用于将PDF转换为文本的Python模块

时间:2008-08-25 04:44:06

标签: python pdf text-extraction pdf-scraping

哪些是将PDF文件转换为文本的最佳Python模块?

13 个答案:

答案 0 :(得分:134)

PDFMiner发布以来,codeape包已更改。

编辑(再次):

PDFMiner已在版本20100213

中再次更新

您可以使用以下内容检查已安装的版本:

>>> import pdfminer
>>> pdfminer.__version__
'20100213'

这是更新版本(包含我更改/添加内容的评论):

def pdf_to_csv(filename):
    from cStringIO import StringIO  #<-- added so you can copy/paste this to try it
    from pdfminer.converter import LTTextItem, TextConverter
    from pdfminer.pdfparser import PDFDocument, PDFParser
    from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter

    class CsvConverter(TextConverter):
        def __init__(self, *args, **kwargs):
            TextConverter.__init__(self, *args, **kwargs)

        def end_page(self, i):
            from collections import defaultdict
            lines = defaultdict(lambda : {})
            for child in self.cur_item.objs:
                if isinstance(child, LTTextItem):
                    (_,_,x,y) = child.bbox                   #<-- changed
                    line = lines[int(-y)]
                    line[x] = child.text.encode(self.codec)  #<-- changed

            for y in sorted(lines.keys()):
                line = lines[y]
                self.outfp.write(";".join(line[x] for x in sorted(line.keys())))
                self.outfp.write("\n")

    # ... the following part of the code is a remix of the 
    # convert() function in the pdfminer/tools/pdf2text module
    rsrc = PDFResourceManager()
    outfp = StringIO()
    device = CsvConverter(rsrc, outfp, codec="utf-8")  #<-- changed 
        # becuase my test documents are utf-8 (note: utf-8 is the default codec)

    doc = PDFDocument()
    fp = open(filename, 'rb')
    parser = PDFParser(fp)       #<-- changed
    parser.set_document(doc)     #<-- added
    doc.set_parser(parser)       #<-- added
    doc.initialize('')

    interpreter = PDFPageInterpreter(rsrc, device)

    for i, page in enumerate(doc.get_pages()):
        outfp.write("START PAGE %d\n" % i)
        interpreter.process_page(page)
        outfp.write("END PAGE %d\n" % i)

    device.close()
    fp.close()

    return outfp.getvalue()

编辑(再次):

以下是pypi 20100619p1中最新版本的更新。简而言之,我用LTTextItem替换了LTChar并将一个LAParams实例传递给了CsvConverter构造函数。

def pdf_to_csv(filename):
    from cStringIO import StringIO  
    from pdfminer.converter import LTChar, TextConverter    #<-- changed
    from pdfminer.layout import LAParams
    from pdfminer.pdfparser import PDFDocument, PDFParser
    from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter

    class CsvConverter(TextConverter):
        def __init__(self, *args, **kwargs):
            TextConverter.__init__(self, *args, **kwargs)

        def end_page(self, i):
            from collections import defaultdict
            lines = defaultdict(lambda : {})
            for child in self.cur_item.objs:
                if isinstance(child, LTChar):               #<-- changed
                    (_,_,x,y) = child.bbox                   
                    line = lines[int(-y)]
                    line[x] = child.text.encode(self.codec)

            for y in sorted(lines.keys()):
                line = lines[y]
                self.outfp.write(";".join(line[x] for x in sorted(line.keys())))
                self.outfp.write("\n")

    # ... the following part of the code is a remix of the 
    # convert() function in the pdfminer/tools/pdf2text module
    rsrc = PDFResourceManager()
    outfp = StringIO()
    device = CsvConverter(rsrc, outfp, codec="utf-8", laparams=LAParams())  #<-- changed
        # becuase my test documents are utf-8 (note: utf-8 is the default codec)

    doc = PDFDocument()
    fp = open(filename, 'rb')
    parser = PDFParser(fp)       
    parser.set_document(doc)     
    doc.set_parser(parser)       
    doc.initialize('')

    interpreter = PDFPageInterpreter(rsrc, device)

    for i, page in enumerate(doc.get_pages()):
        outfp.write("START PAGE %d\n" % i)
        if page is not None:
            interpreter.process_page(page)
        outfp.write("END PAGE %d\n" % i)

    device.close()
    fp.close()

    return outfp.getvalue()

