有没有Python模块可以将PDF文件转换成文本?我尝试了在Activestate中找到的一段代码,它使用了pypdf,但生成的文本没有空格,也没有用处。
有没有Python模块可以将PDF文件转换成文本?我尝试了在Activestate中找到的一段代码,它使用了pypdf,但生成的文本没有空格,也没有用处。
尝试使用PDFMiner。它可以将PDF文件中的文本提取为HTML、SGML或“标记式PDF”格式。
标记式PDF格式似乎是最干净的格式,去除XML标签后只剩下纯文本。
Python 3版本可在以下链接中获取:
PDFMiner软件包自codeape发布以来已经发生了变化。
编辑(再次更新):
PDFMiner在20100213
版本中进行了更新。
您可以使用以下命令检查您所安装的版本:
>>> import pdfminer
>>> pdfminer.__version__
'20100213'
这是更新版本(附有我所更改/添加的注释):
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()
再次编辑:
这是最新版本(pypi中的20100619p1
)的更新。简而言之,我用LTChar
替换了LTTextItem
,并向CsvConverter构造函数传递了LAParams的实例。
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(再次更新):
针对版本20110515
进行了更新(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()
由于这些解决方案都不支持最新版本的PDFMiner,我编写了一个简单的解决方案,使用PDFMiner返回PDF文本。对于那些使用process_pdf
时遇到导入错误的人来说,这将起作用。
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])
请见下面适用于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])
print
命令后加上明显的括号外,还需将file
命令替换为open
命令,并从io
包中导入StringIO
。 - McLawrencePdftotext 是一款开源程序(Xpdf 的一部分),可以从 Python 中调用(这不是您要求的,但可能很有用)。我使用它没有遇到问题。我认为谷歌在 Google 桌面中也使用了它。
pdftotext
似乎工作得非常好,但如果希望在标准输出上看到结果,则需要第二个参数是连字符。 - Gordon Linofffind . -iname "*.pdf" -exec pdftotext -enc UTF-8 -eol unix -raw {} \;
默认情况下,生成的文件将采用原始名称,并带有.txt
扩展名。 - ccpizzapyPDF在使用格式正确的PDF文档时表现良好。如果你只要获取文本(包括空格),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。
在extractText代码的注释中:
定位所有文本绘制命令,并按照内容流中提供的顺序提取文本。这对于某些PDF文件效果很好,但对其他文件效果很差,具体取决于所使用的生成器。这将在未来得到改进。请不要依赖此函数输出的文本顺序,因为如果该函数变得更加复杂,其输出顺序也会发生变化。
这是否是一个问题,取决于您对文本的处理方式(例如,如果文本顺序无关紧要,则没有问题,或者如果生成器按照将要显示的顺序向流中添加文本,则没有问题)。我每天都在使用pyPdf提取代码,没有任何问题。
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:
以上代码是针对旧版本API编写的,请见下方我的评论。
slate
是一个项目,使得通过库很容易使用 PDFMiner:
>>> 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。我使用了PDFMiner 20110515版本,在阅读了他们的pdf2txt.py工具后,我编写了这个简单的代码片段:
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()
C:\Python27\Scripts\pdfminer\tools\pdf2txt.py
。 - Nate Anderson利用pdfminer自带的pdf2txt.py代码,您可以创建一个函数,该函数将接受pdf路径、可选的输出类型(txt|html|xml|tag)和选项,就像命令行pdf2txt一样{'-o': '/path/to/outfile.txt' ...}。默认情况下,您可以调用:
convert_pdf(path)
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
我使用了pdftohtml
命令并带有-xml
参数,通过subprocess.Popen()
读取结果,这将给出pdf中每个文本片段的x坐标、y坐标、宽度、高度和字体。我认为这也是'evince'可能使用的方法,因为相同的错误消息会输出。
如果您需要处理列数据,则情况会略微复杂,因为您必须发明适合pdf文件的算法。问题在于生成PDF文件的程序通常不以任何逻辑格式布置文本。您可以尝试简单的排序算法,并且有时可以奏效,但可能会有一些文本部分没有按照您想象的那样排序。因此,您需要变得更有创造力。
对于我正在处理的pdf,花费了我大约5个小时才找到一个适合的算法。但现在它运行得非常好。祝好运。