我试图使用Python提取包含在这个PDF文件中的文本。
我正在使用PyPDF2包(版本1.27.2)，并有以下脚本:
import PyPDF2
with open("sample.pdf", "rb") as pdf_file:
read_pdf = PyPDF2.PdfFileReader(pdf_file)
number_of_pages = read_pdf.getNumPages()
page = read_pdf.pages[0]
page_content = page.extractText()
print(page_content)
当我运行代码时，我得到以下输出，这与PDF文档中包含的输出不同:
! " # $ % # $ % &% $ &' ( ) * % + , - % . / 0 1 ' * 2 3% 4
5
' % 1 $ # 2 6 % 3/ % 7 / ) ) / 8 % &) / 2 6 % 8 # 3" % 3" * % 31 3/ 9 # &)
%
如何提取PDF文档中的文本?
当前回答
如何从PDF文件中提取文本?
首先要了解的是PDF格式。它有一个用英文编写的公共规范，请参阅ISO 32000-2:2017，并阅读超过700页的PDF 1.7规范。当然，你至少需要阅读维基百科关于PDF的页面
一旦你理解了PDF格式的细节，提取文本或多或少是容易的(但是出现在图形或图像中的文本呢?它的数字1)?不要指望在几周内单独编写一个完美的软件文本提取器....
在Linux上，你也可以使用pdf2text，你可以从你的Python代码中弹出。
一般来说，从PDF文件中提取文本是一个定义不清的问题。对于人类读者来说，一些文本可以由不同的点制成(图形)，或者一张照片等等。
谷歌搜索引擎能够从PDF中提取文本，但据传需要超过5亿行的源代码。你有必要的资源(人力和预算)来发展一个竞争对手吗?
一种可能是将PDF打印到一些虚拟打印机(例如使用GhostScript或Firefox)，然后使用OCR技术提取文本。
相反，我建议处理生成PDF文件的数据表示，例如原始的LaTeX代码(或Lout代码)或OOXML代码。
在所有情况下，您都需要为至少几个人年的软件开发预算。
其他回答
在某些情况下，PyPDF2忽略空白，使结果文本混乱，但我使用PyMuPDF，我真的很满意 你可以使用这个链接获取更多信息
在尝试textract(似乎有太多依赖项)和pypdf2(无法从我测试的pdf中提取文本)和tika(太慢)后，我最终使用xpdf中的pdftotext(正如已经在另一个答案中建议的那样)，并直接从python中调用二进制(您可能需要调整路径到pdftotext):
import os, subprocess
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
args = ["/usr/local/bin/pdftotext",
'-enc',
'UTF-8',
"{}/my-pdf.pdf".format(SCRIPT_DIR),
'-']
res = subprocess.run(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
output = res.stdout.decode('utf-8')
有pdftotext，它基本上相同，但这假设pdftotext在/usr/local/bin中，而我在AWS lambda中使用这个，并希望从当前目录使用它。
顺便说一句:要在lambda上使用这个，你需要把二进制文件和依赖项放到libstdc++中。到函数中。我个人需要编译xpdf。由于这方面的说明会让这个答案变得更糟，我把它们放在了我的个人博客上。
我在这里找到了一个解决方案PDFLayoutTextStripper
这很好，因为它可以保持原始PDF的布局。
它是用Java编写的，但我已经添加了一个网关来支持Python。
示例代码:
from py4j.java_gateway import JavaGateway
gw = JavaGateway()
result = gw.entry_point.strip('samples/bus.pdf')
# result is a dict of {
# 'success': 'true' or 'false',
# 'payload': pdf file content if 'success' is 'true'
# 'error': error message if 'success' is 'false'
# }
print result['payload']
示例输出PDFLayoutTextStripper:
你可以在这里看到更多细节Stripper with Python
您可能希望使用经过时间验证的xPDF和派生工具来提取文本，因为pyPDF2在文本提取方面似乎仍然存在各种问题。
长的答案是，文本如何在PDF中编码有很多变化，它可能需要解码PDF字符串本身，然后可能需要与CMAP映射，然后可能需要分析单词和字母之间的距离等。
如果PDF被损坏(即显示正确的文本，但复制时产生垃圾)，并且您确实需要提取文本，那么您可能需要考虑将PDF转换为图像(使用ImageMagik)，然后使用Tesseract使用OCR从图像中获取文本。
我正在添加代码来实现这一点: 这对我来说很好:
# This works in python 3
# required python packages
# tabula-py==1.0.0
# PyPDF2==1.26.0
# Pillow==4.0.0
# pdfminer.six==20170720
import os
import shutil
import warnings
from io import StringIO
import requests
import tabula
from PIL import Image
from PyPDF2 import PdfFileWriter, PdfFileReader
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFPage
warnings.filterwarnings("ignore")
def download_file(url):
local_filename = url.split('/')[-1]
local_filename = local_filename.replace("%20", "_")
r = requests.get(url, stream=True)
print(r)
with open(local_filename, 'wb') as f:
shutil.copyfileobj(r.raw, f)
return local_filename
class PDFExtractor():
def __init__(self, url):
self.url = url
