pip install pdfminer

# coding=utf-8
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import time
time1=time.time()
import os.path
from pdfminer.pdfparser import PDFParser,PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LTTextBoxHorizontal,LAParams
from pdfminer.pdfinterp import PDFTextExtractionNotAllowed
result=[]
class CPdf2TxtManager():
  def __init__(self):
    '''''
    Constructor
    '''
  def changePdfToText(self, filePath):
    file = open(path, 'rb') # 以二進制讀模式打開
    #用文件對象來創(chuàng)建一個pdf文檔分析器
    praser = PDFParser(file)
    # 創(chuàng)建一個PDF文檔
    doc = PDFDocument()
    # 連接分析器 與文檔對象
    praser.set_document(doc)
    doc.set_parser(praser)
    # 提供初始化密碼
    # 如果沒有密碼 就創(chuàng)建一個空的字符串
    doc.initialize()
    # 檢測文檔是否提供txt轉(zhuǎn)換，不提供就忽略
    if not doc.is_extractable:
      raise PDFTextExtractionNotAllowed
    # 創(chuàng)建PDf 資源管理器 來管理共享資源
    rsrcmgr = PDFResourceManager()
    # 創(chuàng)建一個PDF設(shè)備對象
    laparams = LAParams()
    device = PDFPageAggregator(rsrcmgr, laparams=laparams)
    # 創(chuàng)建一個PDF解釋器對象
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    pdfStr = ''
    # 循環(huán)遍歷列表，每次處理一個page的內(nèi)容
    for page in doc.get_pages(): # doc.get_pages() 獲取page列表
      interpreter.process_page(page)
      # 接受該頁面的LTPage對象
      layout = device.get_result()
      for x in layout:
        if hasattr(x, "get_text"):
          # print x.get_text()
          result.append(x.get_text())
          fileNames = os.path.splitext(filePath)
          with open(fileNames[0] + '.txt','wb') as f:
            results = x.get_text()
            print(results)
            f.write(results + '\n')
if __name__ == '__main__':
  '''''
   解析pdf 文本，保存到txt文件中
  '''
  path = u'C:/data3.pdf'
  pdf2TxtManager = CPdf2TxtManager()
  pdf2TxtManager.changePdfToText(path)
  # print result[0]
  time2 = time.time()
  print u'ok,解析pdf結(jié)束!'
  print u'總共耗時：' + str(time2 - time1) + 's'

# coding=utf-8
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import time
time1=time.time()
import os.path
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFTextExtractionNotAllowed
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
result=[]
class CPdf2TxtManager():
  def __init__(self):
    '''''
    Constructor
    '''
  def changePdfToText(self, filePath):
    file = open(path, 'rb') # 以二進制讀模式打開
    #用文件對象來創(chuàng)建一個pdf文檔分析器
    praser = PDFParser(file)
    # 創(chuàng)建一個PDF文檔
    doc = PDFDocument(praser)
    # 檢測文檔是否提供txt轉(zhuǎn)換，不提供就忽略
    if not doc.is_extractable:
      raise PDFTextExtractionNotAllowed
    # 創(chuàng)建PDf 資源管理器 來管理共享資源
    rsrcmgr = PDFResourceManager()
    # 創(chuàng)建一個PDF設(shè)備對象
    laparams = LAParams()
    device = PDFPageAggregator(rsrcmgr, laparams=laparams)
    # 創(chuàng)建一個PDF解釋器對象
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    pdfStr = ''
    # 循環(huán)遍歷列表，每次處理一個page的內(nèi)容
    for page in PDFPage.create_pages(doc): # doc.get_pages() 獲取page列表
      interpreter.process_page(page)
      # 接受該頁面的LTPage對象
      layout = device.get_result()
      for x in layout:
        if hasattr(x, "get_text"):
          # print x.get_text()
          result.append(x.get_text())
          fileNames = os.path.splitext(filePath)
          with open(fileNames[0] + '.txt','wb') as f:
            results = x.get_text()
            print(results)
            f.write(results + '\n')
if __name__ == '__main__':
  '''''
   解析pdf 文本，保存到txt文件中
  '''
  path = u'C:/36.pdf'
  pdf2TxtManager = CPdf2TxtManager()
  pdf2TxtManager.changePdfToText(path)
  # print result[0]
  time2 = time.time()
  print u'ok,解析pdf結(jié)束!'
  print u'總共耗時：' + str(time2 - time1) + 's'