编辑(再一次):

更新版本20110515(感谢Oeufcoque Penteano!):

def pdf_to_csv(filename):
    from cStringIO import StringIO  
    from pdfminer.converter import LTChar, TextConverter
    from pdfminer.layout import LAParams
    from pdfminer.pdfparser import PDFDocument, PDFParser
    from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter

    class CsvConverter(TextConverter):
        def __init__(self, *args, **kwargs):
            TextConverter.__init__(self, *args, **kwargs)

        def end_page(self, i):
            from collections import defaultdict
            lines = defaultdict(lambda : {})
            for child in self.cur_item._objs:                #<-- changed
                if isinstance(child, LTChar):
                    (_,_,x,y) = child.bbox                   
                    line = lines[int(-y)]
                    line[x] = child._text.encode(self.codec) #<-- changed

            for y in sorted(lines.keys()):
                line = lines[y]
                self.outfp.write(";".join(line[x] for x in sorted(line.keys())))
                self.outfp.write("\n")

    # ... the following part of the code is a remix of the 
    # convert() function in the pdfminer/tools/pdf2text module
    rsrc = PDFResourceManager()
    outfp = StringIO()
    device = CsvConverter(rsrc, outfp, codec="utf-8", laparams=LAParams())
        # becuase my test documents are utf-8 (note: utf-8 is the default codec)

    doc = PDFDocument()
    fp = open(filename, 'rb')
    parser = PDFParser(fp)       
    parser.set_document(doc)     
    doc.set_parser(parser)       
    doc.initialize('')

    interpreter = PDFPageInterpreter(rsrc, device)

    for i, page in enumerate(doc.get_pages()):
        outfp.write("START PAGE %d\n" % i)
        if page is not None:
            interpreter.process_page(page)
        outfp.write("END PAGE %d\n" % i)

    device.close()
    fp.close()

    return outfp.getvalue()

答案 1 :(得分:131)

试试PDFMiner。它可以从PDF文件中提取HTML,SGML或“Tagged PDF”格式的文本。

标记的PDF格式似乎是最干净的,剥离XML标记只留下裸文本。

Python 3版本位于:

答案 2 :(得分:59)

由于这些解决方案都没有支持最新版本的PDFMiner,我编写了一个简单的解决方案,它将使用PDFMiner返回pdf的文本。这适用于那些使用process_pdf

导致导入错误的用户
import sys
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFPage
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.layout import LAParams
from cStringIO import StringIO

def pdfparser(data):

    fp = file(data, 'rb')
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    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.get_pages(fp):
        interpreter.process_page(page)
        data =  retstr.getvalue()

    print data

if __name__ == '__main__':
    pdfparser(sys.argv[1])  

请参阅以下适用于Python 3的代码:

import sys
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFPage
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.layout import LAParams
import io

def pdfparser(data):

    fp = open(data, 'rb')
    rsrcmgr = PDFResourceManager()
    retstr = io.StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    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.get_pages(fp):
        interpreter.process_page(page)
        data =  retstr.getvalue()

    print(data)

if __name__ == '__main__':
    pdfparser(sys.argv[1])  

答案 3 :(得分:43)

Pdftotext一个开源程序(Xpdf的一部分),你可以从python调用它(不是你要求但可能有用)。我没有遇到任何问题。我认为谷歌在谷歌桌面上使用它。

答案 4 :(得分:42)

pyPDF工作正常(假设您正在使用格式正确的PDF)。如果你想要的只是文本(带空格),你可以这样做:

import pyPdf
pdf = pyPdf.PdfFileReader(open(filename, "rb"))
for page in pdf.pages:
    print page.extractText()

您还可以轻松访问元数据,图像数据等。

extractText代码注释中的注释:

  

