def process_pdf(file):
#Creating the required objects
resource_manager = PDFResourceManager()
laparams = LAParams()
device = PDFPageAggregator(resource_manager, laparams=laparams)
page_interpreter = PDFPageInterpreter(resource_manager, device)
#This list will contain the text at each page of the document.
pdfText = list()
#Processing each page in the pdf.
for page in PDFPage.get_pages(file):
page_interpreter.process_page(page)
layout = device.get_result()
text = ""
for element in layout:
# Whenever, we encounter the layout type as text box, we get the text.
# This is to skip images if any.
if isinstance(element, LTTextBox):
text += element.get_text()
pdfText.append(text)
#Returing a list, where element at each index contains the text at each page
return pdfText
def __init__(self, pdf, codec='utf-8'):
"""
Parameters:
--------------
codec: codific, default utf-8
pdf: path to the pdf file
Attributes:
---------------
records: list of lines from the pdf file
text: string of joined records, default ""
didascalies: list of found didascalies with regexpr
nimages: int, number of found images
"""
self.pdf = pdf
self.text = ""
self.records = []
self.didascalies = []
self.nimages = 0
self.images = []
parser = PDFParser(pdf)
#parser = PDFParser(open(pdf, 'rb'))
document = PDFDocument(parser)
if not document.is_extractable:
raise PDFTextExtractionNotAllowed
# Create a PDF resource manager object
# that stores shared resources.
rsrcmgr = PDFResourceManager()
# Create a buffer for the parsed text
retstr = StringIO()
# Spacing parameters for parsing
laparams = LAParams()
self.codec = codec
device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
# Create a PDF interpreter object
interpreter = PDFPageInterpreter(rsrcmgr, device)
# Process each page contained in the document.
for page in PDFPage.create_pages(document):
interpreter.process_page(page)
#images
img_device = PDFPageAggregator(rsrcmgr, laparams=laparams)
img_interpreter = PDFPageInterpreter(rsrcmgr, img_device)
for page in PDFPage.create_pages(document):
img_interpreter.process_page(page)
pdf_item = img_device.get_result()
if pdf_item is not None:
for thing in pdf_item:
if isinstance(thing, LTImage):
self.save_image(thing)
if isinstance(thing, LTFigure):
self.find_images_in_thing(thing)
lines = retstr.getvalue().splitlines()
for line in lines:
self.records.append(line)
def _extract_pdf_scores(stream):
# these laparams seem to work ok with the ILIAS default PDF
# formatting as well as with UR custom styling.
# see pdf/tests/default_style.pdf and pdf/tests.ur_style.pdf
laparams = LAParams(line_overlap=0,
char_margin=20,
word_margin=0.1,
boxes_flow=0,
detect_vertical=False)
rsrcmgr = PDFResourceManager()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
parser = PDFParser(stream)
document = PDFDocument(parser)
page = next(PDFPage.create_pages(document))
interpreter.process_page(page)
layout = device.get_result()
boxes = []
table_head_y = None # y position of result table header
order_name = "Reihenfolge" # FIXME localize
for element in layout:
if isinstance(element, LTTextBoxHorizontal):
boxes.append(element)
if order_name in element.get_text().strip():
table_head_y = element.y0
tboxes = list(filter(lambda box: box.y0 == table_head_y, boxes))
# if LAParams is set correctly, head should extract the whole
# results table's text now.
table = tboxes[0].get_text().replace('\t', '')
table = table[table.find(order_name):]
