74 lines
2.9 KiB
Python
74 lines
2.9 KiB
Python
|
import os
|
|||
|
|
import re
|
|||
|
|
import logging
|
|||
|
|
log = logging.getLogger(__name__)
|
|||
|
|
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:
|
|||
|
|
log.info(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()
|
|||
|
|
# log.info(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:
|
|||
|
|
log.info("转换失败：%s", pdf_name)
|
|||
|
|
continue
|