Python path configuration:

  PYTHONHOME = (not set)

  PYTHONPATH = (not set)

  program name = 'python'

  isolated = 0

  environment = 1

  user site = 1

  import site = 1

  sys._base_executable = '\u0158\x06'

  sys.base_prefix = '.'

  sys.base_exec_prefix = '.'

  sys.executable = '\u0158\x06'

  sys.prefix = '.'

  sys.exec_prefix = '.'

  sys.path = [

    'C:\\anaconda\\python38.zip',

    '.\\DLLs',

    '.\\lib',

    '',

  ]

Fatal Python error: init_fs_encoding: failed to get the Python codec of the filesystem encodin

Python runtime state: core initialized

ModuleNotFoundError: No module named 'encodings'



Current thread 0x000013a8 (most recent call first):

import datetime as dt

import tkinter as tk

# Linux 护眼程序

sec = 60 # 休息时间 秒



root = tk.Tk()

root.config(bg='black')

root.wm_attributes('-topmost',1)

root.wm_attributes('-fullscreen',1)

L = tk.Label(root,font=('Consolas', 50), bg='black')

L.place(relx=0.5,rely=0.5,anchor=tk.CENTER)



# 改变的内容

msg = "{}\n 站起来 {} \n 动一动 {}\n{}"

now = dt.datetime.now()

aa = {0:'↑',1:'→',2:'↓',3:'←'}

bb = {0:'~~_↑_~~',1:'~_↑ ↑_~'}





for i in range(sec):

    t = msg.format(sec-i,aa[i%4],bb[i%2],(now+dt.timedelta(seconds=i)).ctime())

    c = 'Black' # 颜色可以搞随机换

    root.after(i*1000,L.config,{'text':t,'fg':c})

    root.after(sec*1000,root.destroy)



root.mainloop()

 class Parent:



        def __init__(self):

            self.name='parent'

            self.age=10



        def run(self):

            if hasattr(self,'get_salary'):

                print('has func')

                print(self.get_salary())

    

class Child(Parent):



    def __init__(self):

        # self.name='child'

        Parent.__init__(self)

        self.salary=100





    def get_salary(self):

        return self.salary



obj = Child()

obj.run()

pip install pillow

# coding=utf-8

from PIL import Image

import math



key = 3.2# 修改key值可以调整国旗的范围，推荐2~4之间的数字，支持小数

motherland_flag = Image.open('flag-1024.png')

head_picture = Image.open('mmexport1663893338571.png')

# 截图国旗上的五颗五角星

flag_width, flag_height = motherland_flag.size

crop_flag = motherland_flag.crop((66, 0, flag_height+66, flag_height))

# 将国旗截图处理成颜色渐变

for i in range(flag_height):

    for j in range(flag_height):

            color = crop_flag.getpixel((i, j))

            distance = int(math.sqrt(i*i + j*j))

            alpha = 255 - int(distance//key)

            new_color = (*color[0:-1], alpha if alpha > 0 else 0)

            crop_flag.putpixel((i, j), new_color)

# 修改渐变图片的尺寸，适应头像大小，粘贴到头像上

new_crop_flag = crop_flag.resize(head_picture.size)

head_picture.paste(new_crop_flag, (0, 0), new_crop_flag)

# 保存自己的国旗头像

head_picture.save('国旗头像.png')

代码介绍：



导入需要使用的Python库，pillow库用于对图片进行截取、大小修改、粘贴等处理。math库用于计算像素点的距离。



使用Image.open()方法，读取准备好的国旗图片和头像图片到代码中。



对国旗图片进行截取，获取一张正方形的图片，截取时调整截取位置，保证5颗五角星完整展示在截图中。



crop()方法中传入的是一个(left, upper, right, lower)的元组，分别是截图的左、上、右、下像素位置。

将正方形国旗截图设置成透明度渐变的图片。国旗图片的模式默认是RGBA，本文需要的刚好是RGBA(red,green,blue,alpha)模式的图片，RGBA模式的图片颜色值是一个长度为4的元组，我们修改不同像素点的A值即可将图片设置成渐变。



