Как читать pdf-файл с помощью pdfminer3k?


Я скорректировал код Лизы. Он работает сейчас!

    fp = open(path, 'rb')
    from pdfminer.pdfparser import PDFParser, PDFDocument
    from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
    from pdfminer.converter import PDFPageAggregator
    from pdfminer.layout import LAParams, LTTextBox, LTTextLine

    parser = PDFParser(fp)
    doc = PDFDocument()
    parser.set_document(doc)
    doc.set_parser(parser)
    doc.initialize('')
    rsrcmgr = PDFResourceManager()
    laparams = LAParams()
    laparams.char_margin = 1.0
    laparams.word_margin = 1.0
    device = PDFPageAggregator(rsrcmgr, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    extracted_text = ''

    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):
                extracted_text += lt_obj.get_text()

1

Я использую python 3.4, но я предполагаю, что он работает одинаково с python 3.5. Вот что я использую:

from pdfminer.pdfparser import PDFParser, PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LAParams, LTTextBox, LTTextLine

parser = PDFParser(file_content)
doc = PDFDocument()
parser.set_document(doc)
doc.set_parser(parser)
doc.initialize('')
rsrcmgr = PDFResourceManager()
laparams = LAParams()
#I changed the following 2 parameters to get rid of white spaces inside words:
laparams.char_margin = 1.0
laparams.word_margin = 1.0
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
extracted_text = ''

# 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):
            extracted_text += string

with open('convertedFile.txt',"wb") as txt_file:
    txt_file.write(extracted_text.encode("utf-8"))
питон-3.x, питон-3,5,

python-3.x,python-3.5,

3

Ответов: 2


Я скорректировал код Лизы. Он работает сейчас!

    fp = open(path, 'rb')
    from pdfminer.pdfparser import PDFParser, PDFDocument
    from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
    from pdfminer.converter import PDFPageAggregator
    from pdfminer.layout import LAParams, LTTextBox, LTTextLine

    parser = PDFParser(fp)
    doc = PDFDocument()
    parser.set_document(doc)
    doc.set_parser(parser)
    doc.initialize('')
    rsrcmgr = PDFResourceManager()
    laparams = LAParams()
    laparams.char_margin = 1.0
    laparams.word_margin = 1.0
    device = PDFPageAggregator(rsrcmgr, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    extracted_text = ''

    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):
                extracted_text += lt_obj.get_text()

1

Я использую python 3.4, но я предполагаю, что он работает одинаково с python 3.5. Вот что я использую:

from pdfminer.pdfparser import PDFParser, PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LAParams, LTTextBox, LTTextLine

parser = PDFParser(file_content)
doc = PDFDocument()
parser.set_document(doc)
doc.set_parser(parser)
doc.initialize('')
rsrcmgr = PDFResourceManager()
laparams = LAParams()
#I changed the following 2 parameters to get rid of white spaces inside words:
laparams.char_margin = 1.0
laparams.word_margin = 1.0
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
extracted_text = ''

# 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):
            extracted_text += string

with open('convertedFile.txt',"wb") as txt_file:
    txt_file.write(extracted_text.encode("utf-8"))
питон-3.x, питон-3,5,
Похожие вопросы