텍스트 비교

두 텍스트 파일의 차이점을 찾아보세요

실시간 편집

변경 없는 행 숨기기

줄바꿈 비활성화

레이아웃

비교 단위

구문 강조

Diffchecker Desktop 가장 안전하게 Diffchecker를 사용하는 방법. 데스크톱 앱을 사용하면 비교 데이터가 외부로 전송되지 않습니다!데스크톱 앱 받기

camelot/handlers.py

생성일 5년 전비교 결과 만료 없음

42 삭제

행
총
삭제

글자
총
삭제

이 기능을 계속 사용하려면 업그레이드해 주세요 Diffchecker Pro 요금제 보기

169 행

77 추가

행
총
추가

글자
총
추가

이 기능을 계속 사용하려면 업그레이드해 주세요 Diffchecker Pro 요금제 보기

181 행

# -*- coding: utf-8 -*-

import os

import sys

from PyPDF2 import PdfFileReader, PdfFileWriter

import fitz

from .core import TableList

from .parsers import Stream, Lattice

from .utils import (

TemporaryDirectory,

get_page_layout,

get_text_objects,

get_rotation,

is_url,

download_url,

)

class PDFHandler(object):

"""Handles all operations like temp directory creation, splitting

file into single page PDFs, parsing each PDF and then removing the

temp directory.

Parameters

----------

filepath : str

Filepath or URL of the PDF file.

pages : str, optional (default: '1')

Comma-separated page numbers.

Example: '1,3,4' or '1,4-end' or 'all'.

password : str, optional (default: None)

Password for decryption.

"""

def __init__(self, filepath, pages="1", password=None):

if is_url(filepath):

filepath = download_url(filepath)

self.filepath = filepath

if not filepath.lower().endswith(".pdf"):

raise NotImplementedError("File format not supported")

if password is None:

self.password = ""

else:

self.password = password

if sys.version_info[0] < 3:

self.password = self.password.encode("ascii")

self.pages = self._get_pages(self.filepath, pages)

def _get_pages(self, filepath, pages):

"""Converts pages string to list of ints.

Parameters

----------

filepath : str

Filepath or URL of the PDF file.

pages : str, optional (default: '1')

Comma-separated page numbers.

Example: '1,3,4' or '1,4-end' or 'all'.

Returns

-------

P : list

List of int page numbers.

"""

page_numbers = []

if pages == "1":

page_numbers.append({"start": 1, "end": 1})

else:

instream = open(filepath, "rb")

with fitz.open(filepath) as infile:

infile = PdfFileReader(instream, strict=False)

if infile.needsPass:

if infile.isEncrypted:

infile.authenticate(self.password)

infile.decrypt(self.password)

if pages == "all":

page_numbers.append({"start": 1, "end": infile.pageCount})

page_numbers.append({"start": 1, "end": infile.getNumPages()})

else:

for r in pages.split(","):

if "-" in r:

a, b = r.split("-")

if b == "end":

b = infile.pageCount

b = infile.getNumPages()

page_numbers.append(

page_numbers.append({"start": int(a), "end": int(b)})

{"start": int(a), "end": int(b)})

else:

page_numbers.append({"start": int(r), "end": int(r)})

page_numbers.append(

instream.close()

{"start": int(r), "end": int(r)})

P = []

for p in page_numbers:

P.extend(range(p["start"], p["end"] + 1))

return sorted(set(P))

def _save_page(self, filepath, page, temp):

"""Saves specified page from PDF into a temporary directory.

Parameters

----------

filepath : str

Filepath or URL of the PDF file.

page : int

Page number.

temp : str

Tmp directory.

"""

with open(filepath, "rb") as fileobj:

with fitz.open(filepath) as infile:

infile = PdfFileReader(fileobj, strict=False)

if infile.needsPass:

if infile.isEncrypted:

infile.authenticate(self.password)

infile.decrypt(self.password)

fpath = os.path.join(temp, f"page-{page}.pdf")

froot, fext = os.path.splitext(fpath)

p = infile.getPage(page - 1)

p = infile[page - 1]

outfile = PdfFileWriter()

p.setRotation(0)

outfile.addPage(p)

outfile = fitz.open()

with open(fpath, "wb") as f:

outpage = outfile.newPage(-1, width=p.rect.width,

outfile.write(f)

height=p.rect.height)

outpage.showPDFpage(outpage.rect, infile, pno=page-1)

outfile.save(fpath)

layout, dim = get_page_layout(fpath)

