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，没有任何用处。
当前回答
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
其他回答
pyPDF工作正常(假设您使用的是格式良好的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 功能变得更加复杂。
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。
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()
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...'
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
今天找到了解决方案。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
