python 比较常见的工具方法

下面是一些工作过程中比较常见的工具方法，但不代表最终答案。希望能对你有所帮助，如果您有更好更多的方法工具，欢迎推荐！

1. 按行读取带json字符串的文件

# -*- coding:utf-8 -*-
import json
import sys

with open("./aldwx-log-20.20190619194001.json.COMPLETED",'r') as load_f:
    for line in load_f:
        try:
            load_dict = json.loads(line)
            #server_time = load_dict['server_time']
            #et = load_dict['et'] if load_dict.has_key("et") else server_time   #三元表达式
        except :
            pass

2. 获取每日的时间列表

# -*- coding:utf-8 -*-
import datetime
def getBetweenDay():
    date_list = []

    #获取开始与结束时间，范例为获取最近7天时间
    now_time = datetime.datetime.now()
    begin_day = (now_time+datetime.timedelta(days=-7)).strftime("%Y%m%d")
    end_day = (now_time+datetime.timedelta(days=-1)).strftime("%Y%m%d")

    begin_date = datetime.datetime.strptime(begin_day, "%Y%m%d")
    end_date = datetime.datetime.strptime(end_day, "%Y%m%d")

    while begin_date <= end_date:
        date_str = begin_date.strftime("%Y%m%d")
        date_list.append(date_str)
        begin_date += datetime.timedelta(days=1)
    return date_list

3. 计量单位格式化输出

# -*- coding:utf-8 -*-
#计量单位格式化输出
def formatData(value):
    units = ['B', 'KB', 'MB', 'GB', 'TB', 'PB' ]
    try:
        size = float(value)
    except:
        return False

    if size < 0:
        return False

    for unit in units:
        if size >= 1024:
            #中间结果保留4位小数。网上很多资料只注重最终的结果，导致最终结果误差很大
            size = float('%.4f' %( size / 1024))
        else:
            size_h = '{0:.2f} {1}'.format(size, unit)
            return size_h

    #超大数据仅保留到PB级
    size_h = '{0:.2f} {1}'.format(size, units[-1])
    return size_h

4. 元组转换为字典

# -*- coding:utf-8 -*-
def tuple_to_dic(results):
    """元组转换为字典,字典key为元组第一个值，字典值为元组第二个值的列表集"""
    tmp_dic = {}
    for i in range(len(results)):
        if tmp_dic.has_key(results[i][0]):
            tmp_dic[results[i][0]].append(results[i][1])
        else:
            tmp_dic[results[i][0]] = []
            tmp_dic[results[i][0]].append(results[i][1])
    return tmp_dic

示例:
代码如下

# -*- coding:utf-8 -*-

results = ((20190713,1),(20190713,2),(20190713,3),(20190714,4))

def tuple_to_dic(results):
    """元组转换为字典,字典key为元组第一个值，字典值为元组第二个值的列表集"""
    tmp_dic = {}
    for i in range(len(results)):
        if tmp_dic.has_key(results[i][0]):
            tmp_dic[results[i][0]].append(results[i][1])
        else:
            tmp_dic[results[i][0]] = []
            tmp_dic[results[i][0]].append(results[i][1])
    return tmp_dic
dic = tuple_to_dic(results)
print dic

输出结果为

{20190713: [1, 2, 3], 20190714: [4]}

持续更新中...