我正在尝试使用Python提取此PDF文件中包含的文本。
我正在使用PyPDF2包（版本1.27.2），并拥有以下脚本：
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，我的输出结果与PDF文档中的不同：
! " # $ % # $ % &% $ &' ( ) * % + , - % . / 0 1 ' * 2 3% 4
5
' % 1 $ # 2 6 % 3/ % 7 / ) ) / 8 % &) / 2 6 % 8 # 3" % 3" * % 31 3/ 9 # &)
%
我如何提取PDF文档中原样的文本？
def pdf_to_text():
from pdfminer.high_level import extract_text
text = extract_text('test.pdf')
print(text)
# 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)
您可以从这里下载最新版本的tika-app-xxx.jar。
然后将此 .jar 文件放置在您的 Python 脚本文件所在的同一文件夹中。
接下来，在脚本中插入以下代码：
import os
import os.path
tika_dir=os.path.join(os.path.dirname(__file__),'<tika-app-xxx>.jar')
def extract_pdf(source_pdf:str,target_txt:str):
os.system('java -jar '+tika_dir+' -t {} > {}'.format(source_pdf,target_txt))
依赖较少。单个.jar文件比Python包更易于管理。
多格式支持。位置source_pdf可以是任何类型文档的目录。（.doc，.html，.odt等）
最新版本。tika-app.jar始终早于tika python包的相关版本发布。
稳定性。它比PyPDF更稳定和良好维护（由Apache支持）。
需要jre-headless。
试用 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()
.//pdfs// 文件夹中所有PDF文件的文本将存储在列表 pdf_text_list 中。from tika import parser
import glob
def read_pdf(filename):
text = parser.from_file(filename)
return(text)
all_files = glob.glob(".\\pdfs\\*.pdf")
pdf_text_list=[]
for i,file in enumerate(all_files):
text=read_pdf(file)
pdf_text_list.append(text['content'])
print(pdf_text_list)
import os
from PyPDF2 import PdfFileWriter, PdfFileReader
from io import BytesIO
mydir = # specify path to your directory where PDF or PDF's are
for arch in os.listdir(mydir):
buffer = io.BytesIO()
archpath = os.path.join(mydir, arch)
with open(archpath) as f:
pdfFileObj = open(archpath, 'rb')
pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
pdfReader.numPages
pageObj = pdfReader.getPage(0)
ley = pageObj.extractText()
file1 = open("myfile.txt","w")
file1.writelines(ley)
file1.close()
提取PDF中的文本，请使用以下代码
import PyPDF2
pdfFileObj = open('mypdf.pdf', 'rb')
pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
print(pdfReader.numPages)
pageObj = pdfReader.getPage(0)
a = pageObj.extractText()
print(a)
Camelot 看起来是 Python 中从 PDF 中提取表格的相当强大的解决方案。
乍一看，它似乎实现了几乎与 CreekGeek 建议的 tabula-py 包一样准确的提取，后者在可靠性方面已经远远超过了今天发布的任何其他解决方案，但据说它 更加可配置。此外，它还有自己的准确性指标（results.parsing_report）和出色的调试功能。
Camelot 和 Tabula 都将结果作为 Pandas 的数据帧提供，因此很容易在之后调整表格。
pip install camelot-py
camelot包混淆。）import camelot
df_list = []
results = camelot.read_pdf("file.pdf", ...)
for table in results:
print(table.parsing_report)
df_list.append(results[0].df)
它还可以将结果输出为CSV、JSON、HTML或Excel。
使用Camelot需要一些依赖。
NB：由于我的输入非常复杂，包含许多不同的表格，因此我最终使用了同时使用Camelot和Tabula，根据表格来实现最佳结果。
目标：从PDF中提取文本
所需工具：
Poppler for windows：在Windows中pdftotext文件的包装器 对于anaconda：conda install -c conda-forge
pdftotext：将PDF转换为文本的实用程序。
步骤： 安装Poppler。对于Windows，请将“xxx/bin/”添加到环境路径中 pip install pdftotext
import pdftotext
# Load your PDF
with open("Target.pdf", "rb") as f:
pdf = pdftotext.PDF(f)
# Save all text to a txt file.
with open('output.txt', 'w') as f:
f.write("\n\n".join(pdf))
这包括根据文档中的页数动态设置每个PDF页面的新工作表。
import PyPDF2 as p2
import xlsxwriter
pdfFileName = "sample.pdf"
pdfFile = open(pdfFileName, 'rb')
pdfread = p2.PdfFileReader(pdfFile)
number_of_pages = pdfread.getNumPages()
workbook = xlsxwriter.Workbook('pdftoexcel.xlsx')
for page_number in range(number_of_pages):
print(f'Sheet{page_number}')
pageinfo = pdfread.getPage(page_number)
rawInfo = pageinfo.extractText().split('\n')
row = 0
column = 0
worksheet = workbook.add_worksheet(f'Sheet{page_number}')
for line in rawInfo:
worksheet.write(row, column, line)
row += 1
workbook.close()