# fix rotated PDF

chars = get_text_objects(layout, ltype="char")

horizontal_text = get_text_objects(layout, ltype="horizontal_text")

vertical_text = get_text_objects(layout, ltype="vertical_text")

rotation = get_rotation(chars, horizontal_text, vertical_text)

if rotation != "":

fpath_new = "".join([froot.replace("page", "p"), "_rotated", fext])

fpath_new = "".join(

[froot.replace("page", "p"), "_rotated", fext])

os.rename(fpath, fpath_new)

instream = open(fpath_new, "rb")

infile = fitz.open(fpath_new)

infile = PdfFileReader(instream, strict=False)

if infile.needsPass:

if infile.isEncrypted:

infile.authenticate(self.password)

infile.decrypt(self.password)

outfile = fitz.open()

outfile = PdfFileWriter()

p = infile[0]

p = infile.getPage(0)

outpage = outfile.newPage(-1, width=p.rect.width,

height=p.rect.height)

outpage.showPDFpage(outpage.rect, infile, pno=0)

if rotation == "anticlockwise":

p.rotateClockwise(90)

outpage.setRotation((p.rotation + 90) % 360)

elif rotation == "clockwise":

p.rotateCounterClockwise(90)

outpage.setRotation((p.rotation + 270) % 360)

outfile.addPage(p)

with open(fpath, "wb") as f:

outfile.save(fpath)

outfile.write(f)

instream.close()

def parse(

self, flavor="lattice", suppress_stdout=False, layout_kwargs={}, **kwargs

"""Extracts tables by calling parser.get_tables on all single

page PDFs.

Parameters

----------

flavor : str (default: 'lattice')

The parsing method to use ('lattice' or 'stream').

Lattice is used by default.

suppress_stdout : str (default: False)

Suppress logs and warnings.

layout_kwargs : dict, optional (default: {})

A dict of `pdfminer.layout.LAParams <https://github.com/euske/pdfminer/blob/master/pdfminer/layout.py#L33>`_ kwargs.

kwargs : dict

See camelot.read_pdf kwargs.

Returns

-------

tables : camelot.core.TableList

List of tables found in PDF.

"""

tables = []

with TemporaryDirectory() as tempdir:

for p in self.pages:

try:

self._save_page(self.filepath, p, tempdir)

for p in self.pages:

pages = [

self._save_page(self.filepath, p, tempdir)

os.path.join(tempdir, f"page-{p}.pdf") for p in self.pages

pages = [

]

os.path.join(tempdir, f"page-{p}.pdf") for p in self.pages

parser = Lattice(**kwargs) if flavor == "lattice" else Stream(**kwargs)

]

for p in pages:

parser = Lattice(

t = parser.extract_tables(

**kwargs) if flavor == "lattice" else Stream(**kwargs)

p, suppress_stdout=suppress_stdout, layout_kwargs=layout_kwargs

for p in pages:

)

t = parser.extract_tables(

tables.extend(t)

p, suppress_stdout=suppress_stdout, layout_kwargs=layout_kwargs

)

tables.extend(t)

except ValueError as err:

if str(err) == "document closed or encrypted":

raise ValueError("file has not been decrypted") from err

raise

return TableList(sorted(tables))

저장된 비교 결과

원본

파일 열기

# -*- coding: utf-8 -*-

import os
import sys

from PyPDF2 import PdfFileReader, PdfFileWriter

from .core import TableList
from .parsers import Stream, Lattice
from .utils import (
    TemporaryDirectory,
    get_page_layout,
    get_text_objects,
    get_rotation,
    is_url,
    download_url,
)

class PDFHandler(object):
    """Handles all operations like temp directory creation, splitting
    file into single page PDFs, parsing each PDF and then removing the
    temp directory.
    Parameters
    ----------
    filepath : str
        Filepath or URL of the PDF file.
    pages : str, optional (default: '1')
        Comma-separated page numbers.
        Example: '1,3,4' or '1,4-end' or 'all'.
    password : str, optional (default: None)
        Password for decryption.
    """

def __init__(self, filepath, pages="1", password=None):
        if is_url(filepath):
            filepath = download_url(filepath)
        self.filepath = filepath
        if not filepath.lower().endswith(".pdf"):
            raise NotImplementedError("File format not supported")

if password is None:
            self.password = ""
        else:
            self.password = password
            if sys.version_info[0] < 3:
                self.password = self.password.encode("ascii")
        self.pages = self._get_pages(self.filepath, pages)