找到所有文本绘图命令   他们提供的顺序   内容流,并提取文本。   这适用于某些PDF文件,   但对其他人来说很糟糕,取决于   使用的发电机。这将会   在未来精炼。不要依赖   文本的顺序来自于此   功能,如果这样会改变   功能变得更加复杂。

这是否是一个问题取决于你正在对文本做什么(例如,如果顺序无关紧要,没关系,或者生成器按照将要显示的顺序向文本添加文本,没关系)。我在日常使用中有pyPdf提取代码,没有任何问题。

答案 5 :(得分:21)

您也可以很容易地将pdfminer用作库。您可以访问pdf的内容模型,并可以创建自己的文本提取。我这样做是为了使用下面的代码将pdf内容转换为分号分隔文本。

该函数只是根据它们的y和x坐标对TextItem内容对象进行排序,并输出与一个文本行具有相同y坐标的项目,将同一行上的对象与“;”分开。字符。

使用这种方法,我能够从pdf中提取文本,其他工具无法提取适合进一步解析的内容。我尝试过的其他工具包括pdftotext,ps2ascii和在线工具pdftextonline.com。

pdfminer是pdf-scraping的宝贵工具。


def pdf_to_csv(filename):
    from pdflib.page import TextItem, TextConverter
    from pdflib.pdfparser import PDFDocument, PDFParser
    from pdflib.pdfinterp import PDFResourceManager, PDFPageInterpreter

    class CsvConverter(TextConverter):
        def __init__(self, *args, **kwargs):
            TextConverter.__init__(self, *args, **kwargs)

        def end_page(self, i):
            from collections import defaultdict
            lines = defaultdict(lambda : {})
            for child in self.cur_item.objs:
                if isinstance(child, TextItem):
                    (_,_,x,y) = child.bbox
                    line = lines[int(-y)]
                    line[x] = child.text

            for y in sorted(lines.keys()):
                line = lines[y]
                self.outfp.write(";".join(line[x] for x in sorted(line.keys())))
                self.outfp.write("\n")

    # ... the following part of the code is a remix of the 
    # convert() function in the pdfminer/tools/pdf2text module
    rsrc = PDFResourceManager()
    outfp = StringIO()
    device = CsvConverter(rsrc, outfp, "ascii")

    doc = PDFDocument()
    fp = open(filename, 'rb')
    parser = PDFParser(doc, fp)
    doc.initialize('')

    interpreter = PDFPageInterpreter(rsrc, device)

    for i, page in enumerate(doc.get_pages()):
        outfp.write("START PAGE %d\n" % i)
        interpreter.process_page(page)
        outfp.write("END PAGE %d\n" % i)

    device.close()
    fp.close()

    return outfp.getvalue()

<强>更新

上面的代码是针对旧版本的API编写的,请参阅下面的评论。

答案 6 :(得分:17)

slate是一个项目,它使得从库中使用PDFMiner变得非常简单:

>>> with open('example.pdf') as f:
...    doc = slate.PDF(f)
...
>>> doc
[..., ..., ...]
>>> doc[1]
'Text from page 2...'   

答案 7 :(得分:8)

我需要将特定的PDF转换为python模块中的纯文本。我使用了PDFMiner 20110515,在阅读了pdf2txt.py工具后,我编写了这个简单的代码段:

from cStringIO import StringIO
from pdfminer.pdfinterp import PDFResourceManager, process_pdf
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams

def to_txt(pdf_path):
    input_ = file(pdf_path, 'rb')
    output = StringIO()

    manager = PDFResourceManager()
    converter = TextConverter(manager, output, laparams=LAParams())
    process_pdf(manager, converter, input_)

    return output.getvalue() 

答案 8 :(得分:5)

重新利用pdfminer附带的pdf2txt.py代码;你可以创建一个函数来获取pdf的路径;可选地,outtype(txt | html | xml | tag)和opts类似于命令行pdf2txt {' - o':'/ path / to / outfile.txt'...}。默认情况下,您可以调用:

convert_pdf(path)

