def get_outlines(doc, pageslist, pagesdict):
result = []
for (_, title, destname, actionref, _) in doc.get_outlines():
if destname is None and actionref:
action = pdftypes.resolve1(actionref)
if isinstance(action, dict):
subtype = action.get('S')
if subtype is PSLiteralTable.intern('GoTo'):
destname = action.get('D')
if destname is None:
continue
dest = resolve_dest(doc, destname)
# consider targets of the form [page /XYZ left top zoom]
if dest[1] is PSLiteralTable.intern('XYZ'):
(pageref, _, targetx, targety) = dest[:4]
if type(pageref) is int:
page = pageslist[pageref]
elif isinstance(pageref, pdftypes.PDFObjRef):
page = pagesdict[pageref.objid]
else:
sys.stderr.write(
'Warning: unsupported pageref in outline: %s\n' % pageref)
page = None
if page:
pos = Pos(page, targetx, targety)
result.append(Outline(title, destname, pos))
return result
def get_outlines(doc, pagesdict):
result = []
for (_, title, destname, actionref, _) in doc.get_outlines():
if destname is None and actionref:
action = actionref.resolve()
if isinstance(action, dict):
subtype = action.get('S')
if subtype is PSLiteralTable.intern('GoTo'):
destname = action.get('D')
if destname is None:
continue
dest = resolve_dest(doc, destname)
# consider targets of the form [page /XYZ left top zoom]
if dest[1] is PSLiteralTable.intern('XYZ'):
(pageref, _, targetx, targety, _) = dest
page = pagesdict[pageref.objid]
pos = Pos(page, targetx, targety)
result.append(Outline(title, destname, pos))
return result
def get_outlines(doc, pagesdict):
result = []
for (_, title, destname, actionref, _) in doc.get_outlines():
if destname is None and actionref:
action = actionref.resolve()
if isinstance(action, dict):
subtype = action.get('S')
if subtype is PSLiteralTable.intern('GoTo'):
destname = action.get('D')
if destname is None:
continue
dest = resolve_dest(doc, destname)
pageno = pagesdict[dest[0].objid]
(_, _, targetx, targety, _) = dest
result.append(Outline(title, destname, pageno, targetx, targety))
return result
#!/usr/bin/env python
import sys, zlib
from pdfminer.lzw import LZWDecoder
from pdfminer.psparser import PSException, PSObject, \
PSLiteral, PSKeyword, PSLiteralTable, PSKeywordTable, \
literal_name, keyword_name, STRICT
LITERAL_CRYPT = PSLiteralTable.intern('Crypt')
LITERALS_FLATE_DECODE = (PSLiteralTable.intern('FlateDecode'), PSLiteralTable.intern('Fl'))
LITERALS_LZW_DECODE = (PSLiteralTable.intern('LZWDecode'), PSLiteralTable.intern('LZW'))
LITERALS_ASCII85_DECODE = (PSLiteralTable.intern('ASCII85Decode'), PSLiteralTable.intern('A85'))
LITERALS_ASCIIHEX_DECODE = (PSLiteralTable.intern('ASCIIHexDecode'), PSLiteralTable.intern('AHx'))
## PDF Objects
##
class PDFObject(PSObject): pass
class PDFException(PSException): pass
class PDFTypeError(PDFException): pass
class PDFValueError(PDFException): pass
class PDFNotImplementedError(PSException): pass
## PDFObjRef
##
class PDFObjRef(PDFObject):
def __init__(self, doc, objid, _):
if objid == 0:
if STRICT:
from pdfminer.psparser import PSStackParser, PSSyntaxError, PSEOF, \
PSLiteralTable, PSKeywordTable, literal_name, keyword_name, STRICT
from pdfminer.pdftypes import PDFException, PDFTypeError, PDFNotImplementedError, \
PDFStream, PDFObjRef, resolve1, decipher_all, \
int_value, float_value, num_value, str_value, list_value, dict_value, stream_value
