如何将pdfminer用作库

Question

我正在尝试使用pdfminer从pdf获取文本数据。我能够用pdfminer命令行工具pdf2txt.py成功地将这些数据提取到一个.txt文件中。我现在这样做，然后使用python脚本清理.txt文件。我希望将pdf提取过程合并到脚本中，并为自己节省一个步骤。

I thought I was on to something when I found this link，但是我没有成功地解决任何问题。可能这里列出的函数需要再次更新，因为我使用的是更新版本的pdfminer。

I also tried the function shown here, but it also did not work.

我尝试的另一种方法是使用os.system在脚本中调用脚本。这也不成功。

我使用的是Python版本2.7.1和pdfminer版本20110227。

Answer 1

这是一个清理版本，我终于产生了为我工作。下面只返回PDF格式的字符串，给出它的文件名。我希望这能节省一些时间。

from pdfminer.pdfinterp import PDFResourceManager, process_pdf
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from cStringIO import StringIO

def convert_pdf(path):

    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)

    fp = file(path, 'rb')
    process_pdf(rsrcmgr, device, fp)
    fp.close()
    device.close()

    str = retstr.getvalue()
    retstr.close()
    return str

此解决方案在API changes in November 2013之前有效。

Answer 2

我知道回答你自己的问题是低级趣味的，但我想我可能已经解决了这个问题，我不希望其他人浪费时间来寻找解决我问题的方法。

我在问题中发布的一个链接中遵循了建议，并重新设计了pdfminer中包含的当前pdf2txt.py脚本。这是函数，以防对其他人有用。感谢用户skyl发布了这个答案，我所需要做的就是做一些修改，使其能够与pdfminer的当前版本一起工作。

此函数接受pdf并在同一目录中创建同名的.txt文件。

def convert_pdf(path, outtype='txt', opts={}):
import sys
from pdfminer.pdfparser import PDFDocument, PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, process_pdf
from pdfminer.pdfdevice import PDFDevice, TagExtractor
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.cmapdb import CMapDB
from pdfminer.layout import LAParams
import getopt

outfile = path[:-3] + outtype
outdir = '/'.join(path.split('/')[:-1])

# debug option
debug = 0
# input option
password = ''
pagenos = set()
maxpages = 0
# output option
# ?outfile = None
# ?outtype = None
outdir = None
#layoutmode = 'normal'
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 == '-V': laparams.detect_vertical = True
    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 == '-F': laparams.boxes_flow = float(v)
    elif k == '-Y': layoutmode = v
    elif k == '-O': outdir = v
    elif k == '-t': outtype = v
    elif k == '-c': codec = v
    elif k == '-s': scale = float(v)
#
#PDFDocument.debug = debug
#PDFParser.debug = debug
CMapDB.debug = debug
PDFResourceManager.debug = debug
PDFPageInterpreter.debug = debug
PDFDevice.debug = debug
#
rsrcmgr = PDFResourceManager()

outtype = 'text'

if outfile:
    outfp = file(outfile, 'w')
else:
    outfp = sys.stdout
device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams)


fp = file(path, 'rb')
process_pdf(rsrcmgr, device, fp, pagenos, maxpages=maxpages, password=password,
                check_extractable=True)
fp.close()
device.close()
outfp.close()
return

Answer 3

下面是一个适用于最新版本的新解决方案：

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from cStringIO import StringIO

def convert_pdf_to_txt(path):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    fp = file(path, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ""
    maxpages = 0
    caching = True
    pagenos=set()
    for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,caching=caching, check_extractable=True):
        interpreter.process_page(page)
    fp.close()
    device.close()
    str = retstr.getvalue()
    retstr.close()
    return str