# Downloading File in local
def break_pdf(self, filename, start_page=-1, end_page=-1):
pdf_reader = PdfFileReader(open(filename, "rb"))
# Reading each pdf one by one
total_pages = pdf_reader.numPages
if start_page == -1:
start_page = 0
elif start_page < 1 or start_page > total_pages:
return "Start Page Selection Is Wrong"
else:
start_page = start_page - 1
if end_page == -1:
end_page = total_pages
elif end_page < 1 or end_page > total_pages - 1:
return "End Page Selection Is Wrong"
else:
end_page = end_page
for i in range(start_page, end_page):
output = PdfFileWriter()
output.addPage(pdf_reader.getPage(i))
with open(str(i + 1) + "_" + filename, "wb") as outputStream:
output.write(outputStream)
def extract_text_algo_1(self, file):
pdf_reader = PdfFileReader(open(file, 'rb'))
# creating a page object
pageObj = pdf_reader.getPage(0)
# extracting extract_text from page
text = pageObj.extractText()
text = text.replace("\n", "").replace("\t", "")
return text
def extract_text_algo_2(self, file):
pdfResourceManager = PDFResourceManager()
retstr = StringIO()
la_params = LAParams()
device = TextConverter(pdfResourceManager, retstr, codec='utf-8', laparams=la_params)
fp = open(file, 'rb')
interpreter = PDFPageInterpreter(pdfResourceManager, device)
password = ""
max_pages = 0
caching = True
page_num = set()
for page in PDFPage.get_pages(fp, page_num, maxpages=max_pages, password=password, caching=caching,
check_extractable=True):
interpreter.process_page(page)
text = retstr.getvalue()
text = text.replace("\t", "").replace("\n", "")
fp.close()
device.close()
retstr.close()
return text
def extract_text(self, file):
text1 = self.extract_text_algo_1(file)
text2 = self.extract_text_algo_2(file)
if len(text2) > len(str(text1)):
return text2
else:
return text1
def extarct_table(self, file):
# Read pdf into DataFrame
try:
df = tabula.read_pdf(file, output_format="csv")
except:
print("Error Reading Table")
return
print("\nPrinting Table Content: \n", df)
print("\nDone Printing Table Content\n")
def tiff_header_for_CCITT(self, width, height, img_size, CCITT_group=4):
tiff_header_struct = '<' + '2s' + 'h' + 'l' + 'h' + 'hhll' * 8 + 'h'
return struct.pack(tiff_header_struct,
b'II', # Byte order indication: Little indian
42, # Version number (always 42)
8, # Offset to first IFD
8, # Number of tags in IFD
256, 4, 1, width, # ImageWidth, LONG, 1, width
257, 4, 1, height, # ImageLength, LONG, 1, lenght
258, 3, 1, 1, # BitsPerSample, SHORT, 1, 1
259, 3, 1, CCITT_group, # Compression, SHORT, 1, 4 = CCITT Group 4 fax encoding
262, 3, 1, 0, # Threshholding, SHORT, 1, 0 = WhiteIsZero
273, 4, 1, struct.calcsize(tiff_header_struct), # StripOffsets, LONG, 1, len of header
278, 4, 1, height, # RowsPerStrip, LONG, 1, lenght
279, 4, 1, img_size, # StripByteCounts, LONG, 1, size of extract_image
0 # last IFD
)
def extract_image(self, filename):
number = 1
pdf_reader = PdfFileReader(open(filename, 'rb'))
for i in range(0, pdf_reader.numPages):
page = pdf_reader.getPage(i)
try:
xObject = page['/Resources']['/XObject'].getObject()
