def postlist_son(request):
if 'delete_list' in request.POST: # 删子文件夹-批量
pdf_id = request.POST.getlist("d2p_list")
file_infos = FileInfo.objects.filter(id__in=pdf_id)
for file_info in file_infos:
if file_info.file_type == 'FOLDER':
delete_all(file_info.file_path)
file_info.delete()
else:
os.remove(file_info.file_path)
file_info.delete()
file_infos = FileInfo.objects.all()
messages.success(request, "文件删除成功！")
elif 'mpdf_list' in request.POST: # 合并PDF文件夹-批量
output = PdfFileWriter()
outputPages = 0
output_name = ''
pdf_id = request.POST.getlist("d2p_list")
file_infos = FileInfo.objects.filter(id__in=pdf_id)
for file_info in file_infos:
# 读取源PDF文件
input = PdfFileReader(open(file_info.file_path, "rb"))
# 获得源PDF文件中页面总数
pageCount = input.getNumPages()
outputPages += pageCount
print("页数：%d" % pageCount)
# 分别将page添加到输出output中
for iPage in range(pageCount):
output.addPage(input.getPage(iPage))
# output_name=output_name+file_info.file_name.split('.')[0][0]+'-'
output_name = '整合-' + file_info.folder_name.split('\\')[-1]
# 写入到目标PDF文件
outputStream = open(
file_infos[0].folder_name + '\\' + output_name + '.pdf', "wb")
output.write(outputStream)
outputStream.close()
file_info1 = FileInfo(file_name=output_name + '.pdf',
file_path=file_infos[0].folder_name + '\\' +
output_name + '.pdf',
file_type='pdf',
load_user=get_user(request),
is_personal=int(B),
folder_name=file_infos[0].folder_name)
file_info1.save()
file_size1 = os.path.getsize(file_infos[0].folder_name + '\\' +
output_name + '.pdf')
FileInfo.objects.filter(
file_path=file_infos[0].folder_name + '\\' + output_name +
'.pdf').update(
file_size=1 if 0 < file_size1 < 1024 else file_size1 / 1024)
messages.success(request, "PDF合并成功！")
elif 'download_list' in request.POST: # 下载-子文件夹-批量
download_id = request.POST.getlist("d2p_list")
file_infos = FileInfo.objects.filter(id__in=download_id)
# print('下载的文件名：' + file_info.file_name)
for file_info in file_infos:
file = open(file_info.file_path, 'rb')
response = FileResponse(file)
response[
'Content-Disposition'] = 'attachment;filename="%s"' % urlquote(
file_info.file_name)
return response
elif 'tj_list' in request.POST:
word_id = request.POST.getlist("d2p_list")
file_infos = FileInfo.objects.filter(id__in=word_id)
for file_info in file_infos:
in_file = file_info.file_path
out_file = file_info.file_path.split(".")[0] + ".doc"
fp = open(in_file, 'rb') # 以二进制读模式打开
# 用文件对象来创建一个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()
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设备对象
laparams = LAParams()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
# 创建一个PDF解释器对象
interpreter = PDFPageInterpreter(rsrcmgr, device)
# 用来计数页面，图片，曲线，figure，水平文本框等对象的数量
num_page, num_image, num_curve, num_figure, num_TextBoxHorizontal = 0, 0, 0, 0, 0
for page in doc.get_pages(): # doc.get_pages() 获取page列表
num_page += 1 # 页面增一
interpreter.process_page(page)
# 接受该页面的LTPage对象
layout = device.get_result()
for x in layout:
if isinstance(x, LTImage): # 图片对象
num_image += 1
if isinstance(x, LTCurve): # 曲线对象
num_curve += 1
if isinstance(x, LTFigure): # figure对象
num_figure += 1
if isinstance(x, LTTextBoxHorizontal): # 获取文本内容
num_TextBoxHorizontal += 1 # 水平文本框对象增一
# 保存文本内容
with open(out_file, 'a',
encoding='utf-8') as f: #生成doc文件的文件名及路径
results = x.get_text()
f.write(results)
f.write('\n')
print('对象数量：\n', '页面数：%s\n' % num_page, '图片数：%s\n' % num_image,
'曲线数：%s\n' % num_curve,
'水平文本框：%s\n' % num_TextBoxHorizontal)
file_info1 = FileInfo(
file_name=file_info.file_name.split('.')[0] + '.doc',
file_path=out_file,
file_type='doc',
load_user=get_user(request),
is_personal=int(B),
folder_name=file_info.folder_name)
file_info1.save()
file_size1 = os.path.getsize(out_file)
FileInfo.objects.filter(file_path=out_file).update(
file_size=1 if 0 < file_size1 < 1024 else file_size1 /
1024)
messages.success(request, "DOC转换成功！")
else:
pdf_id = request.POST.getlist("d2p_list")
file_infos = FileInfo.objects.filter(id__in=pdf_id)
for file_info in file_infos:
in_file = file_info.file_path
out_file = file_info.file_path.split(".")[0] + ".pdf"
pythoncom.CoInitialize()
word = win32com.client.Dispatch('Word.Application')
doc = word.Documents.Open(in_file)
doc.SaveAs(out_file, FileFormat=17)
doc.Close()
time.sleep(1)
file_info1 = FileInfo(file_name=file_info.file_name.split('.')[0] +
'.pdf',
file_path=out_file,
file_type='pdf',
load_user=get_user(request),
is_personal=int(B),
folder_name=file_info.folder_name)
file_info1.save()
file_size1 = os.path.getsize(out_file)
FileInfo.objects.filter(file_path=out_file).update(
file_size=1 if 0 < file_size1 < 1024 else file_size1 / 1024)
messages.success(request, "PDF转换成功！")
return HttpResponseRedirect(reverse('fileserver:list1', args=[a]))
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(full_name1, 'ab') as f:
results = x.get_text()
f.write((results + '\r\n').encode('utf-8'))
else:
if a[1] == '.doc':
doc = word.Documents.Open(full_name)
doc.SaveAs(FileFormat=7, FileName=full_name1)
doc.Close()
textdoc = readfile(full_name1)
textdoc = textdoc.decode("GBK")
savefile(full_name1, textdoc.encode("utf-8"))
else:
print(corpus_path + "存在无法识别的文件，请检查文件夹内容")
sys.exit(-1)
word.Quit() # 退出word
# 对测试集进行分词
# 若采用命令行传入参数方式，改下面
# corpus_path = sys.argv[2] # 未分词分类语料库路径（绝对路径）
# corpus_path = "./测试数据/" # 未分词分类语料库路径（相对路径）
seg_path = path1 + "/model/测试数据分词后/" # 分词后分类语料库路径
corpus_segment2(corpus_path1, seg_path)
