python每日一练

前言

人生苦短，我用python【2018.6.4第一更】

要求

你有一个目录，放了你一个月的日记，都是 txt，为了避免分词的问题，假设内容都是英文，请统计出你认为每篇日记最重要的词。

代码

# -*- coding:utf-8 -*-
import re
import glob
import os


def get_max_wordlist(filePath):
    try:
        fp = open(filePath, "r")
        dictResult = {}
        wordlist = []
        for line in fp.readlines():
            wordList = re.findall(r"[\w\d-]+", line.lower())
            for li in wordList:
                dictResult[li] = 1 + dictResult.get(li, 0)
        # get max wordlist
        result = max(dictResult.items(), key=lambda item: item[1])
        for dictR in dictResult:
            if dictResult[dictR] == result[1]:
                wordlist.append(dictR)
        # print result[len(result)-1][1]
    except Exception, e:
        print e.message
    finally:
        fp.close()
        return wordlist


def count_word(path):
    fileList = glob.glob(r"./diary/*.txt")
    for fi in fileList:
        filePath = os.path.abspath(os.getcwd()) + re.sub(r"^\.", "", fi)
        result = get_max_wordlist(filePath)
        print "in file {} most important words:".format(filePath)+" ".join(result)
        # print "in file {} most important words:{1[0]},{1[1]},{1[2]},{1[3]}".format(filePath, result)


def main():
    path = "."
    count_word(path)


if __name__ == "__main__":
    main()

另外学习了一下format的用法

# -*- coding:utf-8 -*-
print "{}.{}".format(12, 32)
print "{name}.{age}".format(name="jsk", age=32)
print "{:>8}.{:<8}".format(111, 222)
print "{:>8}.{:x<8}".format(111, 222)
print "{:.2f}.{:x<8}".format(33.22222222, 222)
print "{:b},{:o},{:d},{:x},{:%}".format(17, 17, 17, 17,17)

总结

睡觉了！