def _parse(self):
# the PDFParseContext is a parser for the PDF 'language'
p = PDFParseContext(self.rawContent)
p.parse()
self.context = p
# after parsing all those dictionaries, we need to do
# the 'cross referencing' - figuring out what the bits
# mean. PageCatcher's model lets us do only the bits needed,
# but what the heck, do the lot.
# The 'compilation' object is basically the parsed/resolved/
# reconstructed document, so we cal it pdfTree
c = p.compilation
self.pdfTree = c
(ind, catinfo) = p.catalog
if p.encrypt:
getPdfEncrypt()
c.sanitizePages(save=("Type", "Contents",
"MediaBox", "ArtBox", "BleedBox", "CropBox", "TrimBox",
"Resources", "Rotate"))
#c.sanitizePages() # this drops info we need
c.findAllReferences()
#catalog = \
c.getReference(catinfo)
c.doTranslations(catinfo) # this takes the time!
c.populatePageList()
self.pageCount = len(c.pageList)
# keep a lazy array of parsed page objects
self._pageForms = [None] * len(c.pageList)
def _parse(self):
# the PDFParseContext is a parser for the PDF 'language'
p = PDFParseContext(self.rawContent)
p.parse()
self.context = p
# after parsing all those dictionaries, we need to do
# the 'cross referencing' - figuring out what the bits
# mean. PageCatcher's model lets us do only the bits needed,
# but what the heck, do the lot.
# The 'compilation' object is basically the parsed/resolved/
# reconstructed document, so we cal it pdfTree
c = p.compilation
self.pdfTree = c
(ind, catinfo) = p.catalog
if p.encrypt:
getPdfEncrypt()
c.sanitizePages(save=("Type", "Contents",
"MediaBox", "ArtBox", "BleedBox", "CropBox", "TrimBox",
"Resources", "Rotate"))
#c.sanitizePages() # this drops info we need
c.findAllReferences()
#catalog = \
c.getReference(catinfo)
c.doTranslations(catinfo) # this takes the time!
c.populatePageList()
self.pageCount = len(c.pageList)
# keep a lazy array of parsed page objects
self._pageForms = [None] * len(c.pageList)
def parsedoc(fileName):
"""
Using PDFParseContext object from Pagecatcher module to check for encryption.
"""
try:
from rlextra.pageCatcher.pageCatcher import PDFParseContext
except ImportError:
return
pdfContent = open(fileName, 'rb').read()
p = PDFParseContext(pdfContent, prefix="PageForms")
p.parse()
assert p.encrypt
def _extractAnnotations(self):
"""
Returns list of annotation dictionaries on page.dict
Here is what an annotation dictionary looks like:
{ 'F': 4,
'FT': '/Tx',
'Rect': [108, 577, 407, 594],
'Subtype': '/Widget',
'T': 'AgentName',
'TU': 'blah again',
'Type': '/Annot'}"""
self._annotations = {}
p = PDFParseContext(self.rawContent)
p.parse()
(ind, catinfo) = p.catalog
c = p.compilation
c.sanitizePages(save=("Type", "Contents",
"MediaBox", "ArtBox", "BleedBox", "CropBox", "TrimBox",
"Resources", "Rotate", "Annots"))
#c.sanitizePages() # this drops info we need
c.findAllReferences()
#catalog = \
c.getReference(catinfo)
c.doTranslations(catinfo) # this takes the time!
c.populatePageList()
pageCount = len(c.pageList)
for pageNo in range(pageCount):
pageId = c.pageList[pageNo]
page = c.objects[pageId]
pageDict = page.dict
if "Annots" in pageDict:
rawPageAnnots = c.resolve(pageDict["Annots"])
friendlyPageAnnots = pythonize(rawPageAnnots, c)
else:
friendlyPageAnnots = []
self._annotations[pageNo] = friendlyPageAnnots
def _extractAnnotations(self):
"""
Returns list of annotation dictionaries on page.dict
Here is what an annotation dictionary looks like:
{ 'F': 4,
'FT': '/Tx',
'Rect': [108, 577, 407, 594],
'Subtype': '/Widget',
'T': 'AgentName',
'TU': 'blah again',
'Type': '/Annot'}"""
self._annotations = {}
p = PDFParseContext(self.rawContent)
p.parse()
(ind, catinfo) = p.catalog
c = p.compilation
c.sanitizePages(save=("Type", "Contents",
"MediaBox", "ArtBox", "BleedBox", "CropBox", "TrimBox",
"Resources", "Rotate", "Annots"))
#c.sanitizePages() # this drops info we need
c.findAllReferences()
#catalog = \
c.getReference(catinfo)
c.doTranslations(catinfo) # this takes the time!
c.populatePageList()
pageCount = len(c.pageList)
for pageNo in range(pageCount):
pageId = c.pageList[pageNo]
page = c.objects[pageId]
pageDict = page.dict
if "Annots" in pageDict:
rawPageAnnots = c.resolve(pageDict["Annots"])
friendlyPageAnnots = pythonize(rawPageAnnots, c)
else:
friendlyPageAnnots = []
self._annotations[pageNo] = friendlyPageAnnots