pdf 提取文字

import os
import pandas as pd
import sys
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice, TagExtractor
from pdfminer.pdfpage import PDFPage
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.cmapdb import CMapDB
from pdfminer.layout import LAParams
from pdfminer.image import ImageWriter
# debug option
debug = 1
# input option
password = b''
pagenos = set()
maxpages = 0
# output option
outtype = 'text'
imagewriter = None
rotation = 0
stripcontrol = False
layoutmode = 'normal'
encoding = 'utf-8'
pageno = 1
scale = 1
caching = True
showpageno = True
laparams = LAParams()
PDFDocument.debug = debug
PDFParser.debug = debug
CMapDB.debug = debug
PDFPageInterpreter.debug = debug
#遍历目录下的所有text文件
import time
txt_list = []
for root, dirs, files in os.walk("pdf_sentence/", topdown=False):
    for i,name in enumerate(files):
        rsrcmgr = PDFResourceManager(caching=caching)
        #获取文件绝对地址
        end = name.split('.')[1]
        if 'pdf'in end:
            print(i,name)
            fname = name
            outfile = name.split('.')[0] + '.txt'
            outfp = open("pdf_txt/"+outfile, 'a+', encoding=encoding)
            device = TextConverter(rsrcmgr, outfp, laparams=laparams,
                               imagewriter=imagewriter)
            with open("pdf_sentence/"+fname, 'rb') as fp:
                interpreter = PDFPageInterpreter(rsrcmgr, device)
                for page in PDFPage.get_pages(fp, pagenos,
                                          maxpages=maxpages, password=password,
                                          caching=caching, check_extractable=True):
                    page.rotate = (page.rotate+rotation) % 360
                    time.sleep(1)
                    interpreter.process_page(page)
                    txt_list.append(outfile)
                print(fname + " done !")
            device.close()
            outfp.close()
            print(" device release")

还有一种简单的：

#遍历目录下的所有text文件
import time
import os
txt_list = []
for root, dirs, files in os.walk("pdf_sentence/", topdown=False):
    for i,name in enumerate(files):
        end = name.split('.')[1]
        if 'pdf'in end:
            fname = name
            outfile = name.split('.')[0] 
            re = os.system("python pdf2txt_self.py -o pdf_txt/%s.txt -d pdf_sentence/%s"%(outfile,name))
            print("extract "+name+ " done!")

这里调用了pdf2txt.py

来看一下他的代码：

#!/usr/bin/env python
import sys
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice, TagExtractor
from pdfminer.pdfpage import PDFPage
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.cmapdb import CMapDB
from pdfminer.layout import LAParams
from pdfminer.image import ImageWriter

# main
def main(argv):
    import getopt
    def usage():
        print(f'usage: {argv[0]} [-P password] [-o output] [-t text|html|xml|tag]'
               ' [-O output_dir] [-c encoding] [-s scale] [-R rotation]'
               ' [-Y normal|loose|exact] [-p pagenos] [-m maxpages]'
               ' [-S] [-C] [-n] [-A] [-V] [-M char_margin] [-L line_margin]'
               ' [-W word_margin] [-F boxes_flow] [-d] input.pdf ...')
        return 100
    try:
        (opts, args) = getopt.getopt(argv[1:], 'dP:o:t:O:c:s:R:Y:p:m:SCnAVM:W:L:F:')
    except getopt.GetoptError:
        return usage()
    if not args: return usage()
    # debug option
    debug = 0
    # input option
    password = b''
    pagenos = set()
    maxpages = 0
    # output option
    outfile = None
    outtype = None
    imagewriter = None
    rotation = 0
    stripcontrol = False
    layoutmode = 'normal'
    encoding = 'utf-8'
    pageno = 1
    scale = 1
    caching = True
    showpageno = True
    laparams = LAParams()
    for (k, v) in opts:
        if k == '-d': debug += 1
        elif k == '-P': password = v.encode('ascii')
        elif k == '-o': outfile = v
        elif k == '-t': outtype = v
        elif k == '-O': imagewriter = ImageWriter(v)
        elif k == '-c': encoding = v
        elif k == '-s': scale = float(v)
        elif k == '-R': rotation = int(v)
        elif k == '-Y': layoutmode = v
        elif k == '-p': pagenos.update( int(x)-1 for x in v.split(',') )
        elif k == '-m': maxpages = int(v)
        elif k == '-S': stripcontrol = True
        elif k == '-C': caching = False
        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 == '-W': laparams.word_margin = float(v)
        elif k == '-L': laparams.line_margin = float(v)
        elif k == '-F': laparams.boxes_flow = float(v)
    #
    PDFDocument.debug = debug
    PDFParser.debug = debug
    CMapDB.debug = debug
    PDFPageInterpreter.debug = debug
    #
    rsrcmgr = PDFResourceManager(caching=caching)
    if not outtype:
        outtype = 'text'
        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 = open(outfile, 'w', encoding=encoding)
    else:
        outfp = sys.stdout
    if outtype == 'text':
        device = TextConverter(rsrcmgr, outfp, laparams=laparams,
                               imagewriter=imagewriter)
    elif outtype == 'xml':
        device = XMLConverter(rsrcmgr, outfp, laparams=laparams,
                              imagewriter=imagewriter,
                              stripcontrol=stripcontrol)
    elif outtype == 'html':
        device = HTMLConverter(rsrcmgr, outfp, scale=scale,
                               layoutmode=layoutmode, laparams=laparams,
                               imagewriter=imagewriter, debug=debug)
    elif outtype == 'tag':
        device = TagExtractor(rsrcmgr, outfp)
    else:
        return usage()
    for fname in args:
        with open(fname, 'rb') as fp:
            interpreter = PDFPageInterpreter(rsrcmgr, device)
            for page in PDFPage.get_pages(fp, pagenos,
                                          maxpages=maxpages, password=password,
                                          caching=caching, check_extractable=True):
                page.rotate = (page.rotate+rotation) % 360
                interpreter.process_page(page)
    device.close()
    outfp.close()
    return

