def export_as_csv(pdf_path, csv_path):
filename = os.path.splitext(os.path.basename(pdf_path))[0]
with open(csv_path, 'w', encoding="utf-8") as csv_file:
writer = csv.writer(csv_file)
return_data = []
go = 0
for page in extract_text_by_page(pdf_path):
for letter in page:
if letter == '.':
go = 1
if go == 1 and letter != '.':
if letter in [u"\u25B6"]:
return_data.append(' TRIANGLE ')
pattern = re.search(r'[a-zA-Z0-9]{1}', letter)
if pattern:
return_data.append(letter)
else:
if letter not in [u"\u25B6"]:
s = letter.encode('raw_unicode_escape')
if s in [b'\x0c']:
return_data = ''.join(return_data)
writer.writerow([return_data])
return_data = []
else:
return_data.append(letter)
writer.writerow([return_data])
def export_as_csv(pdf_path, csv_path):
filename = os.path.splitext(os.path.basename(pdf_path))[0]
counter = 1
with open(pdf_path, 'w') as csv_file:
writer = csv.writer(csv_file)
for page in extract_text_by_page(pdf_path):
text = page[0:100]
words = text.split()
writer.writerow(words)
def export_as_json(pdf_path, json_path):
filename = os.path.splitext(os.path.basename(pdf_path))[0]
data = {'Filename': filename}
data['Pages'] = []
counter = 1
for page in extract_text_by_page(pdf_path):
text = page[0:100]
page = {'Page_{}'.format(counter): text}
data['Pages'].append(page)
counter += 1
with open(json_path, 'w') as fh:
json.dump(data, fh)
def export_as_json(pdf_path, json_path):
filename = os.path.splitext(os.path.basename(pdf_path))[0]
data = {'Filename': filename}
data['Pages'] = []
counter = 1
for page in extract_text_by_page(pdf_path):
text = re.sub("\x0c",' ',page)
# 连字符深恶痛绝！
text = text.replace('fi','fi').replace('fl','fl').replace('ff','ff').replace('ffi','ffi').replace('ffl','ffl')
page = {'Page_number':counter ,'text': text.lower()}
data['Pages'].append(page)
counter += 1
with open(json_path, 'w') as fh:
json.dump(data, fh)
def export_as_csv(pdf_path, csv_path, title_array):
filename = os.path.splitext(os.path.basename(pdf_path))[0]
row_length = len(title_array)
with open(csv_path, 'w') as csv_file:
writer = csv.writer(csv_file)
writer.writerow(title_array)
for page in extract_text_by_page(pdf_path):
text = page.replace('\u25cf', ',')
words = text.split()
array = []
for key, word in enumerate(words):
key = key + 1
if key % row_length == 0:
array.append(word)
writer.writerow(array)
array = []
if key % row_length != 0:
array.append(word)
def export_as_xml(pdf_path, xml_path):
filename = os.path.splitext(os.path.basename(pdf_path))[0]
root = xml.Element('{filename}'.format(filename=filename))
pages = xml.Element('Pages')
root.append(pages)
counter = 1
for page in extract_text_by_page(pdf_path):
text = xml.SubElement(pages, 'Page_{}'.format(counter))
text.text = page[0:100]
counter += 1
tree = xml.ElementTree(root)
xml_string = xml.tostring(root, 'utf-8')
parsed_string = minidom.parseString(xml_string)
pretty_string = parsed_string.toprettyxml(indent=' ')
with open(xml_path, 'w') as fh:
fh.write(pretty_string)
def export_as_json(pdf_path):
filename = os.path.splitext(os.path.basename(pdf_path))[0]
data = {'filename': filename, 'number': None}
data['pages'] = []
doc_content_correct = False
doc_number = None
counter = 1
for page in extract_text_by_page(pdf_path):
parsed_page = parse_page(page)
if get_doc_content_correct(parsed_page):
doc_content_correct = True
doc_number = get_doc_number(parsed_page)
content = parsed_page
if counter > 3:
content = parsed_page.split('Взам. Инв. № 3434')
# if content[1]:
# content = content[1]
d = {
'page': counter,
'content': content,
}
data['pages'].append(d)
counter += 1
data['number'] = doc_number
if doc_content_correct == False:
# print("ОШИБКА - Нет или неправильная страница 'Содержание'")
data['errors'] = [
"Содержание тома; Лист: 4. Основная надпись: графа (1) - шифр должен соответствовать шифру, указанному на тит. листе, и добавляется через дефис прописная буква С"
]
# with open(json_path, 'w', encoding="utf-8") as fh:
# json.dump(data, fh, ensure_ascii=False)
return data
def export_as_xml(pdf_path, xml_path):
arquivo = easygui.fileopenbox()
pdf_path = arquivo
filename_w_ext = os.path.basename(arquivo)
filename, file_extension = os.path.splitext(filename_w_ext)
saida = (filename + '_Corrigido.xml')
filename = os.path.splitext(os.path.basename(pdf_path))[0]
root = xml.Element('{filename}'.format(filename=filename))
pages = xml.Element('Pages')
root.append(pages)
counter = 1
for page in extract_text_by_page(pdf_path):
text = xml.SubElement(pages, 'Page_{}'.format(counter))
text.text = page[0:100]
counter += 1
tree = xml.ElementTree(root)
xml_string = xml.tostring(root, 'utf-8')
parsed_string = minidom.parseString(xml_string)
pretty_string = parsed_string.toprettyxml(indent=' ')
with open(xml_path, 'w') as fh:
fh.write(pretty_string)
def extract_text(pdf_path):
for page in extract_text_by_page(pdf_path):
print(page)
print()
