72 lines
2.8 KiB
Python
72 lines
2.8 KiB
Python
import os
|
||
import re
|
||
from tqdm import tqdm
|
||
from pdfminer.pdfparser import PDFParser,PDFDocument
|
||
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
|
||
from pdfminer.converter import PDFPageAggregator
|
||
from pdfminer.layout import LTTextBoxHorizontal,LAParams
|
||
from pdfminer.pdfinterp import PDFTextExtractionNotAllowed
|
||
|
||
def pdf_parse(pdf_path,txt_path):
|
||
'''解析PDF文本，并保存到TXT文件中'''
|
||
fp = open(pdf_path,'rb')
|
||
# pdf1 = urlopen('http://www.tencent.com/20160321.pdf')
|
||
#用文件对象创建一个PDF文档分析器
|
||
parser = PDFParser(fp)
|
||
#创建一个PDF文档
|
||
doc = PDFDocument()
|
||
#连接分析器，与文档对象
|
||
parser.set_document(doc)
|
||
doc.set_parser(parser)
|
||
|
||
#提供初始化密码，如果没有密码，就创建一个空的字符串
|
||
doc.initialize()
|
||
|
||
#检测文档是否提供txt转换，不提供就忽略
|
||
if not doc.is_extractable:
|
||
print(pdf_path)
|
||
raise PDFTextExtractionNotAllowed
|
||
else:
|
||
#创建PDF，资源管理器，来共享资源
|
||
rsrcmgr = PDFResourceManager()
|
||
#创建一个PDF设备对象
|
||
laparams = LAParams()
|
||
device = PDFPageAggregator(rsrcmgr,laparams=laparams)
|
||
#创建一个PDF解释其对象
|
||
interpreter = PDFPageInterpreter(rsrcmgr,device)
|
||
|
||
#循环遍历列表，每次处理一个page内容
|
||
# doc.get_pages() 获取page列表
|
||
for page in doc.get_pages():
|
||
interpreter.process_page(page)
|
||
#接受该页面的LTPage对象
|
||
layout = device.get_result()
|
||
# 这里layout是一个LTPage对象 里面存放着 这个page解析出的各种对象
|
||
# 一般包括LTTextBox, LTFigure, LTImage, LTTextBoxHorizontal 等等
|
||
# 想要获取文本就获得对象的text属性，
|
||
for x in layout:
|
||
if(isinstance(x,LTTextBoxHorizontal)):
|
||
with open(txt_path,'a') as f:
|
||
results = x.get_text()
|
||
# print(results)
|
||
f.write(results +"\n")
|
||
|
||
|
||
if __name__ == '__main__':
|
||
open_pdf_path = '/Users/zhengfei/Desktop/科润智控.pdf' #【设定打开pdf文件路径】
|
||
save_txt_path = '/Users/zhengfei/Desktop/' #【设定保存TXT文件路径】
|
||
pdfList = os.listdir(open_pdf_path)
|
||
for pdf_name in tqdm(pdfList):
|
||
try:
|
||
format = pdf_name.split(".")[1]
|
||
if format=="pdf":
|
||
pdf_path = open_pdf_path+pdf_name
|
||
txt_name = re.sub('.pdf', '.txt', pdf_name)
|
||
elif format=="PDF":
|
||
pdf_path = open_pdf_path+pdf_name
|
||
txt_name = re.sub('.PDF', '.txt', pdf_name)
|
||
txt_path = save_txt_path+txt_name
|
||
pdf_parse(pdf_path, txt_path)
|
||
except:
|
||
print("转换失败：", pdf_name)
|
||
continue |