python - 使用 Python 从简历中提取多个字段

Question

我正在尝试用 Python 处理大量简历。简历示例可能如下所示。不幸的是，每份简历可能不会使用相同的格式。除了使用正则表达式用 python 从简历中提取某些字段(假设我将它们全部转换为纯文本)之外，还有其他好的方法吗？

Name: Someone
Tel: xxx-xxxxxxx
Add: 123 Some Street
Email: Someone@gmail.com

Objective/Goal
To obtain a position in...

Education
2004 - 2006: University of XYZ


Work Experience
2006 - 2008: Programmer

Skills
Programming skills: Python, ..

假设我只对提取其中的几个字段感兴趣，我如何才能获取字段名称和下一个字段之间的所有文本？比如我只想获取姓名和工作经历字段，应该返回如下。

NameField = 'Someone'
WorkExpField = '2006 - 2008: Programmer...'

Answer 1

我的“我要试试这个，但懒得做漂亮”的方法适用于不同格式的简历。我愿意在不同的简历格式上对其进行测试。 欢迎提供更多建议/意见!

import string

class Resume():
    def __init__(self,filename):
        self.filepath = filename
        self.load()
        self.parse()

    def load(self):
        with open(self.filepath,'rb') as f:
            self.content = f.read().splitlines()

    def checkLine(self,word,value, content, line):
        if word in content.lower():
            value = self.addValue(value,line)
        return value

    def addValue(self,value,line):
        value[line] = value.get(line,0) + 1
        return value

    def dict_List(self,dict_, content):
        new = [(key,value) for key,value in dict_.items() if dict_[key] == max(dict_.values())]
        return [(x[0],content[x[0]]) for x in sorted(new)]

    def get_name(self):
        names = []
        for each in self.name:
            if each[0] not in self.headings:
                each = each[1].replace('Name',"")
                if each[0] not in string.letters:
                    each = each[1:]
                names.append(each.strip())
            else:
                index = self.headings[self.headings.index(each[0])+1]
                names.append("\n".join(self.content[each[0]+1:index]))
        if len(names) == 1:
            return names[0]
        else:
            return names

    def get_work(self):
        experience = []
        for each in self.work:
            index = self.headings[self.headings.index(each[0])+1]
            experience.append("\n".join(self.content[each[0]+1:index]))
        if len(experience) == 1:
            return experience[0]
        else:
            return epxerience

    def parse(self):
        name = dict()
        work_experience = dict()
        isHeading = dict()
        for line_num in range(len(self.content)):
            for checkName in ["name",":"]:
                name.update(self.checkLine(checkName,name,self.content[line_num], line_num))
            for checkWork in ["work","experience"]:
                work_experience.update(self.checkLine(checkWork,work_experience, self.content[line_num],line_num))
            if line_num != len(self.content) - 1:
                if len(self.content[line_num + 1]) > len(self.content[line_num]):
                    isHeading.update(self.addValue(isHeading,line_num))
            if line_num > 0:
                if self.content[line_num - 1] == "":
                    isHeading.update(self.addValue(isHeading,line_num))
            if len(self.content[line_num]) == len(self.content[line_num].lstrip()):
                isHeading.update(self.addValue(isHeading,line_num))
            if self.content[line_num] == "":
                isHeading[line_num] = isHeading.get(line_num,0) - 1

        self.name = self.dict_List(name, self.content)
        self.work = self.dict_List(work_experience, self.content)
        self.headings = self.dict_List(isHeading, self.content)
        self.headings = [x[0] for x in self.headings]



if __name__ == "__main__":
    resume = Resume(filename = 'sampleresume.txt')
    print resume.get_name()
    print resume.get_work()

产量:

Someone
2006 - 2008: Programmer