc.getobj(objid)
dumpxml(outfp, obj, mode=mode)
if pagenos:
- for (pageno,page) in enumerate(PDFPage.create_pages(doc)):
+ for (pageno, page) in enumerate(PDFPage.create_pages(doc)):
if pageno in pagenos:
if mode is not None:
for obj in page.contents:
@@ -220,23 +249,28 @@ def dumppdf(outfp, fname, objids, pagenos, password=b'',
dumpallobjs(outfp, doc, mode=mode)
if (not objids) and (not pagenos) and (not dumpall):
dumptrailers(outfp, doc)
- if mode not in ('raw','binary'):
+ if mode not in ('raw', 'binary'):
outfp.write('\n')
return
# main
def main(argv):
- import getopt
- def usage():
- print(f'usage: {argv[0]} [-P password] [-a] [-p pageid] [-i objid] [-o output] '
- '[-r|-b|-t] [-T] [-O output_dir] [-d] input.pdf ...')
- return 100
- try:
- (opts, args) = getopt.getopt(argv[1:], 'dP:ap:i:o:rbtTO:')
- except getopt.GetoptError:
- return usage()
- if not args: return usage()
+ parser = argparse.ArgumentParser()
+ parser.add_argument('input', metavar='input.pdf', nargs='+')
+ parser.add_argument('-P', '--password')
+ parser.add_argument('-a', '--dump-all-text', action='store_true')
+ parser.add_argument('-p', '--page-id', action='store')
+ parser.add_argument('-i', '--object-id', action='store')
+ parser.add_argument('-o', '--output')
+ parser.add_argument('-r', '--raw', action='store_true')
+ parser.add_argument('b', '--binary', action='store_true')
+ parser.add_argument('-t', '--text', action='store_true')
+ parser.add_argument('-T', '--dumpoutline', action='store_true')
+ parser.add_argument('-O', '--output-dir')
+ parser.add_argument('-d', '--debug', action='store_true')
+ args = parser.parse_args()
+
debug = 0
objids = []
pagenos = set()
@@ -246,21 +280,30 @@ def usage():
proc = dumppdf
outfp = sys.stdout
extractdir = None
- for (k, v) in opts:
- if k == '-d': debug += 1
- elif k == '-P': password = v.encode('ascii')
- elif k == '-a': dumpall = True
- elif k == '-p': pagenos.update( int(x)-1 for x in v.split(',') )
- elif k == '-i': objids.extend( int(x) for x in v.split(',') )
- elif k == '-o': outfp = open(v, 'wb')
- elif k == '-r': mode = 'raw'
- elif k == '-b': mode = 'binary'
- elif k == '-t': mode = 'text'
- elif k == '-T': proc = dumpoutline
- elif k == '-O':
- extractdir = v
- proc = extractembedded
- #
+ if args.debug:
+ debug += 1
+ elif args.password:
+ password = args.password.encode('ascii')
+ elif args.dump_all_text:
+ dumpall = True
