将PDF转换为文本的Python模块

是否有任何python模块转换PDF文件为文本?我尝试了在Activestate中发现的一段代码,它使用pypdf,但生成的文本之间没有空格,没有用处。

433291 次浏览

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:

PDFminer给了我也许一行[第1页7…在我尝试使用它的pdf文件的每一页上。

到目前为止,我有最好的答案是pdftopipe,或者是基于Xpdf的c++代码。

pdftopipe的输出是什么样的,请参阅我的问题

Pdftotext一个开源程序(Xpdf的一部分),你可以从python调用它(不是你要的,但可能有用)。我用过没有问题。我认为谷歌在谷歌桌面使用它。

pyPDF工作正常(假设你使用格式良好的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()

您还可以轻松地访问元数据、图像数据等。

extractText代码中的注释指出:

定位所有文本绘图命令,在 方法中提供的顺序 内容流,并提取文本。 这适用于一些PDF文件, 但对其他人来说很糟糕,这取决于 发电机使用。这将是 未来精致。不要依赖 文字的顺序 函数,因为它会改变如果这个 函数变得更加复杂。

这是否是一个问题取决于你对文本所做的事情(例如,如果顺序不重要,这很好,或者如果生成器按照它将显示的顺序将文本添加到流中,这很好)。我有pyPdf提取代码在日常使用中,没有任何问题。

此外,还有PDFTextStream,这是一个商业Java库,也可以从Python中使用。

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。

PDFMiner包在codeape发布后发生了变化。

编辑(再一次):

PDFMiner在20100213版本中再次更新

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):

这里是pypi20100619p1的最新版本的更新。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()

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

我已经使用pdftohtml-xml参数,用subprocess.Popen()读取结果,这将为您提供pdf中每个片段文本的x坐标,y坐标,宽度,高度和字体。我认为这是'evince'可能也使用的,因为同样的错误消息喷吐出来。

如果您需要处理柱状数据,它会变得稍微复杂一些,因为您必须发明一种适合您的pdf文件的算法。问题在于,生成PDF文件的程序并不一定会以任何逻辑格式布局文本。你可以尝试简单的排序算法,它有时是有效的,但可能会有一些小的“散乱者”和“散乱者”,文本片段没有按照你认为的顺序排列。所以你必须要有创造力。

我花了大约5个小时才为我正在做的pdf文件找到一个。但它现在运行得很好。祝你好运。

今天找到解决方案。对我来说很好。甚至将PDF页面转换为PNG图像。 http://www.swftools.org/gfx_tutorial.html < / p >

slate是一个项目,使它非常简单地使用PDFMiner从一个库:

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

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()

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。这将适用于那些使用process_pdf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])