使用Python解析PDF为文本文件
一、解析PDF
使用pdfminer解析PDF文件，其中Layout类型包括LAParams, LTTextBox, LTTextLine, LTFigure, LTImage, LTChar。
示例一：解析LTTextBox
from pdfminer.layout import LTTextBoxHorizontal
from pdfminer.pdfpage import PDFTextExtractionNotAllowed
def parse(Path, Save_name):
parser = PDFParser(Path)
document = PDFDocument(parser)
if not document.is_extractable:
print 'error'
raise PDFTextExtractionNotAllowed
else:
rsrcmgr = PDFResourceManager()
laparams = LAParams()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.create_pages(document):
interpreter.process_page(page)
layout = device.get_result()
for x in layout:
if (isinstance(x, LTTextBoxHorizontal)):
with open('%s' % (Save_name), 'a') as f:
results = x.get_text().encode('utf-8')
print results
f.write(results + "\n")
if __name__ == '__main__':
Path = open('/local/mnt/workspace/PycharmProject/demo/src/tmp/2019.pdf', 'rb')
Parse(Path, '/local/mnt/workspace/PycharmProject/demo/src/tmp/1.txt')示例二：解析更多Layout类型
#!/usr/bin/python
import sys
import os
from binascii import b2a_hex
###
### pdf-miner requirements
###
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument, PDFNoOutlines
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LAParams, LTTextBox, LTTextLine, LTFigure, LTImage, LTChar
def with_pdf (pdf_doc, fn, pdf_pwd, *args):
"""Open the pdf document, and apply the function, returning the results"""
result = None
try:
# open the pdf file
fp = open(pdf_doc, 'rb')
# create a parser object associated with the file object
parser = PDFParser(fp)
# create a PDFDocument object that stores the document structure
doc = PDFDocument(parser, pdf_pwd)
# connect the parser and document objects
parser.set_document(doc)
# supply the password for initialization
if doc.is_extractable:
# apply the function and return the result
result = fn(doc, *args)
# close the pdf file
fp.close()
except IOError:
# the file doesn't exist or similar problem
pass
return result
###
### Table of Contents
###
def _parse_toc (doc):
"""With an open PDFDocument object, get the table of contents (toc) data
[this is a higher-order function to be passed to with_pdf()]"""
toc = []
try:
outlines = doc.get_outlines()
for (level,title,dest,a,se) in outlines:
toc.append( (level, title) )
except PDFNoOutlines:
pass
return toc
def get_toc (pdf_doc, pdf_pwd=''):
"""Return the table of contents (toc), if any, for this pdf file"""
return with_pdf(pdf_doc, _parse_toc, pdf_pwd)
###
### Extracting Images
###
def write_file (folder, filename, filedata, flags='w'):
"""Write the file data to the folder and filename combination
(flags: 'w' for write text, 'wb' for write binary, use 'a' instead of 'w' for append)"""
result = False
if os.path.isdir(folder):
try:
file_obj = open(os.path.join(folder, filename), flags)
file_obj.write(filedata)
file_obj.close()
result = True
except IOError:
pass
return result
def determine_image_type (stream_first_4_bytes):
"""Find out the image file type based on the magic number comparison of the first 4 (or 2) bytes"""
file_type = None
bytes_as_hex = b2a_hex(stream_first_4_bytes)
if bytes_as_hex.startswith('ffd8'):
file_type = '.jpeg'
elif bytes_as_hex == '89504e47':
file_type = '.png'
elif bytes_as_hex == '47494638':
file_type = '.gif'
elif bytes_as_hex.startswith('424d'):
file_type = '.bmp'
return file_type
def save_image (lt_image, page_number, images_folder):
"""Try to save the image data from this LTImage object, and return the file name, if successful"""
result = None
if lt_image.stream:
file_stream = lt_image.stream.get_rawdata()
if file_stream:
file_ext = determine_image_type(file_stream[0:4])
if file_ext:
file_name = ''.join([str(page_number), '_', lt_image.name, file_ext])
if write_file(images_folder, file_name, file_stream, flags='wb'):
result = file_name
return result
###
### Extracting Text
###
def to_bytestring (s, enc='utf-8'):
