自codeape发布以来，PDFMiner包已经更改。

编辑(再一次):

PDFMiner在20100213版本再次更新

您可以使用以下命令检查已安装的版本:

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

以下是更新后的版本(对我修改/添加的内容进行了评论):

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最新版本20100619p1的更新。简而言之，我用LTChar替换了LTTextItem，并将一个腹腔镜实例传递给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):

20110515版本更新(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()

你也可以很容易地使用pdfminer作为一个库。您可以访问pdf的内容模型，并可以创建自己的文本提取。我这样做是为了将pdf内容转换为分号分隔的文本，使用下面的代码。

该函数只是根据TextItem内容对象的y坐标和x坐标对其进行排序，并输出具有相同y坐标的项作为一个文本行，并用';'字符分隔同一行上的对象。

使用这种方法，我能够从pdf中提取文本，而其他任何工具都无法从中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是一个非常宝贵的pdf抓取工具。

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()

更新:

上面的代码是针对旧版本的API编写的，请参阅下面我的评论。

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文件的路径;可选的输出类型(txt|html|xml|标签)和命令行pdf2txt {'-o': '/path/to/outfile.txt'…}。默认情况下，你可以调用:

convert_pdf(path)

将创建一个文本文件，它是文件系统中原始pdf文件的兄弟文件。

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

由于这些解决方案都不支持最新版本的PDFMiner，我写了一个简单的解决方案，将返回使用PDFMiner的pdf文本。这将适用于那些在process_pdf中得到导入错误的人

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])  

请看下面适用于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])  

我需要在python模块中将特定的PDF转换为纯文本。我使用PDFMiner 20110515，在阅读了他们的pdf2txt.py工具后，我写了这个简单的片段:

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() 

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

带标记的PDF格式似乎是最干净的，去掉XML标记只留下纯文本。

Python 3版本如下:

https://github.com/pdfminer/pdfminer.six