except:
print("No XObject Found")
return
for obj in xObject:
try:
if xObject[obj]['/Subtype'] == '/Image':
size = (xObject[obj]['/Width'], xObject[obj]['/Height'])
data = xObject[obj]._data
if xObject[obj]['/ColorSpace'] == '/DeviceRGB':
mode = "RGB"
else:
mode = "P"
image_name = filename.split(".")[0] + str(number)
print(xObject[obj]['/Filter'])
if xObject[obj]['/Filter'] == '/FlateDecode':
data = xObject[obj].getData()
img = Image.frombytes(mode, size, data)
img.save(image_name + "_Flate.png")
# save_to_s3(imagename + "_Flate.png")
print("Image_Saved")
number += 1
elif xObject[obj]['/Filter'] == '/DCTDecode':
img = open(image_name + "_DCT.jpg", "wb")
img.write(data)
# save_to_s3(imagename + "_DCT.jpg")
img.close()
number += 1
elif xObject[obj]['/Filter'] == '/JPXDecode':
img = open(image_name + "_JPX.jp2", "wb")
img.write(data)
# save_to_s3(imagename + "_JPX.jp2")
img.close()
number += 1
elif xObject[obj]['/Filter'] == '/CCITTFaxDecode':
if xObject[obj]['/DecodeParms']['/K'] == -1:
CCITT_group = 4
else:
CCITT_group = 3
width = xObject[obj]['/Width']
height = xObject[obj]['/Height']
data = xObject[obj]._data # sorry, getData() does not work for CCITTFaxDecode
img_size = len(data)
tiff_header = self.tiff_header_for_CCITT(width, height, img_size, CCITT_group)
img_name = image_name + '_CCITT.tiff'
with open(img_name, 'wb') as img_file:
img_file.write(tiff_header + data)
# save_to_s3(img_name)
number += 1
except:
continue
return number
def read_pages(self, start_page=-1, end_page=-1):
# Downloading file locally
downloaded_file = download_file(self.url)
print(downloaded_file)
# breaking PDF into number of pages in diff pdf files
self.break_pdf(downloaded_file, start_page, end_page)
# creating a pdf reader object
pdf_reader = PdfFileReader(open(downloaded_file, 'rb'))
# Reading each pdf one by one
total_pages = pdf_reader.numPages
if start_page == -1:
start_page = 0
elif start_page < 1 or start_page > total_pages:
return "Start Page Selection Is Wrong"
else:
start_page = start_page - 1
if end_page == -1:
end_page = total_pages
elif end_page < 1 or end_page > total_pages - 1:
return "End Page Selection Is Wrong"
else:
end_page = end_page
for i in range(start_page, end_page):
# creating a page based filename
file = str(i + 1) + "_" + downloaded_file
print("\nStarting to Read Page: ", i + 1, "\n -----------===-------------")
file_text = self.extract_text(file)
print(file_text)
self.extract_image(file)
self.extarct_table(file)
os.remove(file)
print("Stopped Reading Page: ", i + 1, "\n -----------===-------------")
os.remove(downloaded_file)
# I have tested on these 3 pdf files
# url = "http://s3.amazonaws.com/NLP_Project/Original_Documents/Healthcare-January-2017.pdf"
url = "http://s3.amazonaws.com/NLP_Project/Original_Documents/Sample_Test.pdf"
# url = "http://s3.amazonaws.com/NLP_Project/Original_Documents/Sazerac_FS_2017_06_30%20Annual.pdf"
# creating the instance of class
pdf_extractor = PDFExtractor(url)
# Getting desired data out
pdf_extractor.read_pages(15, 23)