+ elif args.page_id:
+ pagenos.update(int(x)-1 for x in args.page_id.split(','))
+ elif args.object_id:
+ objids.extend(int(x) for x in args.object_id.split(','))
+ elif args.output:
+ outfp = open(args.output, 'wb')
+ elif args.raw:
+ mode = 'raw'
+ elif args.binary:
+ mode = 'binary'
+ elif args.text:
+ mode = 'text'
+ elif args.dumpoutline:
+ proc = dumpoutline
+ elif args.output_dir:
+ extractdir = args.output_dir
+ proc = extractembedded
+
PDFDocument.debug = debug
PDFParser.debug = debug
#
@@ -269,4 +312,6 @@ def usage():
dumpall=dumpall, mode=mode, extractdir=extractdir)
return
-if __name__ == '__main__': sys.exit(main(sys.argv))
+
+if __name__ == '__main__':
+ sys.exit(main(sys.argv))
diff --git a/tools/latin2ascii.py b/tools/latin2ascii.py
index 9bd6552d..9857abc5 100755
--- a/tools/latin2ascii.py
+++ b/tools/latin2ascii.py
@@ -12,105 +12,108 @@
"""
LATIN2ASCII = {
- #0x00a0: '',
- #0x00a7: '',
-
- # iso-8859-1
- 0x00c0: 'A`',
- 0x00c1: "A'",
- 0x00c2: 'A^',
- 0x00c3: 'A~',
- 0x00c4: 'A:',
- 0x00c5: 'A%',
- 0x00c6: 'AE',
- 0x00c7: 'C,',
- 0x00c8: 'E`',
- 0x00c9: "E'",
- 0x00ca: 'E^',
- 0x00cb: 'E:',
- 0x00cc: 'I`',
- 0x00cd: "I'",
- 0x00ce: 'I^',
- 0x00cf: 'I:',
- 0x00d0: "D'",
- 0x00d1: 'N~',
- 0x00d2: 'O`',
- 0x00d3: "O'",
- 0x00d4: 'O^',
- 0x00d5: 'O~',
- 0x00d6: 'O:',
- 0x00d8: 'O/',
- 0x00d9: 'U`',
- 0x00da: "U'",
- 0x00db: 'U~',
- 0x00dc: 'U:',
- 0x00dd: "Y'",
- 0x00df: 'ss',
-
- 0x00e0: 'a`',
- 0x00e1: "a'",
- 0x00e2: 'a^',
- 0x00e3: 'a~',
- 0x00e4: 'a:',
- 0x00e5: 'a%',
- 0x00e6: 'ae',
- 0x00e7: 'c,',
- 0x00e8: 'e`',
- 0x00e9: "e'",
- 0x00ea: 'e^',
- 0x00eb: 'e:',
- 0x00ec: 'i`',
- 0x00ed: "i'",
- 0x00ee: 'i^',
- 0x00ef: 'i:',
- 0x00f0: "d'",
- 0x00f1: 'n~',
- 0x00f2: 'o`',
- 0x00f3: "o'",
- 0x00f4: 'o^',
- 0x00f5: 'o~',
- 0x00f6: 'o:',
- 0x00f8: 'o/',
- 0x00f9: 'o`',
- 0x00fa: "u'",
- 0x00fb: 'u~',
- 0x00fc: 'u:',
- 0x00fd: "y'",
- 0x00ff: 'y:',
-
- # Ligatures
- 0x0152: 'OE',
- 0x0153: 'oe',
- 0x0132: 'IJ',
- 0x0133: 'ij',
- 0x1d6b: 'ue',
- 0xfb00: 'ff',
- 0xfb01: 'fi',
- 0xfb02: 'fl',
- 0xfb03: 'ffi',
- 0xfb04: 'ffl',
- 0xfb05: 'ft',
- 0xfb06: 'st',
-
- # Symbols
- #0x2013: '',
- 0x2014: '--',
- 0x2015: '||',
- 0x2018: '`',
- 0x2019: "'",
- 0x201c: '``',
- 0x201d: "''",
- #0x2022: '',
- #0x2212: '',
+ # 0x00a0: '',
+ # 0x00a7: '',
+
+ # iso-8859-1
+ 0x00c0: 'A`',
+ 0x00c1: "A'",
+ 0x00c2: 'A^',
+ 0x00c3: 'A~',
+ 0x00c4: 'A:',
+ 0x00c5: 'A%',
