1, needs to be sorted out received resume (from cooperated, 51, for recruitment; Are PDF text type, the image scanning format, content format compare specification) : the main is to need to do a form, statistics under the name, age, educational background, school, major, interest areas, telephone, email,
2, have no contact with python, need to start install python
3, to improve the efficiency of this thing, but baidu has several projects to spend money: Wan Xing PDF can implement delimit region extraction content but require extraction region fixed; Grain specializes in resume management, is very good, powerful but I only need the data extraction function,