本文是以国旗左上角为圆心，离圆心越远的像素点A值越小，像素点越透明。使用getpixel()和putpixel()两个方法来获取和重设像素点的颜色值，使用math.sqrt()计算像素点距离。



将渐变图片的大小转换成和头像的大小一样，然后粘贴到图片顶层。使用resize()方法重设图片大小，使用paste()方法粘贴图片。



保存图片，此时的微信头像图片上已经粘贴了透明渐变的国旗图片，微信国旗头像制作完成。

In [1]: import datetime, aniso8601, iso8601, isodate, dateutil.parser, arrow, ciso8601



In [2]: ds = u'2014-01-09T21:48:00.921000'



In [3]: %timeit ciso8601.parse_datetime(ds)

1000000 loops, best of 3: 204 ns per loop



In [4]: %timeit datetime.datetime.strptime(ds, "%Y-%m-%dT%H:%M:%S.%f")

100000 loops, best of 3: 15 µs per loop



In [5]: %timeit dateutil.parser.parse(ds)

10000 loops, best of 3: 122 µs per loop



In [6]: %timeit aniso8601.parse_datetime(ds)

10000 loops, best of 3: 28.9 µs per loop



In [7]: %timeit iso8601.parse_date(ds)

10000 loops, best of 3: 42 µs per loop



In [8]: %timeit isodate.parse_datetime(ds)

10000 loops, best of 3: 69.4 µs per loop



In [9]: %timeit arrow.get(ds).datetime

10000 loops, best of 3: 87 µs per loop

In [1]: import datetime, aniso8601, iso8601, isodate, dateutil.parser, arrow, ciso8601



In [2]: ds = u'2014-01-09T21:48:00.921000+05:30'



In [3]: %timeit ciso8601.parse_datetime(ds)

1000000 loops, best of 3: 525 ns per loop



In [4]: %timeit dateutil.parser.parse(ds)

10000 loops, best of 3: 162 µs per loop



In [5]: %timeit aniso8601.parse_datetime(ds)

10000 loops, best of 3: 36.8 µs per loop



In [6]: %timeit iso8601.parse_date(ds)

10000 loops, best of 3: 53.5 µs per loop



In [7]: %timeit isodate.parse_datetime(ds)

10000 loops, best of 3: 82.6 µs per loop



In [8]: %timeit arrow.get(ds).datetime

10000 loops, best of 3: 104 µs per loop

Even with time zone information, ciso8601 is 70x as fast as aniso8601.

Tested on Python 2.7.10 on macOS 10.12.6 using the following modules:

import datetime

import random

import sqlite3

import threading

import logging as log

import time



lock = threading.Lock()

class SQLiteDBCls:



    def __init__(self, cache=True):

        _type = ":memory:"



        self.db = sqlite3.connect(_type, check_same_thread=False)



        self.table_name = 'tick_data'



    def create_index(self):



        cmd = 'CREATE INDEX code_ix ON {} (current)'.format(self.table_name)

        with lock:

            try:



                cursor = self.db.cursor()

                cursor.execute(cmd)

            except Exception as e:

                log.info(e)

                self.db.rollback()

            else:

                self.db.commit()



    def create_table(self):

        # cursor = self.db.cursor()

        cmd = 'create table if not exists {} (id INTEGER PRIMARY KEY AUTOINCREMENT,code text,open double,current time)'.format(

            self.table_name)

        with lock:

            try:

                cursor = self.db.cursor()

                cursor.execute(cmd)

            except Exception as e:

                log.info(e)

                self.db.rollback()

            else:

                self.db.commit()



    def add(self, code, price, t):

        cmd = 'insert into {} (code,open,current) values (?,?,?);'.format(self.table_name)

        with lock:

            try:

                cursor = self.db.cursor()

                cursor.execute(cmd, (code, price, t))

            except Exception as e:

                log.info(e)

                self.db.rollback()

            else:

                self.db.commit()



    def batch_add(self, data):