+ 0x00c6: 'AE',
+ 0x00c7: 'C,',
+ 0x00c8: 'E`',
+ 0x00c9: "E'",
+ 0x00ca: 'E^',
+ 0x00cb: 'E:',
+ 0x00cc: 'I`',
+ 0x00cd: "I'",
+ 0x00ce: 'I^',
+ 0x00cf: 'I:',
+ 0x00d0: "D'",
+ 0x00d1: 'N~',
+ 0x00d2: 'O`',
+ 0x00d3: "O'",
+ 0x00d4: 'O^',
+ 0x00d5: 'O~',
+ 0x00d6: 'O:',
+ 0x00d8: 'O/',
+ 0x00d9: 'U`',
+ 0x00da: "U'",
+ 0x00db: 'U~',
+ 0x00dc: 'U:',
+ 0x00dd: "Y'",
+ 0x00df: 'ss',
+
+ 0x00e0: 'a`',
+ 0x00e1: "a'",
+ 0x00e2: 'a^',
+ 0x00e3: 'a~',
+ 0x00e4: 'a:',
+ 0x00e5: 'a%',
+ 0x00e6: 'ae',
+ 0x00e7: 'c,',
+ 0x00e8: 'e`',
+ 0x00e9: "e'",
+ 0x00ea: 'e^',
+ 0x00eb: 'e:',
+ 0x00ec: 'i`',
+ 0x00ed: "i'",
+ 0x00ee: 'i^',
+ 0x00ef: 'i:',
+ 0x00f0: "d'",
+ 0x00f1: 'n~',
+ 0x00f2: 'o`',
+ 0x00f3: "o'",
+ 0x00f4: 'o^',
+ 0x00f5: 'o~',
+ 0x00f6: 'o:',
+ 0x00f8: 'o/',
+ 0x00f9: 'o`',
+ 0x00fa: "u'",
+ 0x00fb: 'u~',
+ 0x00fc: 'u:',
+ 0x00fd: "y'",
+ 0x00ff: 'y:',
+
+ # Ligatures
+ 0x0152: 'OE',
+ 0x0153: 'oe',
+ 0x0132: 'IJ',
+ 0x0133: 'ij',
+ 0x1d6b: 'ue',
+ 0xfb00: 'ff',
+ 0xfb01: 'fi',
+ 0xfb02: 'fl',
+ 0xfb03: 'ffi',
+ 0xfb04: 'ffl',
+ 0xfb05: 'ft',
+ 0xfb06: 'st',
+
+ # Symbols
+ # 0x2013: '',
+ 0x2014: '--',
+ 0x2015: '||',
+ 0x2018: '`',
+ 0x2019: "'",
+ 0x201c: '``',
+ 0x201d: "''",
+ # 0x2022: '',
+ # 0x2212: '',
}
+
def latin2ascii(s):
- return ''.join( LATIN2ASCII.get(ord(c),c) for c in s )
+ return ''.join(LATIN2ASCII.get(ord(c), c) for c in s)
def main(argv):
- import getopt, fileinput
+ import getopt
+ import fileinput
+
def usage():
print('usage: %s [-c codec] file ...' % argv[0])
return 100
@@ -118,13 +121,17 @@ def usage():
(opts, args) = getopt.getopt(argv[1:], 'c')
except getopt.GetoptError:
return usage()
- if not args: return usage()
+ if not args:
+ return usage()
codec = 'utf-8'
for (k, v) in opts:
- if k == '-c': codec = v
+ if k == '-c':
+ codec = v
for line in fileinput.input(args):
- line = latin2ascii(unicode(line, codec, 'ignore'))
+ line = latin2ascii(str(line, codec, 'ignore'))
sys.stdout.write(line.encode('ascii', 'replace'))
return
-if __name__ == '__main__': sys.exit(main(sys.argv))
+
+if __name__ == '__main__':
+ sys.exit(main(sys.argv))
diff --git a/tools/pdf2html.cgi b/tools/pdf2html.cgi
index 4ddba6dc..1b7eebc6 100755
--- a/tools/pdf2html.cgi
+++ b/tools/pdf2html.cgi
@@ -15,47 +15,45 @@
# $ cp pdfminer/tools/pdf2html.cgi $CGIDIR
#
-import sys, os, os.path, re, time
-import cgi, logging, traceback, random
-# comment out at this at runtime.
