6个Python办公黑科技，助你提升工作效率

# encoding: utf-8
import os, sys
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.layout import LAParams
from pdfminer.converter import PDFPageAggregator

import smtplib
smtpObj = smtplib.SMTP( [host [, port [, local_hostname]]] )

SMTP.sendmail(from_addr, to_addrs, msg[, mail_options, rcpt_options])

#!/usr/bin/python# -*- coding: UTF-8 -*- 
import smtplibfrom email.mime.text 
import MIMETextfrom email.header 
import Header sender = 'from@runoob.com'
# 西红柿微：ZPYDWXYreceivers = ['1221121@qq.com']  
# 接收邮件，可设置为你的QQ邮箱或者其他邮箱 
# 三个参数：第一个为文本内容，第二个 plain 设置文本格式，第三个 utf-8 设置编码message = MIMEText('Python 邮件发送测试...', 'plain', 'utf-8')message['From'] = Header("不吃西红柿", 'utf-8')   
# 发送者message['To'] =  Header("测试", 'utf-8')        
# 接收者 subject = 'Python SMTP 邮件测试'message['Subject'] = Header(subject, 'utf-8')  
try:    smtpObj = smtplib.SMTP('localhost')    smtpObj.sendmail(sender, receivers, message.as_string())    
print "邮件发送成功"except smtplib.SMTPException:    
print "Error: 无法发送邮件"

#查看订单明细号是否重复，结果是没。
df1["订单明细号"].duplicated().value_counts()
df2["订单明细号"].duplicated().value_counts()

df_c=pd.merge(df1,df2,on="订单明细号",how="left")

pd.pivot_table(sale,index="地区名称",columns="业务员名称",values="利润",aggfunc=[np.sum,np.mean])

sale["订单明细号2"]=sale["订单明细号"]

#在订单明细号2里前10个都+1.
sale["订单明细号2"][1:10]=sale["订单明细号2"][1:10]+1

#差异输出
result=sale.loc[sale["订单明细号"].isin(sale["订单明细号2"])==False]

sale.drop_duplicates("业务员编码",inplace=True)

#用0填充缺失值
sale["客户名称"]=sale["客户名称"].fillna(0)
#删除有客户编码缺失值的行
sale.dropna(subset=["客户编码"])

sale.loc[(sale["地区名称"]=="北京")&(sale["业务员名称"]=="张爱")&(sale["订单金额"]>5000)]

sale.loc[sale["存货名称"].str.contains("三星|索尼")]

sale.groupby(["地区名称","业务员名称"])["利润"].sum()

sale.loc[sale["存货名称"].str.contains("三星")&(sale["税费"]>=1000)][["订单明细号","利润"]].describe()

sale["存货名称"].map(lambda s :s.strip(""))

# encoding: utf-8
import json
from pyecharts.charts import Pie
from pyecharts import options as opts
from pyecharts.charts import Radar



def draw_Radar():
    from pyecharts.charts import Radar
    radar = Radar()
    # //由于雷达图传入的数据得为多维数据，所以这里需要做一下处理
    radar_data = [[10, 10, 10, 10, 10]]
    radar_data1 = [[2, 10, 3, 6, 3]]
    radar_data2 = [[1, 8, 7, 5, 8]]

    # //设置column的最大值，为了雷达图更为直观，这里的月份最大值设置有所不同
    schema = [
        ("物理", 100), ("魔法", 10), ("防御", 10),("难度", 10),("喜好", 10)
    ]
    # //传入坐标
    radar.add_schema(schema)
    radar.add("满分", radar_data)
    # //一般默认为同一种颜色，这里为了便于区分，需要设置item的颜色
    radar.add("安妮", radar_data1, color="#E37911")
    radar.add("卡尔玛", radar_data2, color="#1C86EE")
    radar.render()

if __name__ == '__main__':

    draw_Radar()

# encoding: utf-8
import os, sys
import docx

def word_reader(file):
    try:
        # docx 直接读
        if 'docx' in file:
            res = ''
            f = docx.Document(file)
            for para in f.paragraphs:
                res = res + '\n' +para.text
        else:
            # 先转格式doc>docx
            os.system("textutil -convert docx '%s'"%file)
            word_reader(file+'x')
            res = ''
            f = docx.Document(file+'x')
            for para in f.paragraphs:
                res = res + '\n' +para.text
        return res
    except:
        # print(file, 'read failed')
        return ''

>>> import math
>>> math.cos(math.pi / 4)
0.70710678118654757
>>> math.log(1024, 2)
10.0