        # 批量加入

        print('===========',threading.current_thread().getName())

        # log.info(threading.current_thread().getName())

        cmd = 'insert into {} (code,open,current) values (?,?,?)'.format(self.table_name)

        with lock:

            try:

                cursor = self.db.cursor()

                cursor.executemany(cmd, data)

            except Exception as e:

                log.info(e)

                self.db.rollback()

            else:

                self.db.commit()



    def result(self):

        cmd = 'select count(*) from `{}`'.format(self.table_name)



        with lock:



            try:

                cursor = self.db.cursor()

                cursor.execute(cmd)

            except Exception as e:

                log.info(e)

                self.db.rollback()

            else:

                return cursor.fetchone()



 

def data_gen():

    minute = 6000

    code = ['123011.SS','110010.SS','112111.SS']

    for i in range(minute):

        current = (datetime.datetime.now()+datetime.timedelta(minutes=i)).strftime('%H:%M:%D')

        data_list =

        for c in code:

            price = 5+random.random()+120

            data = (c,price,current)

            data_list.append(data)

        yield data_list

        # time.sleep(0.5)



app = SQLiteDBCls(cache=True)

app.create_table()

app.create_index()



def data_validation():

    print(app.result())

    app.sync_up()



def multithread_mode():

    total_count = 0

    thread_list = 

    for d in data_gen():

        print(d)

        total_count+=len(d)

        # app.batch_add(d)

        t=threading.Thread(target=app.batch_add,args=(d,))

        thread_list.append(t)

    for t in thread_list:

        t.start()



    for t in thread_list:

        t.join()



    print(total_count)





if __name__=='__main__':

    multithread_mode()

    data_validation()

File "/home/xda/miniconda3/envs/cpy/lib/python3.9/threading.py", line 910, in run

    self._target(*self._args, **self._kwargs)

  File "/home/xda/github/stock_strategy/sqlite_issue_debug.py", line 77, in batch_add

    self.db.commit()

Exception in thread Thread-3824:

Exception in thread Thread-3826:

Traceback (most recent call last):

  File "/home/xda/miniconda3/envs/cpy/lib/python3.9/threading.py", line 973, in _bootstrap_inner

sqlite3.OperationalError: cannot commit - no transaction is activeTraceback (most recent call last):

  File "/home/xda/github/stock_strategy/sqlite_issue_debug.py", line 72, in batch_add



    cursor.executemany(cmd, data)

sqlite3.InterfaceError: Error binding parameter 0 - probably unsupported type.

conn = pymysql.connect(host=host, port=port, user=user, password=password, db=db, charset='utf8',timeout=3)
 

原因：在setuptools 58之后的版本已经废弃了use_2to3

pip install setuptools==57.5.0

from baidu_collection import baidu_site_collect

from seo_info import crawl_info

from configure.settings import DBSelector

import datetime

import argparse



client = DBSelector().mongo('qq')

doc = client['db_parker']['seo']





def main():



    parser = argparse.ArgumentParser()

    '''

    Command line options

    '''

    parser.add_argument(

        '-n',

        '--name', type=str,

        help='input web domain'

    )



    parser.add_argument(

        '-f',

        '--file', type=str,

        help='input web site domain file name'

    )



    FLAGS = parser.parse_args()

    site_list=

    if FLAGS.name:

        print(FLAGS.name)

        if '.' in FLAGS.name:

            site_list.append(FLAGS.name)



    elif FLAGS.file:

        print(FLAGS.file)

        with open(FLAGS.file,'r') as fp:

            webs=fp.readlines()



        site_list.extend(list(map(lambda x:x.strip(),webs)))



    if site_list:



        run(site_list=site_list)

    else:

        print("please input correct web domain")





def run(site_list):