-#import cgitb; cgitb.enable()
-import pdfminer
-from pdfminer.pdfdocument import PDFDocument
-from pdfminer.pdfpage import PDFPage
-from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
-from pdfminer.converter import HTMLConverter, TextConverter
from pdfminer.layout import LAParams
+from pdfminer.converter import HTMLConverter, TextConverter
+from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
+from pdfminer.pdfpage import PDFPage
+import pdfminer
+import sys
+import os
+import os.path
+import re
+import time
+import cgi
+import logging
+import traceback
+import random
+from utility import url
+# comment out at this at runtime.
+import cgitb
+cgitb.enable()
-# quote HTML metacharacters
-def q(x):
- return x.replace('&','&').replace('>','>').replace('<','<').replace('"','"')
-
-# encode parameters as a URL
-Q = re.compile(r'[^a-zA-Z0-9_.-=]')
-def url(base, **kw):
- r = []
- for (k,v) in kw.iteritems():
- v = Q.sub(lambda m: '%%%02X' % ord(m.group(0)), encoder(q(v), 'replace')[0])
- r.append('%s=%s' % (k, v))
- return base+'&'.join(r)
+# convert
+#
+class FileSizeExceeded(ValueError):
+ pass
-## convert
-##
-class FileSizeExceeded(ValueError): pass
def convert(infp, outfp, path, codec='utf-8',
maxpages=0, maxfilesize=0, pagenos=None,
html=True):
# save the input file.
- src = file(path, 'wb')
+ src = open(path, 'wb')
nbytes = 0
while 1:
data = infp.read(4096)
nbytes += len(data)
if maxfilesize and maxfilesize < nbytes:
raise FileSizeExceeded(maxfilesize)
- if not data: break
+ if not data:
+ break
src.write(data)
src.close()
infp.close()
@@ -68,7 +66,7 @@ def convert(infp, outfp, path, codec='utf-8',
layoutmode='exact')
else:
device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams)
- fp = file(path, 'rb')
+ fp = open(path, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages):
interpreter.process_page(page)
@@ -77,8 +75,8 @@ def convert(infp, outfp, path, codec='utf-8',
return
-## WebApp
-##
+# WebApp
+#
class WebApp(object):
TITLE = 'pdf2html demo'
@@ -103,27 +101,28 @@ class WebApp(object):
def put(self, *args):
for x in args:
- if isinstance(x, str):
- self.outfp.write(x)
- elif isinstance(x, unicode):
- self.outfp.write(x.encode(self.codec, 'xmlcharrefreplace'))
+ # if isinstance(x, str):
+ # self.outfp.write(x)
+ # elif isinstance(x, bytes):
+ self.outfp.write(x.encode(self.codec, 'xmlcharrefreplace'))
return
def response_200(self):
if self.server.startswith('cgi-httpd'):
# required for cgi-httpd
- self.outfp.write('HTTP/1.0 200 OK\r\n')
- self.outfp.write('Content-type: %s\r\n' % self.content_type)
- self.outfp.write('Connection: close\r\n\r\n')
+ self.outfp.write(b'HTTP/1.0 200 OK\r\n')
+ content_type = 'Content-type: %s\r\n' % self.content_type
+ self.outfp.write(content_type.encode())
+ self.outfp.write(b'Connection: close\r\n\r\n')
return
def response_404(self):
if self.server.startswith('cgi-httpd'):
# required for cgi-httpd
self.outfp.write('HTTP/1.0 404 Not Found\r\n')
- self.outfp.write('Content-type: text/html\r\n')
- self.outfp.write('Connection: close\r\n\r\n')
- self.outfp.write('page does not exist\n')
+ self.outfp.write(b'Content-type: text/html\r\n')
+ self.outfp.write(b'Connection: close\r\n\r\n')
+ self.outfp.write(b'page does not exist\n')
return
