def __init__(self, rsrcmgr, outfp, codec='utf-8', pageno=1, laparams=None,
imagewriter=None, stripcontrol=False):
PDFConverter.__init__(self, rsrcmgr, outfp, codec=codec, pageno=pageno,
laparams=laparams)
self.imagewriter = imagewriter
self.stripcontrol = stripcontrol
self.textboxes = []
self.page_width = []
self.page_height = []
self.classified = []
self.classified_header = []
self.classified_paragraph = []
self.classified_section = []
self.classified_subsection = []
self.tree = Tree()
self.tree.create_node("Documents", 'documents')
self.num_tabs = 0
self.write_header()
self.headerExist = False
self.in_li = False
json_file = open('data/model.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
self.model = model_from_json(loaded_model_json)
self.model.load_weights("data/model.h5")
self.tokenizer = []
with open('data/tokenizer.pickle', 'rb') as handle:
self.tokenizer = pickle.load(handle)
return
def __init__(self, rsrcmgr, outfp, codec='utf-8', pageno=1, laparams=None, showpageno=False, imagewriter=None):
PDFConverter.__init__(self, rsrcmgr, outfp, codec=codec, pageno=pageno, laparams=laparams)
self.showpageno = showpageno
self.imagewriter = imagewriter
self.blotterProcessor = BlotterProcessor(outfp)
self.coro = self.blotterProcessor.processDocument()
return
def __init__(self, rsrcmgr, outfp, codec='utf-8', pageno=1, laparams=None,
showpageno=False, imagewriter=None):
PDFConverter.__init__(self, rsrcmgr, outfp, codec=codec, pageno=pageno, laparams=laparams)
self.showpageno = showpageno
self.imagewriter = imagewriter
self.current_total_height = 0
return
def __init__(self, rsrcmgr, doc, codec='utf-8', pageno=1,
laparams=None, imagewriter=None):
PDFConverter.__init__(self, rsrcmgr, None, codec=codec, pageno=pageno, laparams=laparams)
self.imagewriter = imagewriter
self.laparams = laparams
self.doc = doc
self.sizes = []
return
def __init__(self, rsrcmgr, outfp, codec='utf-8', pageno=1,
laparams=None, imagewriter=None, stripcontrol=False, document=None):
PDFConverter.__init__(self, rsrcmgr, outfp, codec=codec, pageno=pageno, laparams=laparams)
self.imagewriter = imagewriter
self.stripcontrol = stripcontrol
self.document = document
self.rsrcmgr = rsrcmgr
self.write_header()
return
def render_image(self, name, stream):
"""
Some dummy functions to save memory/CPU when all that is wanted
is text. This stops all the image and drawing output from being
recorded and taking up RAM.
"""
if self.imagewriter is None:
return
PDFConverter.render_image(self, name, stream)
return
def __init__(self, rsrcmgr, outfp, codec='utf-8', pageno=1, laparams=None,
imagewriter=None, stripcontrol=False):
PDFConverter.__init__(self, rsrcmgr, outfp, codec=codec, pageno=pageno,
laparams=laparams)
self.imagewriter = imagewriter
self.stripcontrol = stripcontrol
self.textboxes = []
self.page_width = []
self.page_height = []
self.write_header()
return
def __init__(self,
rsrcmgr,
outfp,
pageno=1,
laparams=None,
showpageno=False):
PDFConverter.__init__(self,
rsrcmgr,
outfp,
pageno=pageno,
laparams=laparams)
self.showpageno = showpageno
def __init__(self, rsrcmgr, outfp):
laparams = LAParams()
laparams.char_margin=0.1
PDFConverter.__init__(self, rsrcmgr, outfp, codec='utf-8', laparams=laparams)
self.lines = []
self.boxes = []
self.writer = csv.writer(outfp, lineterminator='\n')
self.writer.writerow(["企業・事業場名称",
"所在地",
"公表日",
"違反法条",
"事案概要",
"その他参考事項"])
