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
试试borb，一个纯python PDF库
import typing
from borb.pdf.document import Document
from borb.pdf.pdf import PDF
from borb.toolkit.text.simple_text_extraction import SimpleTextExtraction
def main():
# variable to hold Document instance
doc: typing.Optional[Document] = None
# this implementation of EventListener handles text-rendering instructions
l: SimpleTextExtraction = SimpleTextExtraction()
# open the document, passing along the array of listeners
with open("input.pdf", "rb") as in_file_handle:
doc = PDF.loads(in_file_handle, [l])
# were we able to read the document?
assert doc is not None
# print the text on page 0
print(l.get_text(0))
if __name__ == "__main__":
main()
其他回答
Pdfplumber是一个更好的从pdf中读取和提取数据的库。它还提供了读取表数据的方法，在经历了大量这样的库之后，pdfplumber最适合我。
请注意，它最适合机器编写的pdf，而不是扫描的pdf。
import pdfplumber
with pdfplumber.open(r'D:\examplepdf.pdf') as pdf:
first_page = pdf.pages[0]
print(first_page.extract_text())
在2020年，上述解决方案并不适用于我正在使用的特定pdf。下面是诀窍。我用的是Windows 10和Python 3.8
测试pdf文件:https://drive.google.com/file/d/1aUfQAlvq5hA9kz2c9CyJADiY3KpY3-Vn/view?usp=sharing
#pip install pdfminer.six
import io
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
def convert_pdf_to_txt(path):
'''Convert pdf content from a file path to text
:path the file path
'''
rsrcmgr = PDFResourceManager()
codec = 'utf-8'
laparams = LAParams()
with io.StringIO() as retstr:
with TextConverter(rsrcmgr, retstr, codec=codec,
laparams=laparams) as device:
with open(path, 'rb') as fp:
interpreter = PDFPageInterpreter(rsrcmgr, device)
password = ""
maxpages = 0
caching = True
pagenos = set()
for page in PDFPage.get_pages(fp,
pagenos,
maxpages=maxpages,
password=password,
caching=caching,
check_extractable=True):
interpreter.process_page(page)
return retstr.getvalue()
if __name__ == "__main__":
print(convert_pdf_to_txt('C:\\Path\\To\\Test_PDF.pdf'))
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)
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。
从2021年开始，我想推荐pdfreader，因为pypddf2 /3现在看起来很麻烦，tika实际上是用java写的，需要在后台安装jre。Pdfreader是python的，目前维护得很好，这里有大量的文档。
正常安装:pip install pdfreader
用法的简短例子:
from pdfreader import PDFDocument, SimplePDFViewer
# get raw document
fd = open(file_name, "rb")
doc = PDFDocument(fd)
# there is an iterator for pages
page_one = next(doc.pages())
all_pages = [p for p in doc.pages()]
# and even a viewer
fd = open(file_name, "rb")
viewer = SimplePDFViewer(fd)
