def extract_text(self):
text = u""
content = self["/Contents"].getObject()
if not isinstance(content, ContentStream):
content = ContentStream(content, self.pdf)
for operands, operator in content.operations:
if operator == "Tj":
_text = operands[0]
if isinstance(_text, TextStringObject):
text += _text
elif operator == "T*":
text += "\n"
elif operator == "'":
text += "\n"
_text = operands[0]
if isinstance(_text, TextStringObject):
text += operands[0]
elif operator == '"':
_text = operands[2]
if isinstance(_text, TextStringObject):
text += "\n"
text += _text
elif operator == "TJ":
for i in operands[0]:
if isinstance(i, TextStringObject):
text += i
if text and not text.endswith(" "):
text += " " # Don't let words concatenate
return text
def extractPDFText(self):
text = u""
content = self["/Contents"].getObject()
if not isinstance(content, ContentStream):
content = ContentStream(content, self.pdf)
# Note: we check all strings are TextStringObjects. ByteStringObjects
# are strings where the byte->string encoding was unknown, so adding
# them to the text here would be gibberish.
for operands, operator in content.operations:
if operator == "Tj":
_text = operands[0]
if isinstance(_text, TextStringObject):
text += _text
elif operator == "T*":
text += "\n"
elif operator == "'":
text += "\n"
_text = operands[0]
if isinstance(_text, TextStringObject):
text += operands[0]
elif operator == '"':
_text = operands[2]
if isinstance(_text, TextStringObject):
text += "\n"
text += _text
elif operator == "TJ":
for i in operands[0]:
if isinstance(i, TextStringObject):
text += i
elif operator == "k":
text += "\n"
return text
def extractOperators(self):
ops = []
content = self["/Contents"].getObject()
if not isinstance(content, ContentStream):
content = ContentStream(content, self.pdf)
for op in content.operations:
ops.append(op)
return ops
def replace_text(cls, page, text, replace):
# HACK
from pyPdf.pdf import ContentStream, PageObject
from pyPdf.generic import TextStringObject, NameObject
content = ContentStream(page["/Contents"].getObject(), page.pdf)
for idx in range(len(content.operations)):
operands, operator = content.operations[idx]
if operator == 'Tj':
operands[0] = TextStringObject(operands[0].replace(
text, replace))
new_page = PageObject.createBlankPage(page.pdf)
new_page.mergePage(page)
new_page[NameObject('/Contents')] = content
return new_page
def pdf_add_content(content_string, page, scale=1, offsetx=0, offsety=0):
"""Add content to the end of the content stream of the PDF page.
Inputs: content_string The PDF drawing commands to add, as a single string.
page The pyPdf.pdf.PageObject to add the content to.
scale Before adding the content, adjust the the coordinate
offsetx system with a (uniform) scale factor and a
offsety translation of offsetx and offsety.
"""
coord_trans = '%.2f 0 0 %.2f %.2f %.2f cm' % (scale, scale, offsetx,
offsety)
commands = '\n'.join(('Q', 'q', coord_trans, content_string, 'Q'))
try:
orig_content = page['/Contents'].getObject()
except KeyError:
orig_content = ArrayObject([])
stream = ContentStream(orig_content, page.pdf)
stream.operations.insert(0, [[], 'q']) # Existing content may not restore
stream.operations.append([[], commands]) # graphics state at the end.
page[NameObject('/Contents')] = stream
def extract_text(self):
""" Patched extractText() from pyPdf to put spaces between different text snippets.
"""
text = u""
content = self["/Contents"].getObject()
if not isinstance(content, ContentStream):
content = ContentStream(content, self.pdf)
# Note: we check all strings are TextStringObjects. ByteStringObjects
# are strings where the byte->string encoding was unknown, so adding
# them to the text here would be gibberish.
for operands, operator in content.operations:
if operator == "Tj":
_text = operands[0]
if isinstance(_text, TextStringObject):
text += _text
elif operator == "T*":
text += "\n"
elif operator == "'":
text += "\n"
_text = operands[0]
if isinstance(_text, TextStringObject):
text += operands[0]
elif operator == '"':
_text = operands[2]
if isinstance(_text, TextStringObject):
text += "\n"
text += _text
elif operator == "TJ":
for i in operands[0]:
if isinstance(i, TextStringObject):
text += i
if text and not text.endswith(" "):
text += " " # Don't let words concatenate
return text
def InsertXObject(self, name):
" XObject can be an image or a 'form' (an arbitrary PDF sequence) "
dlist = []
xobject = self.page["/Resources"].getObject()['/XObject']
stream = xobject[name]
if stream.get('/Subtype') == '/Form':
# insert contents into current page drawing
if not name in self.formdrawings: # extract if not already done
pdf_fonts = self.FetchFonts(stream)
bbox = stream.get('/BBox')
matrix = stream.get('/Matrix')
form_ops = ContentStream(stream, self.pdfdoc).operations
oplist = [([], 'q'), (matrix, 'cm')] # push state & apply matrix
oplist.extend(form_ops) # add form contents
oplist.append(([], 'Q')) # restore original state
self.formdrawings[name] = self.ProcessOperators(oplist, pdf_fonts)
dlist.extend(self.formdrawings[name])
elif stream.get('/Subtype') == '/Image':
width = stream.get('/Width')
height = stream.get('/Height')
depth = stream.get('/BitsPerComponent')
filters = stream.get("/Filter", ())
dlist.append(self.AddBitmap(stream._data, width, height, filters))
return dlist