document = open('1a_Foundations.pdf', 'rb')
#Create resource manager
rsrcmgr = PDFResourceManager()
# Set parameters for analysis.
laparams = LAParams()
# Create a PDF page aggregator object.
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
pages = PDFPage.create_pages(document)
# interpreter.process_page(pages)
#page is the iterator of the pages, it is for one single page object
title = []
content = []
for page in PDFPage.get_pages(document):
interpreter.process_page(page)
layout = device.get_result()
if layout.pageid > 1:
# print ("aaa")
if parse_obj(layout._objs) == True:
text_title = parse_obj_title(layout._objs).encode(
'ascii', 'ignore')
text_title = text_title[:-1]
title.append(text_title)
text_content = parse_obj_content(layout._objs)
content.append(text_content)
with open('title111.txt', 'w', encoding='utf-8') as f:
for i in title:
f.write(i)
f.write('\n')
from pdfminer3.layout import LAParams, LTTextBox
from pdfminer3.pdfpage import PDFPage
from pdfminer3.pdfinterp import PDFResourceManager
from pdfminer3.pdfinterp import PDFPageInterpreter
from pdfminer3.converter import PDFPageAggregator
from pdfminer3.converter import TextConverter
import io
resource_manager = PDFResourceManager()
fake_file_handle = io.StringIO()
converter = TextConverter(resource_manager,
fake_file_handle,
laparams=LAParams())
page_interpreter = PDFPageInterpreter(resource_manager, converter)
with open('test.pdf', 'rb') as fh:
for page in PDFPage.get_pages(fh, caching=True, check_extractable=True):
page_interpreter.process_page(page)
text = fake_file_handle.getvalue()
# close open handles
converter.close()
fake_file_handle.close()
print(text)
def run(self):
super(XML, self).run()
if self.xml_type == 'letter':
resource_manager = PDFResourceManager()
fake_file_handle = io.BytesIO()
converter = XMLConverter(resource_manager, fake_file_handle)
page_interpreter = PDFPageInterpreter(resource_manager, converter)
with open(self.output_file_path, 'rb') as fh:
for page in PDFPage.get_pages(fh,
caching=True,
check_extractable=True):
page_interpreter.process_page(page)
text = fake_file_handle.getvalue().decode('utf-8')
text += '\n</pages>'
self.output_xml_content = text
# close open handles
converter.close()
fake_file_handle.close()
super(XML, self).deleteOutputFile()
else:
def __extract_text_by_page(pdf_path):
with open(pdf_path, 'rb') as fh:
for page in PDFPage.get_pages(fh,
caching=True,
check_extractable=True):
resource_manager = PDFResourceManager()
fake_file_handle = io.StringIO()
converter = TextConverter(resource_manager,
fake_file_handle,
codec='utf-8')
page_interpreter = PDFPageInterpreter(
resource_manager, converter)
page_interpreter.process_page(page)
text = fake_file_handle.getvalue()
# text = text.encode('utf-8')
yield text
# close open handles
converter.close()
fake_file_handle.close()
def __replace_nontext(text, replacement=u'\uFFFD'):
_char_tail = ''
if sys.maxunicode > 0x10000:
_char_tail = u'%s-%s' % (
chr(0x10000), chr(min(sys.maxunicode, 0x10FFFF)))
_nontext_sub = re.compile(
r'[^\x09\x0A\x0D\x20-\uD7FF\uE000-\uFFFD%s]' % _char_tail,
re.U).sub
return _nontext_sub(replacement, text)
root = xml.Element('{filename}'.format(filename='Result'))
pages = xml.Element('Pages')
root.append(pages)
counter = 1
for page in __extract_text_by_page(self.output_file_path):
text = xml.SubElement(pages, 'Page_{}'.format(counter))
text.text = page[:]
counter += 1
#root.append(pages)
tree = xml.ElementTree(root)
#xml_string = xml.tostring(tree, 'utf-8', method='xml')
xml_string = xml.tostring(root, 'utf-8', method='xml')
xml_string = __replace_nontext(
xml_string.decode('utf-8'),
replacement=u'\uFFFD').encode('utf-8')
#xml_string += '\n</pages>'
parsed_string = minidom.parseString(xml_string)