def _get_pages(self, filepath, pages):
        """Converts pages string to list of ints.
        Parameters
        ----------
        filepath : str
            Filepath or URL of the PDF file.
        pages : str, optional (default: '1')
            Comma-separated page numbers.
            Example: '1,3,4' or '1,4-end' or 'all'.
        Returns
        -------
        P : list
            List of int page numbers.
        """
        page_numbers = []
        if pages == "1":
            page_numbers.append({"start": 1, "end": 1})
        else:
            instream = open(filepath, "rb")
            infile = PdfFileReader(instream, strict=False)
            if infile.isEncrypted:
                infile.decrypt(self.password)
            if pages == "all":
                page_numbers.append({"start": 1, "end": infile.getNumPages()})
            else:
                for r in pages.split(","):
                    if "-" in r:
                        a, b = r.split("-")
                        if b == "end":
                            b = infile.getNumPages()
                        page_numbers.append({"start": int(a), "end": int(b)})
                    else:
                        page_numbers.append({"start": int(r), "end": int(r)})
            instream.close()
        P = []
        for p in page_numbers:
            P.extend(range(p["start"], p["end"] + 1))
        return sorted(set(P))

def _save_page(self, filepath, page, temp):
        """Saves specified page from PDF into a temporary directory.
        Parameters
        ----------
        filepath : str
            Filepath or URL of the PDF file.
        page : int
            Page number.
        temp : str
            Tmp directory.
        """
        with open(filepath, "rb") as fileobj:
            infile = PdfFileReader(fileobj, strict=False)
            if infile.isEncrypted:
                infile.decrypt(self.password)
            fpath = os.path.join(temp, f"page-{page}.pdf")
            froot, fext = os.path.splitext(fpath)
            p = infile.getPage(page - 1)
            outfile = PdfFileWriter()
            outfile.addPage(p)
            with open(fpath, "wb") as f:
                outfile.write(f)
            layout, dim = get_page_layout(fpath)
            # fix rotated PDF
            chars = get_text_objects(layout, ltype="char")
            horizontal_text = get_text_objects(layout, ltype="horizontal_text")
            vertical_text = get_text_objects(layout, ltype="vertical_text")
            rotation = get_rotation(chars, horizontal_text, vertical_text)
            if rotation != "":
                fpath_new = "".join([froot.replace("page", "p"), "_rotated", fext])
                os.rename(fpath, fpath_new)
                instream = open(fpath_new, "rb")
                infile = PdfFileReader(instream, strict=False)
                if infile.isEncrypted:
                    infile.decrypt(self.password)
                outfile = PdfFileWriter()
                p = infile.getPage(0)
                if rotation == "anticlockwise":
                    p.rotateClockwise(90)
                elif rotation == "clockwise":
                    p.rotateCounterClockwise(90)
                outfile.addPage(p)
                with open(fpath, "wb") as f:
                    outfile.write(f)
                instream.close()

def parse(
        self, flavor="lattice", suppress_stdout=False, layout_kwargs={}, **kwargs
    ):
        """Extracts tables by calling parser.get_tables on all single
        page PDFs.
        Parameters
        ----------
        flavor : str (default: 'lattice')
            The parsing method to use ('lattice' or 'stream').
            Lattice is used by default.
        suppress_stdout : str (default: False)
            Suppress logs and warnings.
        layout_kwargs : dict, optional (default: {})
            A dict of `pdfminer.layout.LAParams <https://github.com/euske/pdfminer/blob/master/pdfminer/layout.py#L33>`_ kwargs.
        kwargs : dict
            See camelot.read_pdf kwargs.
        Returns
        -------
        tables : camelot.core.TableList
            List of tables found in PDF.
        """
        tables = []
        with TemporaryDirectory() as tempdir:
            for p in self.pages:
                self._save_page(self.filepath, p, tempdir)
            pages = [
                os.path.join(tempdir, f"page-{p}.pdf") for p in self.pages
            ]
            parser = Lattice(**kwargs) if flavor == "lattice" else Stream(**kwargs)
            for p in pages:
                t = parser.extract_tables(
                    p, suppress_stdout=suppress_stdout, layout_kwargs=layout_kwargs
                )
                tables.extend(t)
        return TableList(sorted(tables))