将创建一个文本文件,将文件系统中的兄弟文件创建为原始文件。

def convert_pdf(path, outtype='txt', opts={}):
    import sys
    from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, process_pdf
    from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter, TagExtractor
    from pdfminer.layout import LAParams
    from pdfminer.pdfparser import PDFDocument, PDFParser
    from pdfminer.pdfdevice import PDFDevice
    from pdfminer.cmapdb import CMapDB

    outfile = path[:-3] + outtype
    outdir = '/'.join(path.split('/')[:-1])

    debug = 0
    # input option
    password = ''
    pagenos = set()
    maxpages = 0
    # output option
    codec = 'utf-8'
    pageno = 1
    scale = 1
    showpageno = True
    laparams = LAParams()
    for (k, v) in opts:
        if k == '-d': debug += 1
        elif k == '-p': pagenos.update( int(x)-1 for x in v.split(',') )
        elif k == '-m': maxpages = int(v)
        elif k == '-P': password = v
        elif k == '-o': outfile = v
        elif k == '-n': laparams = None
        elif k == '-A': laparams.all_texts = True
        elif k == '-D': laparams.writing_mode = v
        elif k == '-M': laparams.char_margin = float(v)
        elif k == '-L': laparams.line_margin = float(v)
        elif k == '-W': laparams.word_margin = float(v)
        elif k == '-O': outdir = v
        elif k == '-t': outtype = v
        elif k == '-c': codec = v
        elif k == '-s': scale = float(v)
    #
    CMapDB.debug = debug
    PDFResourceManager.debug = debug
    PDFDocument.debug = debug
    PDFParser.debug = debug
    PDFPageInterpreter.debug = debug
    PDFDevice.debug = debug
    #
    rsrcmgr = PDFResourceManager()
    if not outtype:
        outtype = 'txt'
        if outfile:
            if outfile.endswith('.htm') or outfile.endswith('.html'):
                outtype = 'html'
            elif outfile.endswith('.xml'):
                outtype = 'xml'
            elif outfile.endswith('.tag'):
                outtype = 'tag'
    if outfile:
        outfp = file(outfile, 'w')
    else:
        outfp = sys.stdout
    if outtype == 'txt':
        device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams)
    elif outtype == 'xml':
        device = XMLConverter(rsrcmgr, outfp, codec=codec, laparams=laparams, outdir=outdir)
    elif outtype == 'html':
        device = HTMLConverter(rsrcmgr, outfp, codec=codec, scale=scale, laparams=laparams, outdir=outdir)
    elif outtype == 'tag':
        device = TagExtractor(rsrcmgr, outfp, codec=codec)
    else:
        return usage()

    fp = file(path, 'rb')
    process_pdf(rsrcmgr, device, fp, pagenos, maxpages=maxpages, password=password)
    fp.close()
    device.close()

    outfp.close()
    return

答案 9 :(得分:1)

PDFminer在我尝试过的pdf文件的每一页上都给了我一行[第1页,共7页...]。

到目前为止,我得到的最佳答案是pdftoipe,或者是基于Xpdf的c ++代码。

请参阅my question了解pdftoipe的输出结果。

答案 10 :(得分:1)

另外还有PDFTextStream这是一个商业Java库,也可以在Python中使用。

答案 11 :(得分:1)

我已将pdftohtml-xml参数一起使用,使用subprocess.Popen()读取结果,这将为您提供x coord,y coord,width,height和font < pdf中的文字的em>代码段。我认为这也是'evince'可能使用的,因为同样的错误信息会喷出来。

如果您需要处理柱状数据,那么由于您必须发明适合您的pdf文件的算法,因此会稍微复杂一些。问题是制作PDF文件的程序并不一定要以任何逻辑格式布局文本。您可以尝试简单的排序算法,它有时会起作用,但可能会有很少的“落后者”和“流浪者”,这些文本不会按照您认为的顺序排列。所以你必须要有创意。

我花了大约5个小时来找出我正在制作的pdf。但它现在效果很好。祝好运。

答案 12 :(得分:0)

今天找到解决方案。对我来说很棒。甚至将PDF页面渲染为PNG图像。 http://www.swftools.org/gfx_tutorial.html