Python:一周笔记

import email
from email.mime.text import MIMEText
import smtplib
from email.header import Header

# 构造邮件信息
msg = MIMEText('这是一份python自动脚本邮件信息。', 'plain', 'utf-8') # 邮件正文

# QQ发给公司： 多了这步 server.starttls()
from_addr = "xie_wei_sh@foxmail.com" # 发件人
password = "****" # 发件人邮箱密码
smtp_server = "smtp.qq.com"  # SMTP 服务器地址
port = 587  # SMTP 服务器端口
to_addr = "paul.xie@chinascope.com"  # 收件人

msg["From"] = Header("Python爱好者<{}>".format(from_addr))  # 显示的邮件发件人
msg["To"] = Header("admin<{}>".format(to_addr))
msg["Subject"] = Header("来自SMTP的问候", "utf-8")  # 邮件主题

# 发送邮件 
server = smtplib.SMTP(smtp_server, port)
server.starttls()
server.set_debuglevel(1)
server.login(from_addr, password=password)
server.sendmail(from_addr, [to_addr], msg=msg.as_string())
server.quit()

import yagmail

# 设置发送人信息及SMTP服务器和端口
yag = yagmail.SMTP(
    user="xie_wei_sh@foxmail.com",
    password="****",
    host="smtp.qq.com",
    port="587"
)

contents = u"系统发出警告,你已严重违规。"
yag.send(to=["paul.xie@chinascope.com","1156143589@qq.com"], subject="yagmail", contents=contents)

# 参数说明
to : 收件人，可以接受一个list 发送至多人

subject: 邮件主题

contents: 邮件正文，默认是文本信息，其实还可以接收各种常见的文件比如，*.jpg, *.docx, *.pdf ，*.html 等信息，只需要设置完整路径，或者同一目录下文件名称即可。

import logging

logger = logging.getLogger("logger_name") # 记录器
handler = logging.StreamHandler()  # 日志显示在控制台，还可以设置将日志信息输出为文本形式FileHandler()
formatter = logging.Formatter(
        '%(asctime)s %(name)-12s %(levelname)-8s %(message)s')
        
handler.setFormatter(formatter) # 设置日志显示方式
logger.addHandler(handler) # 添加处理器
logger.setLevel(logging.DEBUG) # 设置日志级别

logger.debug('often makes a very good meal of %s', 'visiting tourists') # 日志在程序中的使用

# 读取本地pdf转化为字符串
from cStringIO import StringIO

from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage


def convert_pdf_2_text(path):

    rsrcmgr = PDFResourceManager()
    retstr = StringIO()

    device = TextConverter(rsrcmgr, retstr, codec='utf-8', laparams=LAParams())
    interpreter = PDFPageInterpreter(rsrcmgr, device)

    with open(path, 'rb') as fp:
        for page in PDFPage.get_pages(fp, set()):
            interpreter.process_page(page)
        text = retstr.getvalue()

    device.close()
    retstr.close()

    return text

# 将数据读入内存在进行处理
url_data = requests.get("http://www.sse.com.cn/disclosure/bond/announcement/bookentry/c/2768799626348021.pdf").content

data = StringIO(url_data)
parser = PDFParser(data)
document = PDFDocument(parser)
rercmgr = PDFResourceManager(document)
retstr = StringIO()
laparams = LAParams()
codec = 'utf-8'
device = TextConverter(rercmgr, retstr, codec=codec, laparams=laparams)
interpreter = PDFPageInterpreter(rercmgr, device)
for page in PDFPage.create_pages(document):
    interpreter.process_page(page)
text = retstr.getvalue()


# 返回的text 就能普通字符串的处理提取信息了。

from hashlib

md = hashlib.md5()
md.update("字符串")
md5.hexdigest()

// 现在的问题是想要根据一个字典数据形成一个hash, 以使得可以判断字典数据没有完全一致的。

str = ("_".join("%s:%s" % (key, value) for key, value in dict_item.items() if key not in ("ct")) + "_" + str(number)).encode("utf-8")

md5.update(str)
md5.hexdigest()

coll_values.create_index([("md5_values", pymongo.ASCENDING)], unique=True)

query = [
    {
        "$match": {"key": code, "year": year, "type": type}
    },
    {
        "$group": {"_id": {"code": "$key", "year":"$year"}, "total": {"$sum":1}}
    }

]
total = []
for code in ["ACH", "IKGH", "ALN", "AMCN", "ATAI", "AXN", "ATV", "BIDU", "BITA", "BORN", "BSPM"]:
    for one in ["2011", '2012', '2013', '2014', "2015"]:
        A = Count(code=code, year=one, type="Annual", factor="Income Statement")
        result = A.aggregation()
        total.append(list(result))
pprint(total)

# 根据股票信息统计年份的数据数

import xlwt

wb = xlwt.Workbook()
ws = wb.add_sheet('A Test Sheet')

ws.write(0, 0, 1234.56)  # 第一行第一列写入123.56
ws.write(2, 0, 1)   # 第三行第一列写入 1
ws.write(2, 1, 1)   # 第三行第二列写入 1
ws.write(2, 2, xlwt.Formula("A3+B3"))  # 第三行第三列是前面值之和

wb.save('example.xls')  # 保存为文件名example.xls

// mongodb 实例

from pymongo import MongoClient
from xlwt import Workbook
from xlwt import easyxf  # 可以定义字体，颜色等样式


class MongoToXls(object):

    def __init__(self, collection, name):
        self.work_book = collection
        self.sheet_name = name
        self.wb = Workbook()
        self.ws = [self.wb.add_sheet(one) for one in self.sheet_name]
        self.style = easyxf("align: vert centre, horiz center")
        pass

    def info(self, number):
        self.contents = list(self.work_book[number].find())
        self.headers = [key for key in self.contents[0].keys()]
        rows = len(self.contents)
        columns = len(self.headers)
        return rows, columns

    def write_header(self, number):
        ws = self.ws[number]
        _, columns = self.info(number)
        for i in range(0, columns):
            ws.write(0, i, self.headers[i], style=self.style)

    def write_content(self, number):
        ws = self.ws[number]
        rows, columns = self.info(number)
        if rows >= 65536:
            rows = 65535
        for j in range(1, rows + 1):
            for k in range(0, columns):
                ws.write(j, k, str(self.contents[j - 1][self.headers[k]]), style=self.style)

    def save(self):
        name = "_".join(self.sheet_name) +"2"+ str(".xls")
        self.wb.save(str(name))

collection1 = MongoClient()["db5"]["base"]
collection2 = MongoClient()["db5"]["items"]
collection3 = MongoClient()["db5"]["values"]
collection = [collection1, collection2, collection3]
name = ["base", "items", "values"]

A = MongoToXls(collection=collection, name=name)
for number in range(len(collection)):
    print A.info(number)
    A.write_header(number)
    A.write_content(number)
A.save()