수정본

파일 열기

# -*- coding: utf-8 -*-

import os
import sys

import fitz

def _get_pages(self, filepath, pages):
        """Converts pages string to list of ints.
        Parameters
        ----------
        filepath : str
            Filepath or URL of the PDF file.
        pages : str, optional (default: '1')
            Comma-separated page numbers.
            Example: '1,3,4' or '1,4-end' or 'all'.
        Returns
        -------
        P : list
            List of int page numbers.
        """
        page_numbers = []
        if pages == "1":
            page_numbers.append({"start": 1, "end": 1})
        else:
            with fitz.open(filepath) as infile:
                if infile.needsPass:
                    infile.authenticate(self.password)
                if pages == "all":
                    page_numbers.append({"start": 1, "end": infile.pageCount})
                else:
                    for r in pages.split(","):
                        if "-" in r:
                            a, b = r.split("-")
                            if b == "end":
                                b = infile.pageCount
                            page_numbers.append(
                                {"start": int(a), "end": int(b)})
                        else:
                            page_numbers.append(
                                {"start": int(r), "end": int(r)})
        P = []
        for p in page_numbers:
            P.extend(range(p["start"], p["end"] + 1))
        return sorted(set(P))

def _save_page(self, filepath, page, temp):
        """Saves specified page from PDF into a temporary directory.
        Parameters
        ----------
        filepath : str
            Filepath or URL of the PDF file.
        page : int
            Page number.
        temp : str
            Tmp directory.
        """
        with fitz.open(filepath) as infile:
            if infile.needsPass:
                infile.authenticate(self.password)
            fpath = os.path.join(temp, f"page-{page}.pdf")
            froot, fext = os.path.splitext(fpath)
            p = infile[page - 1]
            p.setRotation(0)
            outfile = fitz.open()
            outpage = outfile.newPage(-1, width=p.rect.width,
                                      height=p.rect.height)
            outpage.showPDFpage(outpage.rect, infile, pno=page-1)
            outfile.save(fpath)

layout, dim = get_page_layout(fpath)
            # fix rotated PDF
            chars = get_text_objects(layout, ltype="char")
            horizontal_text = get_text_objects(layout, ltype="horizontal_text")
            vertical_text = get_text_objects(layout, ltype="vertical_text")
            rotation = get_rotation(chars, horizontal_text, vertical_text)
            if rotation != "":
                fpath_new = "".join(
                    [froot.replace("page", "p"), "_rotated", fext])
                os.rename(fpath, fpath_new)
                infile = fitz.open(fpath_new)
                if infile.needsPass:
                    infile.authenticate(self.password)
                outfile = fitz.open()
                p = infile[0]

outpage = outfile.newPage(-1, width=p.rect.width,
                                          height=p.rect.height)
                outpage.showPDFpage(outpage.rect, infile, pno=0)
                if rotation == "anticlockwise":
                    outpage.setRotation((p.rotation + 90) % 360)
                elif rotation == "clockwise":
                    outpage.setRotation((p.rotation + 270) % 360)

outfile.save(fpath)

def parse(
        self, flavor="lattice", suppress_stdout=False, layout_kwargs={}, **kwargs
    ):
        """Extracts tables by calling parser.get_tables on all single
        page PDFs.
        Parameters
        ----------
        flavor : str (default: 'lattice')
            The parsing method to use ('lattice' or 'stream').
            Lattice is used by default.
        suppress_stdout : str (default: False)
            Suppress logs and warnings.
        layout_kwargs : dict, optional (default: {})
            A dict of `pdfminer.layout.LAParams <https://github.com/euske/pdfminer/blob/master/pdfminer/layout.py#L33>`_ kwargs.
        kwargs : dict
            See camelot.read_pdf kwargs.
        Returns
        -------
        tables : camelot.core.TableList
            List of tables found in PDF.
        """
        tables = []
        with TemporaryDirectory() as tempdir:
            try:
                for p in self.pages:
                    self._save_page(self.filepath, p, tempdir)
                pages = [
                    os.path.join(tempdir, f"page-{p}.pdf") for p in self.pages
                ]
                parser = Lattice(
                    **kwargs) if flavor == "lattice" else Stream(**kwargs)
                for p in pages:
                    t = parser.extract_tables(
                        p, suppress_stdout=suppress_stdout, layout_kwargs=layout_kwargs
                    )
                    tables.extend(t)
            except ValueError as err:
                if str(err) == "document closed or encrypted":
                    raise ValueError("file has not been decrypted") from err

raise

return TableList(sorted(tables))