    # TODO： 改为命令行形式





    for site in site_list:

        count = baidu_site_collect(site)

        info = crawl_info(site)

        print(info)

        print(count)

        info['site'] = site

        info['baidu_count'] = count

        info['update_time'] = datetime.datetime.now()

        doc.insert_one(info)





if __name__ == '__main__':

    main()

from parsel import Selector

import requests



def baidu_site_collect(site):

    # 百度收录

    headers = {'User-Agent': 'Chrome Google FireFox IE'}

    url = 'https://www.baidu.com/s?wd=site:{}&rsv_spt=1&rsv_iqid=0xf8b7b7e50006c034&issp=1&f=8&rsv_bp=1&rsv_idx=2&ie=utf-8&tn=baiduhome_pg&rsv_enter=0&rsv_dl=ib&rsv_sug3=14&rsv_sug1=7&rsv_sug7=100&rsv_n=2&rsv_btype=i&inputT=8238&rsv_sug4=8238'.format(site)

    resp = requests.get(

        url=url,

        headers=headers

    )



    resp.encoding='utf8'

    html = resp.text

    selector = Selector(text=html)



    count = selector.xpath('//div[@class="op_site_domain c-row"]/div/p/span/b/text()').extract_first()

    if count:

        count=int(count.replace(',',''))

    return count



if __name__=='__main__':

    site='30daydo.com'

    print(baidu_site_collect(site))

import argparse

from atexit import register

import sys

import requests

import re

from parsel import Selector



#参数自定义



# parser = argparse.ArgumentParser()

# parser.add_argument('-r', dest='read', help='path file')

# parser.add_argument('-u',dest='read',help='targetdomain')

# parser_args = parser.parse_args()

#爬虫模块查询



VERBOSE = True



def askurl(target_url):

    headers = {

        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.106 Safari/537.36'

    }





    #baidu权重

    baidu_url=f"https://rank.chinaz.com/{target_url}"

    baidu_txt=requests.get(url=baidu_url,headers=headers)

    baidu_html=baidu_txt.content.decode('utf-8')

    baidu_PC=re.findall('PC端</i><img src="//csstools.chinaz.com/tools/images/rankicons/baidu(.*?).png"></a></li>',baidu_html,re.S)

    baidu_moblie=re.findall('移动端</i><img src="//csstools.chinaz.com/tools/images/rankicons/bd(.*?).png"></a></li>',baidu_html,re.S)

    #分割线

    print("*"*60)



    #如果查询html中有正则出来到权重关键字就输出，否则将不输出

    result={}



    baidu_pc_weight = None

    baidu_mobile_weight = None



    if len(baidu_PC) > 0:

        print('百度_PC:', baidu_PC[0])

        baidu_pc_weight=baidu_PC[0]

    if len(baidu_moblie) > 0:

        print('百度_moblie:', baidu_moblie[0])

        baidu_mobile_weight = baidu_moblie[0]

    else:

        print("百度无权重")



    result['baidu_pc_weight']=baidu_pc_weight

    result['baidu_mobile_weight']=baidu_mobile_weight



    #360权重

    url=f"https://rank.chinaz.com/sorank/{target_url}/"

    text = requests.get(url=url,headers=headers)

    html=text.content.decode('utf-8')

    sorank360_PC=re.findall('PC端</i><img src="//csstools.chinaz.com/tools/images/rankicons/360(.*?).png"></a><',html,re.S)

    sorank360_Mobile=re.findall('移动端</i><img src="//csstools.chinaz.com/tools/images/rankicons/360(.*?).png"',html,re.S)



    _360_pc_weight=None

    _360_mobile_weight=None



    # 如果查询html中有正则出来到权重关键字就输出，否则将不输出

    if len(sorank360_PC) > 0:

