# Python 2.7.6
# PdfAdapter.py
""" Reusable library to extract text from pdf file
Uses pdfminer library; For Python 3.x use pdfminer3k module
Below links have useful information on components of the program
https://euske.github.io/pdfminer/programming.html
http://denis.papathanasiou.org/posts/2010.08.04.post.html
"""
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
# From PDFInterpreter import both PDFResourceManager and PDFPageInterpreter
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
# from pdfminer.pdfdevice import PDFDevice
# To raise exception whenever text extraction from PDF is not allowed
from pdfminer.pdfpage import PDFTextExtractionNotAllowed
from pdfminer.layout import LAParams, LTTextBox, LTTextLine
from pdfminer.converter import PDFPageAggregator
import logging
__doc__ = "eusable library to extract text from pdf file"
__name__ = "pdfAdapter"
""" Basic logging config
"""
log = logging.getLogger(__name__)
log.addHandler(logging.NullHandler())
class pdf_text_extractor:
""" Modules overview:
- PDFParser: fetches data from pdf file
- PDFDocument: stores data parsed by PDFParser
- PDFPageInterpreter: processes page contents from PDFDocument
- PDFDevice: translates processed information from PDFPageInterpreter
to whatever you need
- PDFResourceManager: Stores shared resources such as fonts or images
used by both PDFPageInterpreter and PDFDevice
- LAParams: A layout analyzer returns a LTPage object for each page in
the PDF document
- PDFPageAggregator: Extract the decive to page aggregator to get LT
object elements
"""
def __init__(self, pdf_file_path, password=""):
""" Class initialization block.
Pdf_file_path - Full path of pdf including name
password = If not passed, assumed as none
"""
self.pdf_file_path = pdf_file_path
self.password = password
def getText(self):
""" Algorithm:
1) Txr information from PDF file to PDF document object using parser
2) Open the PDF file
3) Parse the file using PDFParser object
4) Assign the parsed content to PDFDocument object
5) Now the information in this PDFDocumet object has to be processed.
For this we need PDFPageInterpreter, PDFDevice and PDFResourceManager
6) Finally process the file page by page
"""
# Open and read the pdf file in binary mode
with open(self.pdf_file_path, "rb") as fp:
# Create parser object to parse the pdf content
parser = PDFParser(fp)
# Store the parsed content in PDFDocument object
document = PDFDocument(parser, self.password)
# Check if document is extractable, if not abort
if not document.is_extractable:
raise PDFTextExtractionNotAllowed
# Create PDFResourceManager object that stores shared resources
# such as fonts or images
rsrcmgr = PDFResourceManager()
# set parameters for analysis
laparams = LAParams()
# Create a PDFDevice object which translates interpreted
# information into desired format
# Device to connect to resource manager to store shared resources
# device = PDFDevice(rsrcmgr)
# Extract the decive to page aggregator to get LT object elements
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
# Create interpreter object to process content from PDFDocument
# Interpreter needs to be connected to resource manager for shared
# resources and device
interpreter = PDFPageInterpreter(rsrcmgr, device)
# Initialize the text
extracted_text = ""
# Ok now that we have everything to process a pdf document,
# lets process it page by page
for page in PDFPage.create_pages(document):
# As the interpreter processes the page stored in PDFDocument
# object
interpreter.process_page(page)
# The device renders the layout from interpreter
layout = device.get_result()
# Out of the many LT objects within layout, we are interested
# in LTTextBox and LTTextLine
for lt_obj in layout:
if (isinstance(lt_obj, LTTextBox) or
isinstance(lt_obj, LTTextLine)):
extracted_text += lt_obj.get_text()
return extracted_text.encode("utf-8")
4 回答
PDF不包含表格数据，除非它包含结构化内容 . 一些工具包括试探法来尝试猜测数据结构并将其反馈 . 我在http://www.jpedal.org/PDFblog/2009/04/pdf-text/撰写了一篇博客文章，解释了PDF文本提取的问题 .
我遇到了类似的问题，并最终使用了_1408719中的XPDF . 其中一个工具是PDFtoText，但我想这一切都可以实现，PDF是如何产生的 .
将生成一个文本文件thingwithtablesinit.txt与右表 .
如其他答案中所述，从PDF中提取文本不是一项简单的任务 . 但是，有一些Python库，如 pdfminer （Python 3的 pdfminer3k ），效率相当高 .
下面的代码片段显示了一个Python类，可以将其实例化以从PDF中提取文本 . 这在大多数情况下都有效 .
（来源 - https://gist.github.com/vinovator/a46341c77273760aa2bb）
注 - 还有其他库，例如 PyPDF2 ，它们擅长转换PDF，例如合并PDF页面，拆分或裁剪特定页面等 .