pdfMiner3k

[寒潭烟光]

from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LAParams, LTTextBoxHorizontal
from pdfminer.pdfparser import PDFParser, PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, PDFTextExtractionNotAllowed
from pdfminer.pdfdevice import PDFDevice


def read_pdf(pdf_filename, txt_filename):
fp = open(pdf_filename, 'rb')
parser = PDFParser(fp)
doc = PDFDocument()
parser.set_document(doc)
doc.set_parser(parser)
doc.initialize('')
if not doc.is_extractable:
raise PDFTextExtractionNotAllowed
rsrcmgr = PDFResourceManager()
laparams = LAParams()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in doc.get_pages():
interpreter.process_page(page)
layout = device.get_result()
for x in layout:
if isinstance(x, LTTextBoxHorizontal):
with open(txt_filename, 'a') as f:
results = x.get_text()
print(results)
f.write(results + '\n')


if __name__ == '__main__':
pdf_filename = 'E:\\知识图谱项目\\《中国药典》2015年版 第一部.pdf'
txt_filename = 'E:\\知识图谱项目\\《中国药典》2015年版 第一部.txt'
read_pdf(pdf_filename, txt_filename)

D:\python3.6.2\python.exe E:/知识图谱项目源码/extractEntity/extract_entity_codex.py
WARNING:root:Cannot locate objid=21077
WARNING:root:Cannot locate objid=21077
WARNING:root:Wrong type: None required: <class 'dict'>
WARNING:root:Cannot locate objid=21074

Process finished with exit code 0

为什么为出现警告，而且没有读取PDF文件的任何内容

[CSDN客服-糊胡]

引用 楼主 cswangjiawei 的回复:

from pdfminer.converter import PDFPageAggregator from pdfminer.layout import LAParams, LTTextBoxHorizontal from pdfminer.pdfparser import PDFParser, PDFDocument from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, PDFTextExtractionNotAllowed from pdfminer.pdfdevice import PDFDevice def read_pdf(pdf_filename, txt_filename): fp = open(pdf_filename, 'rb') parser = PDFParser(fp) doc = PDFDocument() parser.set_document(doc) doc.set_parser(parser) doc.initialize('') if not doc.is_extractable: raise PDFTextExtractionNotAllowed rsrcmgr = PDFResourceManager() laparams = LAParams() device = PDFPageAggregator(rsrcmgr, laparams=laparams) interpreter = PDFPageInterpreter(rsrcmgr, device) for page in doc.get_pages(): interpreter.process_page(page) layout = device.get_result() for x in layout: if isinstance(x, LTTextBoxHorizontal): with open(txt_filename, 'a') as f: results = x.get_text() print(results) f.write(results + '\n') if __name__ == '__main__': pdf_filename = 'E:\\知识图谱项目\\《中国药典》2015年版 第一部.pdf' txt_filename = 'E:\\知识图谱项目\\《中国药典》2015年版 第一部.txt' read_pdf(pdf_filename, txt_filename) D:\python3.6.2\python.exe E:/知识图谱项目源码/extractEntity/extract_entity_codex.py WARNING:root:Cannot locate objid=21077 WARNING:root:Cannot locate objid=21077 WARNING:root:Wrong type: None required: <class 'dict'> WARNING:root:Cannot locate objid=21074 Process finished with exit code 0 为什么为出现警告，而且没有读取PDF文件的任何内容

您好！ 请问您反馈的是知识库的问题吗？如果是，经技术产品，不是我们的问题，应该是您电脑的问题。

[Mark-30]

请问解决了吗

[muhuaqingfeng]

请问这个问题怎么解决？