return
def __init__(self,
rsrcmgr,
outfp,
pageno=1,
laparams=None,
showpageno=False,
imagewriter=None):
PDFConverter.__init__(self,
rsrcmgr,
outfp,
pageno=pageno,
laparams=laparams)
self.showpageno = showpageno
self.imagewriter = imagewriter
self.outtext = ''
def __init__(self,
rsrcmgr,
recorder,
codec='utf-8',
pageno=1,
laparams=None,
imagewriter=None,
pages='all'):
PDFConverter.__init__(self,
rsrcmgr,
outfp=sys.stderr,
codec=codec,
pageno=pageno,
laparams=laparams)
self.recorder = recorder #custom class which is definied next
self.pages = pages
def __init__(self, rsrcmgr, outfp, codec='utf-8', pageno=1, laparams=None):
PDFConverter.__init__(self,
rsrcmgr,
outfp,
codec=codec,
pageno=pageno,
laparams=laparams)
self.layoutmode = 'normal'
self._yoffset = 50
self._font = None
self._fontstack = []
self._posstack = []
self._texts = []
def __init__(self,
rsrcmgr,
outfp,
codec='utf-8',
pageno=1,
laparams=None,
imagewriter=None,
stripcontrol=False):
PDFConverter.__init__(self,
rsrcmgr,
outfp,
codec=codec,
pageno=pageno,
laparams=laparams)
self.imagewriter = imagewriter
self.stripcontrol = stripcontrol
self.root = ContentNode(type="pages")
return
def __init__(self,
rsrcmgr,
doc,
codec='utf-8',
pageno=1,
laparams=None,
imagewriter=None):
PDFConverter.__init__(self,
rsrcmgr,
None,
codec=codec,
pageno=pageno,
laparams=laparams)
self.imagewriter = imagewriter
self.laparams = laparams
self.doc = doc
self.sizes = []
return
def __init__(self, rsrcmgr, outfp, codec='utf-8', pageno=1, laparams=None):
PDFConverter.__init__(self,
rsrcmgr,
codecs.getwriter(
locale.getpreferredencoding())(outfp),
codec=codec,
pageno=pageno,
laparams=laparams)
self.document_root = {'tag': 'pages'}
self.stack = []
self.taglists = dict([
(t, []) for t in
"char pages page textbox textline textbox page rect polygon line figure curve textgrouplrtb textgrouptbrl"
.split()
])
self.hasrun = False
self.interesting_attributes = 'tag index id bbox rotate pageid text size sizes orientation fontname fontnames fontstyles fonts bboxes length height width'.split(
' ')
self.open()
def pdf_to_file(file_path):
resource_manager = PDFResourceManager()
fake_file_handle = io.StringIO()
converter = PDFConverter(resource_manager, fake_file_handle)
page_interpreter = PDFPageInterpreter(converter, resource_manager)
with open(filename, 'rb') as fp:
fp.seek(0, 0)
for page in PDFPage.get_pages(fp, caching=True,
check_extractable=True):
page_interpreter.process_page(int(0))
text = fake_file_handle.getvalue()
converter.close()
fake_file_handle.close()
if text:
return text
def __init__(
self,
rsrcmgr,
codec="utf-8",
pageno=1,
laparams=None,
imagewriter=None,
stripcontrol=False,
):
PDFConverter.__init__(self,
rsrcmgr,
sys.stdout,
codec=codec,
pageno=pageno,
laparams=laparams)
self.rpa_pdf_document = RpaPdfDocument()
self.figure = None
self.current_page = None
self.imagewriter = imagewriter
self.stripcontrol = stripcontrol
self.write_header()
def __init__(self, rsrcmgr):
PDFConverter.__init__(self, rsrcmgr, None, codec='utf-8', pageno=1, laparams=None)
self.pages = {}
return
def __init__(self, rsrcmgr, outfp, codec='utf-8', pageno=1, laparams=None):
PDFConverter.__init__(self, rsrcmgr, outfp, codec=codec, pageno=pageno, laparams=laparams)
self.textlines = []
def render_image(self, name, stream):
if self.imagewriter is None:
return
PDFConverter.render_image(self, name, stream)
return