def response_301(self, url):
@@ -135,21 +134,25 @@ class WebApp(object):
def coverpage(self):
self.put(
- '%s\n' % q(self.TITLE),
- '%s
\n' % q(self.TITLE),
- '
\n',
- 'Powered by PDFMiner-%s\n' % pdfminer.__version__,
- '\n',
- )
+ '
%s\n' % q(self.TITLE),
+ '%s
\n' % q(self.TITLE),
+ '
\n',
+ 'Powered by ',
+ '',
+ 'PDFMiner-%s\n' % pdfminer.__version__,
+ '\n',
+ )
return
def setup(self):
@@ -167,7 +170,7 @@ class WebApp(object):
form = cgi.FieldStorage(fp=self.infp, environ=self.environ)
if (self.method != 'POST' or
'c' not in form or
- 'f' not in form):
+ 'f' not in form):
self.response_200()
self.coverpage()
return
@@ -194,15 +197,20 @@ class WebApp(object):
self.content_type = 'text/plain; charset=%s' % self.codec
self.response_200()
try:
- convert(item.file, self.outfp, tmppath, pagenos=pagenos, codec=self.codec,
- maxpages=self.MAXPAGES, maxfilesize=self.MAXFILESIZE, html=html)
- except Exception, e:
+ convert(
+ item.file, self.outfp, tmppath, pagenos=pagenos,
+ codec=self.codec, maxpages=self.MAXPAGES,
+ maxfilesize=self.MAXFILESIZE, html=html
+ )
+ except Exception as e:
self.put('
Sorry, an error has occurred: %s' % q(repr(e)))
- self.logger.error('convert: %r: path=%r: %s' % (e, traceback.format_exc()))
+ self.logger.error(
+ 'convert: %r: path=%r: %s' %
+ (e, traceback.format_exc()))
finally:
try:
os.remove(tmppath)
- except:
+ except Exception:
pass
return
diff --git a/tools/pdf2txt.py b/tools/pdf2txt.py
index fa829136..9936ce72 100755
--- a/tools/pdf2txt.py
+++ b/tools/pdf2txt.py
@@ -1,30 +1,44 @@
#!/usr/bin/env python
import sys
+import argparse
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
-from pdfminer.pdfdevice import PDFDevice, TagExtractor
+from pdfminer.pdfdevice import 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
-# main
-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()
+
+def main():
+ parser = argparse.ArgumentParser()
+ parser.add_argument('input', metavar='input.pdf', nargs='+')
+ parser.add_argument('-P', '--password')
+ parser.add_argument('-o', '--output')
+ parser.add_argument('-t', '--text-type',
+ choices=['text', 'html', 'xml', 'tag'])
+ parser.add_argument('-O', '--output-dir')
+ parser.add_argument('-c', '--encoding')
+ parser.add_argument('-s', '--scale')
+ parser.add_argument('-R', '--rotation')
+ parser.add_argument('-Y', '--layout-mode',
+ choices=['normal', 'loose', 'exact'])
+ parser.add_argument('-p', '--pagenos')
+ parser.add_argument('-m', '--maxpages')
+ parser.add_argument('-S', '--strip-control', action='store_true')
+ parser.add_argument('-C', '--disable-caching', action='store_true')
+ parser.add_argument('-n', '--no-layout', action='store_true')
+ parser.add_argument('-A', '--all-texts', action='store_true')
+ parser.add_argument('-V', '--detect-vertical', action='store_true')
+ parser.add_argument('-M', '--char-margin')
+ parser.add_argument('-L', '--line-margin')
+ parser.add_argument('-W', '--word-margin')
+ parser.add_argument('-F', '--boxes-flow')
+ parser.add_argument('-d', '--debug', action='store_true')
+ args = parser.parse_args()
+
# debug option
debug = 0
# input option
@@ -39,32 +53,50 @@ def usage():
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)
+ if args.debug:
+ debug += 1
+ elif args.password:
