def act_extract(self):
if self.filepath_in is None or not os.path.exists(self.filepath_in):
self.act_open()
# initialize
self.combobox.clear()
self.combobox.addItem('原件')
self.combobox.addItem(r'提取的文件')
self.combobox.setCurrentIndex(1)
#
extract = Extract(self.filepath_in)
extract.process(output_filepath=self.filepath_extract)
#db['project_info'].set_db(extract.extract_project_infos())
self.refresh_left_preview(self.filepath_extract)
extract_filename = 'simohua-extract.docx'
extract_filepath = os.path.join(os.getcwd(), extract_filename)
output_filename = 'output.docx'
output_filepath = os.path.join(os.getcwd(), output_filename)
tmp_dir1 = os.path.join(os.getcwd(), 'tmp\\split')
tmp_dir2 = os.path.join(os.getcwd(), 'tmp\\split-processed')
from misc import mkdir
if __name__ == "__main__":
#
extract = Extract(input_filepath)
extract.process() #output_filepath=extract_filepath)
db['project_info'].set_db(extract.extract_project_infos())
#
mkdir(tmp_dir1)
split = Split(input_filepath=extract_filepath)
sections = split.process()
#
db['finance'].filtering(need_years=3)
db['human'].select_people(name_list=['总经理姓名', '联系人姓名', '项目经理人姓名'])
db['projects_done'].filtering(project_types=['水利'], need_years=3)
db['projects_being'].filtering(project_types=['水利'])
#
mkdir(tmp_dir2)
for section in sections:
fillin = FillIn(os.path.join(tmp_dir1, section + '.docx'))
fillin.process(os.path.join(tmp_dir2, section + '.docx'))