"""Convert the given unicode string to a bytestring, using the standard encoding,
unless it's already a bytestring"""
if s:
if isinstance(s, str):
return s
else:
return s.encode(enc)
def update_page_text_hash (h, lt_obj, pct=0.2):
"""Use the bbox x0,x1 values within pct% to produce lists of associated text within the hash"""
x0 = lt_obj.bbox[0]
x1 = lt_obj.bbox[2]
key_found = False
for k, v in h.items():
hash_x0 = k[0]
if x0 >= (hash_x0 * (1.0-pct)) and (hash_x0 * (1.0+pct)) >= x0:
hash_x1 = k[1]
if x1 >= (hash_x1 * (1.0-pct)) and (hash_x1 * (1.0+pct)) >= x1:
# the text inside this LT* object was positioned at the same
# width as a prior series of text, so it belongs together
key_found = True
v.append(to_bytestring(lt_obj.get_text()))
h[k] = v
if not key_found:
# the text, based on width, is a new series,
# so it gets its own series (entry in the hash)
h[(x0,x1)] = [to_bytestring(lt_obj.get_text())]
return h
def parse_lt_objs (lt_objs, page_number, images_folder, text=[]):
"""Iterate through the list of LT* objects and capture the text or image data contained in each"""
text_content = []
page_text = {} # k=(x0, x1) of the bbox, v=list of text strings within that bbox width (physical column)
for lt_obj in lt_objs:
if isinstance(lt_obj, LTTextBox) or isinstance(lt_obj, LTTextLine):
# text, so arrange is logically based on its column width
page_text = update_page_text_hash(page_text, lt_obj)
elif isinstance(lt_obj, LTImage):
# an image, so save it to the designated folder, and note its place in the text
saved_file = save_image(lt_obj, page_number, images_folder)
if saved_file:
# use html style ![]()
tag to mark the position of the image within the text
text_content.append('+')
')
else:
print >> sys.stderr, "error saving image on page", page_number, lt_obj.__repr__
elif isinstance(lt_obj, LTFigure):
# LTFigure objects are containers for other LT* objects, so recurse through the children
text_content.append(parse_lt_objs(lt_obj, page_number, images_folder, text_content))
for k, v in sorted([(key,value) for (key,value) in page_text.items()]):
# sort the page_text hash by the keys (x0,x1 values of the bbox),
# which produces a top-down, left-to-right sequence of related columns
text_content.append(''.join(v))
return '\n'.join(text_content)
###
### Processing Pages
###
def _parse_pages (doc, images_folder):
"""With an open PDFDocument object, get the pages and parse each one
[this is a higher-order function to be passed to with_pdf()]"""
rsrcmgr = PDFResourceManager()
laparams = LAParams()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
text_content = []
for i, page in enumerate(PDFPage.create_pages(doc)):
interpreter.process_page(page)
# receive the LTPage object for this page
layout = device.get_result()
# layout is an LTPage object which may contain child objects like LTTextBox, LTFigure, LTImage, etc.
text_content.append(parse_lt_objs(layout, (i+1), images_folder))
return text_content
def get_pages (pdf_doc, pdf_pwd='', images_folder='/tmp'):
"""Process each of the pages in this pdf file and return a list of strings representing the text found in each page"""
return with_pdf(pdf_doc, _parse_pages, pdf_pwd, *tuple([images_folder]))
a = open('/local/mnt/workspace/PycharmProject/demo/src/tmp/3.txt','a')
for i in get_pages('/local/mnt/workspace/PycharmProject/demo/src/tmp/total.pdf'):
a.write(i)
a.close()
因为pdfminer对PDF中图片解析能力不足，如果Layout类型为LTFigure， 则解析结果为图片。那么，如果想得到文本文件，还需要进一步对图片进行解析。这里，用到tesseract。
二、tesseract的使用
操作系统为CentOS 7。
1. 安装
# sudo yum install tesseract2. 添加语言包
安装完成默认带英文语言包，如果需要中文语言包，可下载https://github.com/daheicode/chi_sim。下载得到的语言包放在tesseract目录下 /usr/share/tesseact/tessdata/
# whereis tesseract
# cd /usr/share/tesseract/tessdata/
# cp ~/chi_sim.traineddata .3. 使用
选项 -l 指定解析中文。更多操作可以查看 tesseract --help
# tesseract -v
# tesseract /tmp/imgs/1_Image1.jpeg -l chi_sim test.txt