+ password = args.password.encode('ascii')
+ elif args.output:
+ outfile = args.output
+ elif args.text_type:
+ outtype = args.text_type
+ elif args.output_dir:
+ imagewriter = ImageWriter(args['output-dir'])
+ elif args.encoding:
+ encoding = args.encoding
+ elif args.scale:
+ scale = float(args.scale)
+ elif args.rotation:
+ rotation = int(args.rotation)
+ elif args.layout_mode:
+ layoutmode = args.layout_mode
+ elif args.pagenos:
+ pagenos.update(int(x)-1 for x in args.pagenos.split(','))
+ elif args.maxpages:
+ maxpages = int(args.maxpages)
+ elif args.strip_control:
+ stripcontrol = True
+ elif args.disable_caching:
+ caching = False
+ elif args.no_layout:
+ laparams = None
+ elif args.all_texts:
+ laparams.all_texts = True
+ elif args.detect_vertical:
+ laparams.detect_vertical = True
+ elif args.char_margin:
+ laparams.char_margin = float(args.char_margin)
+ elif args.word_margin:
+ laparams.word_margin = float(args.word_margin)
+ elif args.line_margin:
+ laparams.line_margin = float(args.line_margin)
+ elif args.boxes_flow:
+ laparams.boxes_flow = float(args.boxes_flow)
#
PDFDocument.debug = debug
PDFParser.debug = debug
@@ -98,18 +130,20 @@ def usage():
imagewriter=imagewriter, debug=debug)
elif outtype == 'tag':
device = TagExtractor(rsrcmgr, outfp)
- else:
- return usage()
- for fname in args:
+
+ for fname in args.input:
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):
+ 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
+ if outfile:
+ outfp.close()
+
-if __name__ == '__main__': sys.exit(main(sys.argv))
+if __name__ == '__main__':
+ sys.exit(main())
diff --git a/tools/prof.py b/tools/prof.py
old mode 100644
new mode 100755
index abcfb8be..07e4e555
--- a/tools/prof.py
+++ b/tools/prof.py
@@ -1,13 +1,17 @@
#!/usr/bin/env python
import sys
+
def prof_main(argv):
- import hotshot, hotshot.stats
+ import cProfile
+ import pstats
+
def usage():
print('usage: %s module.function [args ...]' % argv[0])
return 100
args = argv[1:]
- if len(args) < 1: return usage()
+ if len(args) < 1:
+ return usage()
name = args.pop(0)
prof = name+'.prof'
i = name.rindex('.')
@@ -16,14 +20,16 @@ def usage():
func = getattr(module, funcname)
if args:
args.insert(0, argv[0])
- prof = hotshot.Profile(prof)
- prof.runcall(lambda : func(args))
+ prof = cProfile(prof)
+ prof.runcall(lambda: func(args))
prof.close()
else:
- stats = hotshot.stats.load(prof)
+ stats = pstats.Stats(prof)
stats.strip_dirs()
stats.sort_stats('time', 'calls')
stats.print_stats(1000)
return
-if __name__ == '__main__': sys.exit(prof_main(sys.argv))
+
+if __name__ == '__main__':
+ sys.exit(prof_main(sys.argv))
diff --git a/tools/runapp.py b/tools/runapp.py
index 81f5acfb..f30dc56c 100755
--- a/tools/runapp.py
+++ b/tools/runapp.py
@@ -1,19 +1,20 @@
#!/usr/bin/env python
##
-## WebApp class runner
+# WebApp class runner
##
-## usage:
-## $ runapp.py pdf2html.cgi
+# usage:
+# $ runapp.py pdf2html.cgi
##
import sys
import urllib
-from httplib import responses
-from BaseHTTPServer import HTTPServer
-from SimpleHTTPServer import SimpleHTTPRequestHandler
+from http.client import responses
+from http.server import HTTPServer, SimpleHTTPRequestHandler
-## WebAppHandler
+# WebAppHandler
##
+
+
class WebAppHandler(SimpleHTTPRequestHandler):
APP_CLASS = None
