哪些是将PDF文件转换为文本的最佳Python模块？
试试PDFMiner.它可以从PDF文件中提取HTML,SGML或"Tagged PDF"格式的文本.
http://www.unixuser.org/~euske/python/pdfminer/index.html
Tagged PDF格式似乎是最干净的,剥离XML标签只留下裸文本.
Python 3版本可在以下位置获得:
https://github.com/pdfminer/pdfminer.six
该PDFMiner包已经改变,因为codeape公布.
编辑(再次):
PDFMiner已在版本中再次更新 20100213
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):
下面是最新版本的更新的PyPI,20100619p1.总之我换成LTTextItem用LTChar,并通过LAParams的实例向CsvConverter构造.
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()
由于这些解决方案都没有支持最新版本的PDFMiner,因此我编写了一个简单的解决方案,它将使用PDFMiner返回pdf文本.这适用于那些导致导入错误的人process_pdf
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])
Pdftotext一个开源程序(Xpdf的一部分),你可以从python中调用它(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使用它.
pyPDF工作正常(假设您正在使用格式良好的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()
您还可以轻松访问元数据,图像数据等.
extractText代码注释中的注释:
按照内容流中提供的顺序查找所有文本绘制命令,然后提取文本.这适用于某些PDF文件,但对其他PDF文件效果不佳,具体取决于所使用的生成器.这将在未来得到完善.不要依赖于此函数的文本顺序,因为如果此功能变得更复杂,它将会改变.
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,或者如果生成器按照它将显示的顺序将文本添加到流中,那很好) .我在日常使用中有pyPdf提取代码,没有任何问题.
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.
该函数根据y和x坐标简单地对TextItem内容对象进行排序,并输出具有相同y坐标的项作为一个文本行,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()
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.
slate 是一个项目,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...'
我需要将特定的PDF转换为python模块中的纯文本.我使用PDFMiner 20110515,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()
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pdf.
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
京公网安备 11010802040832号 | 京ICP备19059560号-6 