def __init__(
self,
infile,
detailed_analysis: bool = False,
progbar: bool = False,
max_workers: int = None,
check_pages=None,
):
self._infile = infile
if check_pages is None:
check_pages = range(0, 1_000_000_000)
with pikepdf.open(infile) as pdf:
if pdf.is_encrypted:
raise EncryptedPdfError() # Triggered by encryption with empty passwd
self._pages = _pdf_pageinfo_concurrent(
pdf,
infile,
progbar,
max_workers,
check_pages=check_pages,
detailed_analysis=detailed_analysis,
)
self._needs_rendering = pdf.root.get('/NeedsRendering', False)
self._has_acroform = False
if '/AcroForm' in pdf.root:
if len(pdf.root.AcroForm.get('/Fields', [])) > 0:
self._has_acroform = True
elif '/XFA' in pdf.root.AcroForm:
self._has_acroform = True
def _pdf_get_all_pageinfo(infile,
detailed_analysis=False,
log=None,
progbar=False):
pdf = pikepdf.open(infile) # Do not close in this function
if pdf.is_encrypted:
pdf.close()
raise EncryptedPdfError() # Triggered by encryption with empty passwd
if detailed_analysis:
pages_xml = None
else:
pages_xml = ghosttext.extract_text_xml(infile,
pdf,
pageno=None,
log=log)
pages = []
for n, _ in tqdm(
enumerate(pdf.pages),
total=len(pdf.pages),
desc="Scan",
unit='page',
disable=not progbar,
):
page_xml = pages_xml[n] if pages_xml else None
page = PageInfo(pdf, n, infile, page_xml, detailed_analysis)
pages.append(page)
return pages, pdf
def get_page_analysis(infile, pageno, pscript5_mode):
rman = pdfminer.pdfinterp.PDFResourceManager(caching=True)
dev = TextPositionTracker(rman,
laparams=LAParams(all_texts=True,
detect_vertical=True))
interp = pdfminer.pdfinterp.PDFPageInterpreter(rman, dev)
if pscript5_mode:
patcher = patch.multiple(
'pdfminer.pdffont.PDFType3Font',
spec=True,
get_ascent=PDFType3Font__PScript5_get_ascent,
get_descent=PDFType3Font__PScript5_get_descent,
get_height=PDFType3Font__PScript5_get_height,
)
patcher.start()
try:
with Path(infile).open('rb') as f:
page = PDFPage.get_pages(f, pagenos=[pageno], maxpages=0)
interp.process_page(next(page))
except PDFTextExtractionNotAllowed:
raise EncryptedPdfError()
finally:
if pscript5_mode:
patcher.stop()
return dev.get_result()
def get_pdfinfo(
input_file,
detailed_analysis=False,
progbar=False,
max_workers=None,
check_pages=None,
):
try:
return PdfInfo(
input_file,
detailed_analysis=detailed_analysis,
progbar=progbar,
max_workers=max_workers,
check_pages=check_pages,
)
except pikepdf.PasswordError:
raise EncryptedPdfError()
except pikepdf.PdfError:
raise InputFileError()
def get_page_analysis(infile, pageno, pscript5_mode):
rman = pdfminer.pdfinterp.PDFResourceManager(caching=True)
if pdfminer.__version__ < '20200402':
# Workaround for https://github.com/pdfminer/pdfminer.six/issues/395
disable_boxes_flow = 2
else:
disable_boxes_flow = None
dev = TextPositionTracker(
rman,
laparams=LAParams(all_texts=True,
detect_vertical=True,
boxes_flow=disable_boxes_flow),
)
interp = pdfminer.pdfinterp.PDFPageInterpreter(rman, dev)
patcher = None
if pscript5_mode:
patcher = patch.multiple(
'pdfminer.pdffont.PDFType3Font',
spec=True,
get_ascent=PDFType3Font__PScript5_get_ascent,
get_descent=PDFType3Font__PScript5_get_descent,
get_height=PDFType3Font__PScript5_get_height,
)
patcher.start()
try:
with Path(infile).open('rb') as f:
page_iter = PDFPage.get_pages(f, pagenos=[pageno], maxpages=0)
page = next(page_iter, None)
if page is None:
raise InputFileError(
f"pdfminer could not process page {pageno} (counting from 0)."
)
interp.process_page(page)
except PDFTextExtractionNotAllowed as e:
raise EncryptedPdfError() from e
finally:
if patcher is not None:
patcher.stop()
return dev.get_result()
def get_pdfinfo(
input_file,
*,
executor: Executor,
detailed_analysis=False,
progbar=False,
max_workers=None,
check_pages=None,
) -> PdfInfo:
try:
return PdfInfo(
input_file,
detailed_analysis=detailed_analysis,
progbar=progbar,
max_workers=max_workers,
check_pages=check_pages,
executor=executor,
)
except pikepdf.PasswordError as e:
raise EncryptedPdfError() from e
except pikepdf.PdfError as e:
raise InputFileError() from e