# note: question titles might lack spaces; this is no problem
# since we compare question names and scores only through
# Result.normalize_question_title() later.
scores = dict()
cols = []
for line in table.split("\n")[1:]:
cols += re.split(r'\s+', line)
if len(cols) >= 6:
scores[cols[2]] = cols[4]
cols = cols[6:]
return scores
def convert(pdffile):
my_file = pdffile
extracted_text = ""
# Open and read the pdf file in binary mode
fp = open(my_file, "rb")
# Create parser object to parse the pdf content
parser = PDFParser(fp)
# Store the parsed content in PDFDocument object
document = PDFDocument(parser, password)
# Check if document is extractable, if not abort
if not document.is_extractable:
raise PDFTextExtractionNotAllowed
# Create PDFResourceManager object that stores shared resources such as fonts or images
rsrcmgr = PDFResourceManager()
# set parameters for analysis
laparams = LAParams()
# Create a PDFDevice object which translates interpreted information into desired format
# Device needs to be connected to resource manager to store shared resources
# device = PDFDevice(rsrcmgr)
# Extract the decive to page aggregator to get LT object elements
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
# Create interpreter object to process page content from PDFDocument
# Interpreter needs to be connected to resource manager for shared resources and device
interpreter = PDFPageInterpreter(rsrcmgr, device)
# Ok now that we have everything to process a pdf document, lets process it page by page
for page in PDFPage.create_pages(document):
# As the interpreter processes the page stored in PDFDocument object
interpreter.process_page(page)
# The device renders the layout from interpreter
layout = device.get_result()
# Out of the many LT objects within layout, we are interested in LTTextBox and LTTextLine
for lt_obj in layout:
if isinstance(lt_obj, LTTextBox) or isinstance(lt_obj, LTTextLine):
extracted_text += lt_obj.get_text()
#close the pdf file
fp.close()
# print (extracted_text.encode("utf-8"))
with open(log_file, "wb") as my_log:
my_log.write(extracted_text.encode("utf-8"))
print("Done !!")
def main(args):
msg(SCRIPT, args)
if len(args) != 1:
msg('Parse a PDF file and print some pdfminer-specific stats')
msg('Usage:', SCRIPT, '<PDF-filename>')
return 1
infilename, = args
lt_types = collections.Counter()
with open(infilename, 'rb') as pdf_file:
# Create a PDF parser object associated with the file object.
parser = PDFParser(pdf_file)
# Create a PDF document object that stores the document structure.
# Supply the password for initialization.
password = ''
document = PDFDocument(parser, password)
# Check if the document allows text extraction.
if not document.is_extractable:
raise PDFTextExtractionNotAllowed(filename)
# Make a page iterator
pages = PDFPage.create_pages(document)
# Set up for some analysis
rsrcmgr = PDFResourceManager()
laparams = LAParams(
detect_vertical=True,
all_texts=True,
)
#device = PDFDevice(rsrcmgr)
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
# Look at all (nested) objects on each page
for page_count, page in enumerate(pages, 1):
# oh so stateful
interpreter.process_page(page)
layout = device.get_result()
lt_types.update(type(item).__name__ for item in flat_iter(layout))
msg('page_count', page_count)
msg('lt_types:', ' '.join('{}:{}'.format(*tc) for tc in lt_types.items()))
def pdfparser(filename):
fp = open(filename, 'rb')
rsrcmgr = PDFResourceManager()
codec = 'utf-8'
laparams = LAParams()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
# Create a PDF interpreter object.
interpreter = PDFPageInterpreter(rsrcmgr, device)
# Process each page contained in the document.
paginas = []
for page in PDFPage.get_pages(fp, check_extractable=False):
interpreter.process_page(page)
layout = device.get_result()
pagina = []
for element in layout:
if isinstance(element, LTTextBox) or isinstance(element, LTText):
texto = element.get_text()
if texto:
if len(texto) < 2:
pagina[-1] += texto
else:
pagina += texto.split("\n")
# limpa linhas vazias
pagina_limpa = []
for linha in pagina:
if linha.strip():
pagina_limpa.append(linha.strip())
if len(pagina_limpa) > 0:
paginas.append(pagina_limpa)
text_filename = os.path.splitext(filename)[0] + '.txt'
textfile = open(text_filename, 'w')
# remove header
header_candidato = ''
for pagina in paginas:
if pagina[0].strip() != header_candidato:
header_candidato = pagina[0].strip()
else:
pagina.pop(0)
for linha in pagina:
textfile.write("%s\n" % linha)
textfile.close()
def convert_pdf_to_txt(path):
fp = open(path, 'rb')
txt = ''
parser = PDFParser(fp)
doc = PDFDocument()
parser.set_document(doc)
doc.set_parser(parser)
doc.initialize('')
rsrcmgr = PDFResourceManager()