## Exceptions
##
class PDFSyntaxError(PDFException): pass
class PDFNoValidXRef(PDFSyntaxError): pass
class PDFEncryptionError(PDFException): pass
class PDFPasswordIncorrect(PDFEncryptionError): pass
# some predefined literals and keywords.
LITERAL_OBJSTM = PSLiteralTable.intern('ObjStm')
LITERAL_XREF = PSLiteralTable.intern('XRef')
LITERAL_PAGE = PSLiteralTable.intern('Page')
LITERAL_PAGES = PSLiteralTable.intern('Pages')
LITERAL_CATALOG = PSLiteralTable.intern('Catalog')
## XRefs
##
class XRefObjRange(object):
def __init__(self, start, nobjs):
self.start = start
self.nobjs = nobjs
return
def __repr__(self):
from pdfminer.pdffont import PDFFontError, PDFType1Font, PDFTrueTypeFont, PDFType3Font, PDFCIDFont
from pdfminer.pdfparser import PDFDocument, PDFParser, PDFPasswordIncorrect
from pdfminer.pdfcolor import PDFColorSpace, PREDEFINED_COLORSPACE, \
LITERAL_DEVICE_GRAY, LITERAL_DEVICE_RGB, LITERAL_DEVICE_CMYK
from pdfminer.cmap import CMapDB
## Exceptions
##
class PDFResourceError(PDFException): pass
class PDFInterpreterError(PDFException): pass
## Constants
##
LITERAL_PDF = PSLiteralTable.intern('PDF')
LITERAL_TEXT = PSLiteralTable.intern('Text')
LITERAL_FONT = PSLiteralTable.intern('Font')
LITERAL_FORM = PSLiteralTable.intern('Form')
LITERAL_IMAGE = PSLiteralTable.intern('Image')
## PDFTextState
##
class PDFTextState(object):
def __init__(self):
self.font = None
self.fontsize = 0
self.charspace = 0
self.wordspace = 0
#!/usr/bin/env python
import sys
from pdfminer.psparser import PSLiteralTable
## PDFColorSpace
##
LITERAL_DEVICE_GRAY = PSLiteralTable.intern('DeviceGray')
LITERAL_DEVICE_RGB = PSLiteralTable.intern('DeviceRGB')
LITERAL_DEVICE_CMYK = PSLiteralTable.intern('DeviceCMYK')
class PDFColorSpace(object):
def __init__(self, name, ncomponents):
self.name = name
self.ncomponents = ncomponents
return
def __repr__(self):
return '<PDFColorSpace: %s, ncomponents=%d>' % (self.name,
self.ncomponents)
PREDEFINED_COLORSPACE = dict(
(name, PDFColorSpace(name, n)) for (name, n) in {
'CalRGB': 3,
'CalGray': 1,
'Lab': 3,
'DeviceRGB': 3,
'DeviceCMYK': 4,
'DeviceGray': 1,
'Separation': 1,
#!/usr/bin/env python
import sys
from pdfminer.psparser import PSLiteralTable
## PDFColorSpace
##
LITERAL_DEVICE_GRAY = PSLiteralTable.intern('DeviceGray')
LITERAL_DEVICE_RGB = PSLiteralTable.intern('DeviceRGB')
LITERAL_DEVICE_CMYK = PSLiteralTable.intern('DeviceCMYK')
class PDFColorSpace(object):
def __init__(self, name, ncomponents):
self.name = name
self.ncomponents = ncomponents
return
def __repr__(self):
return '<PDFColorSpace: %s, ncomponents=%d>' % (self.name, self.ncomponents)
PREDEFINED_COLORSPACE = dict(
(name, PDFColorSpace(name,n)) for (name,n) in {
'CalRGB': 3,
'CalGray': 1,
'Lab': 3,
'DeviceRGB': 3,
'DeviceCMYK': 4,
'DeviceGray': 1,
'Separation': 1,
char2gid[c] = (unpack('>H', fp.read(2))[0] + idd) & 0xffff
else:
for c in xrange(sc, ec+1):
char2gid[c] = (c + idd) & 0xffff
gid2char = dict( (gid, pack('>H', char))
for (char,gid) in char2gid.iteritems() )
return CMap().update(char2gid, gid2char)
## Fonts
##
class PDFFontError(PDFException): pass
class PDFUnicodeNotDefined(PDFFontError): pass
LITERAL_STANDARD_ENCODING = PSLiteralTable.intern('StandardEncoding')
LITERAL_TYPE1C = PSLiteralTable.intern('Type1C')
# PDFFont
class PDFFont(object):
def __init__(self, descriptor, widths, default_width=None):
self.descriptor = descriptor
self.widths = widths
self.fontname = descriptor.get('FontName', 'unknown')
if isinstance(self.fontname, PSLiteral):
self.fontname = literal_name(self.fontname)
self.ascent = num_value(descriptor.get('Ascent', 0))
self.descent = num_value(descriptor.get('Descent', 0))
self.default_width = default_width or descriptor.get('MissingWidth', 0)
class PDFNoValidXRef(PDFSyntaxError):
pass
class PDFEncryptionError(PDFException):
pass
class PDFPasswordIncorrect(PDFEncryptionError):
pass
# some predefined literals and keywords.
LITERAL_OBJSTM = PSLiteralTable.intern('ObjStm')
LITERAL_XREF = PSLiteralTable.intern('XRef')
LITERAL_PAGE = PSLiteralTable.intern('Page')
LITERAL_PAGES = PSLiteralTable.intern('Pages')
LITERAL_CATALOG = PSLiteralTable.intern('Catalog')
## XRefs
##
class XRefObjRange(object):
def __init__(self, start, nobjs):
self.start = start
self.nobjs = nobjs
return
def __repr__(self):
return CMap().update(char2gid, gid2char)
## Fonts
##
class PDFFontError(PDFException):
pass
class PDFUnicodeNotDefined(PDFFontError):
pass
LITERAL_STANDARD_ENCODING = PSLiteralTable.intern('StandardEncoding')
LITERAL_TYPE1C = PSLiteralTable.intern('Type1C')
# PDFFont
class PDFFont(object):
def __init__(self, descriptor, widths, default_width=None):
self.descriptor = descriptor
self.widths = widths
self.fontname = descriptor.get('FontName', 'unknown')
if isinstance(self.fontname, PSLiteral):
self.fontname = literal_name(self.fontname)
self.ascent = num_value(descriptor.get('Ascent', 0))
self.descent = num_value(descriptor.get('Descent', 0))
self.default_width = default_width or descriptor.get('MissingWidth', 0)
self.leading = num_value(descriptor.get('Leading', 0))