if __name__ == '__main__': sys.exit(main(sys.argv))

代码写的很清楚，稍微改了一丢丢（基本没改哈哈哈）就能用的

#!/usr/bin/env python
import sys
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice, TagExtractor
from pdfminer.pdfpage import PDFPage
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.cmapdb import CMapDB
from pdfminer.layout import LAParams
from pdfminer.image import ImageWriter

# main
def main(argv):
    import getopt
    def usage():
        print(f'usage: {argv[0]} [-P password] [-o output] [-t text|html|xml|tag]'
               ' [-O output_dir] [-c encoding] [-s scale] [-R rotation]'
               ' [-Y normal|loose|exact] [-p pagenos] [-m maxpages]'
               ' [-S] [-C] [-n] [-A] [-V] [-M char_margin] [-L line_margin]'
               ' [-W word_margin] [-F boxes_flow] [-d] input.pdf ...')
        return 100
    try:
        (opts, args) = getopt.getopt(argv[1:], 'dP:o:t:O:c:s:R:Y:p:m:SCnAVM:W:L:F:')
    except getopt.GetoptError:
        return usage()
    if not args: return usage()
    # debug option
    debug = 0
    # input option
    password = b''
    pagenos = set()
    maxpages = 0
    # output option
    outfile = None
    outtype = 'text'
    imagewriter = None
    rotation = 0
    stripcontrol = False
    layoutmode = 'normal'
    encoding = 'utf-8'
    pageno = 1
    scale = 1
    caching = True
    showpageno = True
    laparams = LAParams()
    for (k, v) in opts:
        if k == '-d': debug += 1
        elif k == '-P': password = v.encode('ascii')
        elif k == '-o': outfile = v
        elif k == '-t': outtype = v
        elif k == '-O': imagewriter = ImageWriter(v)
        elif k == '-c': encoding = v
        elif k == '-s': scale = float(v)
        elif k == '-R': rotation = int(v)
        elif k == '-Y': layoutmode = v
        elif k == '-p': pagenos.update( int(x)-1 for x in v.split(',') )
        elif k == '-m': maxpages = int(v)
        elif k == '-S': stripcontrol = True
        elif k == '-C': caching = False
        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 == '-W': laparams.word_margin = float(v)
        elif k == '-L': laparams.line_margin = float(v)
        elif k == '-F': laparams.boxes_flow = float(v)
    #
    PDFDocument.debug = debug
    PDFParser.debug = debug
    CMapDB.debug = debug
    PDFPageInterpreter.debug = debug
    #
    rsrcmgr = PDFResourceManager(caching=caching)
    if outfile:
        outfp = open(outfile, 'a+', encoding=encoding)
    else:
        outfp = sys.stdout
    if outtype == 'text':
        device = TextConverter(rsrcmgr, outfp, laparams=laparams,
                               imagewriter=imagewriter)
  
    for fname in args:
        with open(fname, 'rb') as fp:
            interpreter = PDFPageInterpreter(rsrcmgr, device)
            for page in PDFPage.get_pages(fp, pagenos,
                                          maxpages=maxpages, password=password,
                                          caching=caching, check_extractable=True):
                page.rotate = (page.rotate+rotation) % 360
                interpreter.process_page(page)
    device.close()
    outfp.close()
    return

if __name__ == '__main__': sys.exit(main(sys.argv))