laparams = LAParams()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
# Process each page contained in the document.
for page in doc.get_pages():
interpreter.process_page(page)
layout = device.get_result()
for lt_obj in layout:
if isinstance(lt_obj, LTTextBox) or isinstance(lt_obj, LTTextLine):
txt += lt_obj.get_text()
return (txt)
def parse(path):
fp = open(path, 'rb') # 以二进制读模式打开
praser = PDFParser(fp)
# 创建一个PDF文档
doc = PDFDocument()
# 连接分析器 与文档对象
praser.set_document(doc)
doc.set_parser(praser)
# 提供初始化密码
# 如果没有密码 就创建一个空的字符串
doc.initialize()
# 检测文档是否提供txt转换，不提供就忽略
if not doc.is_extractable:
raise PDFTextExtractionNotAllowed
else:
# 创建PDf 资源管理器 来管理共享资源
rsrcmgr = PDFResourceManager()
# 创建一个PDF设备对象
laparams = LAParams()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
# 创建一个PDF解释器对象
interpreter = PDFPageInterpreter(rsrcmgr, device)
fulltext = []
# 循环遍历列表，每次处理一个page的内容
for page in doc.get_pages(): # doc.get_pages() 获取page列表
interpreter.process_page(page)
# 接受该页面的LTPage对象
layout = device.get_result()
str_page = ""
for x in layout:
if isinstance(x, LTTextBoxHorizontal):
results = x.get_text()
str_page += results
fulltext.append(str_page)
return fulltext
from pdfminer3.layout import LAParams, LTTextBox, LTLine, LTTextLine
from pdfminer3.pdfpage import PDFPage
from pdfminer3.pdfinterp import PDFResourceManager
from pdfminer3.pdfinterp import PDFPageInterpreter
from pdfminer3.converter import PDFPageAggregator
extracted_text = ''
fp = open('C:\\Users\\Ritvik\\Desktop\\Tekoaly\\PDF\\768686236423.pdf', 'rb')
rsrcmgr = PDFResourceManager()
laparams = LAParams()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
pages = PDFPage.get_pages(fp)
for page in pages:
print('Processing next page...')
interpreter.process_page(page)
layout = device.get_result()
for lt_obj in layout:
if isinstance(lt_obj, LTTextBox) or isinstance(lt_obj, LTTextLine):
extracted_text += lt_obj.get_text()
print(extracted_text)
# for lobj in layout:
# if isinstance(lobj, LTTextBox):
# x, y, text = lobj.bbox[0], lobj.bbox[3], lobj
# print(' text: %s' % (text) ,end=' ')
class VhdlSpecParser():
FONT_TRANSLATION = {"HEFBHG+TimesNewRomanPS-ItalicMT": "it",
"HEFBAE+TimesNewRomanPS-BoldMT": "b",
"HEFBBF+TimesNewRomanPSMT": None,
None:None}
FOOTER_STR = 'Copyright © 2009 IEEE. All rights reserved.'
def __init__(self, ofile):
rsrcmgr = PDFResourceManager()
laparams = LAParams()
self.device = PDFPageAggregator(rsrcmgr, laparams=laparams)
self.interpreter = PDFPageInterpreter(rsrcmgr, self.device)
self.last_font = None
self.in_rule = False
self.font_print_pending = False
self.header_footer_skipping = False
self.ofile = ofile
def parse_page(self, page):
self.interpreter.process_page(page)
layout = self.device.get_result()
self.parse_obj(layout._objs)
def parse_obj(self, objs):
font_translation = self.FONT_TRANSLATION
for obj in objs:
if isinstance(obj, pdfminer3.layout.LTTextBox):
for o in obj._objs:
if isinstance(o, pdfminer3.layout.LTTextLine):
if self.header_footer_skipping:
text = o.get_text()
if text.startswith("Std 1076-"):
self.header_footer_skipping = False
continue
text = o.get_text()
if text.startswith(self.FOOTER_STR):
self.header_footer_skipping = True
continue
# print(text)
is_rule_header = "::=" in text
if is_rule_header or self.in_rule:
self.in_rule = True
if not is_rule_header:
if text and not text.startswith(" "):
self.in_rule = False
continue
if text.strip():
for c in o._objs:
if isinstance(c, pdfminer3.layout.LTChar) and self.last_font != c.fontname:
# this character has different font need to propagate it to output
self.font_print_pending = True
if c.get_text().isspace() and font_translation[self.last_font] is not None:
# print the font enclosing string directly after this word (ignore whitespaces behind)
self.font_print_pending = True
self.ofile.write("</%s>" % f)
self.last_font = None
if self.font_print_pending and not (c.get_text().isspace()):
self.font_print_pending = False
f = font_translation[self.last_font]
if f:
self.ofile.write("</%s>" % f)
f = font_translation[c.fontname]
if f:
self.ofile.write("<%s>" % f)
self.last_font = c.fontname
self.ofile.write(c.get_text())
# if it's a container, recurse
elif isinstance(obj, pdfminer3.layout.LTFigure):
parse_obj(obj._objs)
else:
pass
# 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}"
) # テキストボックスの座標を表示する。
# output_txt.close()