@@ -37,7 +38,7 @@ def run_cgi(self):
else:
script, rest = rest, ''
scriptname = '/' + script
- scriptfile = self.translate_path(scriptname)
+ # scriptfile = self.translate_path(scriptname)
env = {}
env['SERVER_SOFTWARE'] = self.version_string()
env['SERVER_NAME'] = self.server.server_name
@@ -45,7 +46,7 @@ def run_cgi(self):
env['SERVER_PROTOCOL'] = self.protocol_version
env['SERVER_PORT'] = str(self.server.server_port)
env['REQUEST_METHOD'] = self.command
- uqrest = urllib.unquote(rest)
+ uqrest = urllib.parse.unquote(rest)
env['PATH_INFO'] = uqrest
env['PATH_TRANSLATED'] = self.translate_path(uqrest)
env['SCRIPT_NAME'] = scriptname
@@ -55,11 +56,11 @@ def run_cgi(self):
if host != self.client_address[0]:
env['REMOTE_HOST'] = host
env['REMOTE_ADDR'] = self.client_address[0]
- if self.headers.typeheader is None:
- env['CONTENT_TYPE'] = self.headers.type
+ if self.headers.get_content_type() is None:
+ env['CONTENT_TYPE'] = self.headers.get_default_type()
else:
- env['CONTENT_TYPE'] = self.headers.typeheader
- length = self.headers.getheader('content-length')
+ env['CONTENT_TYPE'] = self.headers.get_content_type()
+ length = self.headers.get('content-length')
if length:
env['CONTENT_LENGTH'] = length
accept = []
@@ -69,10 +70,10 @@ def run_cgi(self):
else:
accept = accept + line[7:].split(',')
env['HTTP_ACCEPT'] = ','.join(accept)
- ua = self.headers.getheader('user-agent')
+ ua = self.headers.get('user-agent')
if ua:
env['HTTP_USER_AGENT'] = ua
- co = filter(None, self.headers.getheaders('cookie'))
+ co = filter(None, self.headers.get('cookie'))
if co:
env['HTTP_COOKIE'] = ', '.join(co)
for k in ('QUERY_STRING', 'REMOTE_HOST', 'CONTENT_LENGTH',
@@ -85,8 +86,12 @@ def run_cgi(self):
return
# main
+
+
def main(argv):
- import getopt, imp
+ import getopt
+ import imp
+
def usage():
print('usage: %s [-h host] [-p port] [-n name] module.class' % argv[0])
return 100
@@ -98,16 +103,22 @@ def usage():
port = 8080
name = 'WebApp'
for (k, v) in opts:
- if k == '-h': host = v
- elif k == '-p': port = int(v)
- elif k == '-n': name = v
- if not args: return usage()
+ if k == '-h':
+ host = v
+ elif k == '-p':
+ port = int(v)
+ elif k == '-n':
+ name = v
+ if not args:
+ return usage()
path = args.pop(0)
module = imp.load_source('app', path)
WebAppHandler.APP_CLASS = getattr(module, name)
- print('Listening %s:%d...' % (host,port))
- httpd = HTTPServer((host,port), WebAppHandler)
+ print('Listening %s:%d...' % (host, port))
+ httpd = HTTPServer((host, port), WebAppHandler)
httpd.serve_forever()
return
-if __name__ == '__main__': sys.exit(main(sys.argv))
+
+if __name__ == '__main__':
+ sys.exit(main(sys.argv))
diff --git a/tools/utility.py b/tools/utility.py
new file mode 100644
index 00000000..c7365a2c
--- /dev/null
+++ b/tools/utility.py
@@ -0,0 +1,23 @@
+import re
+
+
+# quote HTML metacharacters
+def q(x):
+ return x \
+ .replace('&', '&') \
+ .replace('>', '>') \
+ .replace('<', '<')\
+ .replace('"', '"')
+
+
+# encode parameters as a URL
+Q = re.compile(r'[^a-zA-Z0-9_.-=]')
+
+
+def url(base, **kw):
+ r = []
+ for (k, v) in kw.iteritems():
+ v = Q.sub(lambda m: '%%%02X' % ord(m.group(0)),
+ q(v).encode("utf-8", 'replace')[0])
+ r.append('%s=%s' % (k, v))
+ return base+'&'.join(r)
\ No newline at end of file