使用Python将pdf文件转换成word,csv

一:下载所需要的库

1 :pdfminer    安装库命令 pip install pdfminer3k

pdfminer3k是pdfminer的Python 3端口。PDFMiner是从PDF文档中提取信息的工具。与其他PDF相关的工具不同,它完全专注于获取和分析文本数据。PDFMiner允许获取页面中文本的确切位置,以及其他信息,如字体或线条。它包含一个PDF转换器,可以将PDF文件转换为其他文本格式(如HTML)。它有一个可扩展的PDF解析器,可用于其他目的而不是文本分析。

2:  docx          安装库命令 pip install python_docx

Python DocX目前是Python OpenXML的一部分,你可以用它打开Word 2007及以后的文档,而用它保存的文档可以在Microsoft Office 2007/2010, Microsoft Mac Office 2008, Google Docs, OpenOffice.org 3, and Apple iWork 08中打开。

from pdfminer.pdfparser import PDFParser, PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter,process_pdf
from pdfminer.layout import LAParams
from pdfminer.converter import PDFPageAggregator
from pdfminer.pdfinterp import PDFTextExtractionNotAllowed
from docx import Document
document = Document()
import warnings
warnings.filterwarnings("ignore")
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from io import StringIO
from urllib.request import urlopen
import pandas as pd

def readPDF(pdfFile):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, laparams=laparams)

    process_pdf(rsrcmgr, device, pdfFile)
    device.close()

    content = retstr.getvalue()
    retstr.close()
    return content
def save_to_file(file_name, contents):
    fh = open(file_name, 'w')
    fh.write(contents)
    fh.close()

save_to_file('mobiles.txt', 'your contents str')


def main():
    pdfFile = urlopen("http://pythonscraping.com/pages/warandpeace/chapter1.pdf")
    outputString = readPDF(pdfFile)
#c.word save_to_file(
'c.csv',outputString) if __name__ == '__main__': main()

使用docx 保存为word

from pdfminer.pdfparser import PDFParser, PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.layout import LAParams
from pdfminer.converter import PDFPageAggregator
from pdfminer.pdfinterp import PDFTextExtractionNotAllowed
from docx import Document
document = Document()
import warnings
warnings.filterwarnings("ignore")
import os
file_name=os.open('/Users/dudu/Desktop/test1/a.pdf',os.O_RDWR )

def main():

    fn = open(file_name,'rb')
    parser = PDFParser(fn)
    doc = PDFDocument()
    parser.set_document(doc)
    doc.set_parser(parser)
    resource = PDFResourceManager()
    laparams = LAParams()
    device = PDFPageAggregator(resource,laparams=laparams)
    interpreter = PDFPageInterpreter(resource,device)
    for i in doc.get_pages():
        interpreter.process_page(i)
        layout = device.get_result()
        for out in layout:
            if hasattr(out,"get_text"):
                content = out.get_text().replace(u'\xa0', u' ') 
                document.add_paragraph(
                    content, style='ListBullet'   
                )
            document.save('a'+'.docx')
    print ('处理完成')
 
if __name__ == '__main__':
    main()

加下面的公众号,我会定期发一些资料。

猜你喜欢

转载自www.cnblogs.com/dudu1992/p/8976349.html