pretty_string = parsed_string.toprettyxml(indent=' ')
#pretty_string += '\n</pages>'
# with open(output_file_path, 'w', encoding="utf-8") as f:
# f.write(pretty_string)
self.output_xml_content = pretty_string
super(XML, self).deleteOutputFile()
interpreter = PDFPageInterpreter(resource_manager, device)
# 出力用のテキストファイル
# output_txt = open('output.txt', 'w')
def print_and_write(txt):
print(txt)
# output_txt.write(txt)
# output_txt.write('\n')
with open(sys.argv[1], 'rb') as f:
# PDFPage.get_pages()にファイルオブジェクトを指定して、PDFPageオブジェクトを順に取得する。
# 時間がかかるファイルは、キーワード引数pagenosで処理するページ番号（0始まり）のリストを指定するとよい。
for page in PDFPage.get_pages(f):
print_and_write('\n====== ページ区切り ======\n')
interpreter.process_page(page) # ページを処理する。
layout = device.get_result() # LTPageオブジェクトを取得。
# ページ内のテキストボックスのリストを取得する。
boxes = find_textboxes_recursively(layout)
# テキストボックスの左上の座標の順でテキストボックスをソートする。
# y1（Y座標の値）は上に行くほど大きくなるので、正負を反転させている。
boxes.sort(key=lambda b: (-b.y1, b.x0))
for box in boxes:
print_and_write('-' * 10) # 読みやすいよう区切り線を表示する。
print_and_write(box.get_text().strip()) # テキストボックス内のテキストを表示する。
print_and_write(f"{box.x0}, {box.y0} - {box.x1}, {box.y1}"
def scanDoublePages(parent, galleryprices, dailyprices):
daily = open("daily.txt", "w+")
gal = open("gallery.txt", "w+")
sweet = open("sweet.txt", "w+")
duplicatestest = open("duplicatestest.txt", "w+")
number = 0
numberlist = []
originalfile = []
folder = "temp"
cleanFolder(folder)
# listing the files inside the folder
parentnew = list_files_walk(parent)
# creating a temporary folder
os.mkdir(folder)
# splitting the temporary files
splitter(parentnew, folder)
# getting the temporary files
parentnew2 = list_files_walk(folder)
# sorting the files by name
parentnew2.sort()
# iterate over all the files in directory 'parent'
for file_name in parentnew2:
resource_manager = PDFResourceManager()
handle = io.StringIO()
converter = TextConverter(resource_manager, handle)
page_interpreter = PDFPageInterpreter(resource_manager, converter)
arquivo = open(file_name, 'rb')
if "page_001.pdf" in file_name:
number = 0
with arquivo as fh:
for page in PDFPage.get_pages(fh, caching=True, check_extractable=True):
booleangal = True
booleanSweet = True
page_interpreter.process_page(page)
text = handle.getvalue()
text = text[:-1]
text = text + "¬¬¬"
#print(text)
# searching the reference number
search = find_between(text, "#", "Order")
# searching the order number
search2 = find_between(text, "# ", "Order Date")
# Searching the design name
name = find_between(text, "SKUPrice1", "$")
# Prices
price = find_between(text, name, ",")
# Products
products = find_between(text, "SKUPrice1", "¬¬¬")
#print(products)
originalfilenumber = find_between(file_name, "_file_", "_page")
print(originalfilenumber)
if search == "":
numberlist.append(str(number) + ";" + originalfilenumber)
originalfile.append(originalfilenumber)
# print(result[number-1])
# f.write(result[number - 1] + "\n")
else:
duplicatestest.write(search2 + "\n")
for daprices in dailyprices:
if products.find(daprices) != -1:
print(search2 + " Daily Shirt")
booleangal = False
daily.write(name + "^" + file_name + "^" + search2 + "\n")
break
if booleangal:
for gaprices in galleryprices:
if products.find(gaprices) != -1:
print(search2 + " Gallery Shirt")
gal.write(name + "^" + file_name + "^" + search2 + "\n")
booleanSweet = False
break
if booleanSweet:
sweet.write(name + "^" + file_name + "^" + search2 + "\n")
print(search2 + " Sweet Deal")
number = number + 1
converter.close()
handle.close()
daily.close()
gal.close()
duplicatestest.close()
sweet.close()
cleanFolder(folder)
print(originalfile)
print("Files with double pages: ")
print(numberlist)
os.mkdir(folder)
splitterCustom(parentnew, folder, numberlist,originalfile)