'''
读取pdf文件
'''
from urllib.request import urlopen
from pdfminer.pdfinterp import PDFResourceManager, process_pdf
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from io import StringIO
from io import open
import os
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
pathDir = os.listdir('/home/hepburn/feb') # 读取feb文件夹下的pdf文件
# print(pathDir)
for allDir in pathDir:
child = os.path.join('%s' % (allDir))
print(child)
filename = '/home/hepburn/feb/{}'.format(child) #每个文件的路径
print(filename)
# pdfFile = urlopen("http://pythonscraping.com/pages/warandpeace/chapter1.pdf") # 读取PDF链接
pdfFile = open(filename, 'rb')
outputString = readPDF(pdfFile)
print(outputString)
with open('/home/hepburn/ahtml/{}.html'.format(child), 'w') as f:
f.write(outputString) # 写入文件
pdfFile.close()
python读取pdf文件
最新推荐文章于 2024-03-25 08:28:08 发布