import os
import re
from pdfminer.converter import LTChar, TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFTextExtractionNotAllowed
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LAParams, LTTextBox
from io import StringIO
from io import open
#读取pdf文件文本内容
def read(path):
parser = PDFParser(path)
doc = PDFDocument(parser, '')
parser.set_document(doc)
if not doc.is_extractable:
raise PDFTextExtractionNotAllowed
else:
# 创建PDf 资源管理器 来管理共享资源
rsrcmgr = PDFResourceManager()
# 创建一个PDF聚合器,包含资源管理器与参数分析器
laparams = LAParams()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
# 创建一个PDF解释器对象
python PDF2TXT,提取到TXT的字序混乱,请教怎么修改?
最新推荐文章于 2023-11-24 15:35:43 发布
![](https://img-home.csdnimg.cn/images/20240711042549.png)