        _360_pc_weight=sorank360_PC[0]

        print("360_PC:", sorank360_PC[0])

    if len(sorank360_Mobile) > 0:

        _360_mobile_weight=sorank360_Mobile[0]

        print("360_moblie:", sorank360_Mobile[0])

    else:

        print("360无权重")



    result['360_pc_weight']=_360_pc_weight

    result['360_mobile_weight']=_360_mobile_weight





    #搜狗权重





    sogou_pc_weight=None

    sogou_mobile_weight=None



    sogou_url = f"https://rank.chinaz.com/sogoupc/{target_url}"

    sougou_txt = requests.get(url=sogou_url, headers=headers)

    sougou_html = sougou_txt.content.decode('utf-8')

    sougou_PC = re.findall('PC端</i><img src="//csstools.chinaz.com/tools/images/rankicons/sogou(.*?).png"></a></li>',sougou_html, re.S)

    sougou_mobile = re.findall('移动端</i><img src="//csstools.chinaz.com/tools/images/rankicons/sogou(.*?).png"></a></li>',sougou_html, re.S)



    # 如果查询html中有正则出来到权重关键字就输出，否则将不输出

    if len(sougou_PC) > 0:

        print('搜狗_PC：', sougou_PC[1])

        sogou_pc_weight=sougou_PC[1]

        

    if len(sougou_mobile) > 0 :

        print('搜狗_moblie：', sougou_mobile[1])

        sogou_mobile_weight=sougou_mobile[1]



    else:

        print('搜狗无权重')





    result['sogou_pc_weight']=sogou_pc_weight

    result['sogou_mobile_weight']=sogou_mobile_weight





    #神马权重

    shenma_pc_weight =None   

    shenma_url=f'https://rank.chinaz.com/smrank/{target_url}'

    shenma_txt=requests.get(url=shenma_url,headers=headers)

    shenma_html=shenma_txt.content.decode('utf-8')

    shenma_PC=re.findall('class="tc mt5"><img src="//csstools.chinaz.com/tools/images/rankicons/shenma(.*?).png"></a></li>',shenma_html,re.S)



    # 如果查询html中有正则出来到权重关键字就输出，否则将不输出

    if len(shenma_PC) > 0:

        print('神马权重为：', shenma_PC[1])

        shenma_pc_weight=shenma_PC[1]

    else:

        print("神马无权重")





    result['shenma_pc_weight']=shenma_pc_weight

    # result['shenma_mobile_weight']=None





    #头条权重



    toutiao_pc_weight=None

    toutiao_url=f'https://rank.chinaz.com/toutiao/{target_url}'

    toutiao_txt=requests.get(url=toutiao_url,headers=headers)

    toutiao_html=toutiao_txt.content.decode('utf-8')

    toutiao_PC=re.findall('class="tc mt5"><img src="//csstools.chinaz.com/tools/images/rankicons/toutiao(.*?).png"></a></li>',toutiao_html,re.S)



    # 如果查询html中有正则出来到权重关键字就输出，否则将不输出

    if len(toutiao_PC) > 0:

        print('头条权重为：', toutiao_PC[1])

        toutiao_pc_weight=toutiao_PC[1]

    else:

        print("头条无权重")



    result['toutiao_pc_weight']=toutiao_pc_weight

    # result['toutiao_mobile_weight']=None





    #备案信息、title、企业性质

    beian_url=f"https://seo.chinaz.com/{target_url}"

    beian_txt=requests.get(url=beian_url,headers=headers)

    beian_html=beian_txt.content.decode('utf-8')

    

    with open('beian_html.html','w') as fp:

        fp.write(beian_html)



    title,beian_no,name,ip,nature,register,years=parse_info(beian_html)

    

    result['name']=name

    result['title']=title

    result['beian_no']=beian_no

    result['ip']=ip

    result['nature']=nature

    result['register']=register

    result['years']=years





    try:

        print("备案信息:",beian_no,"名称:",name,"网站首页Title：",title,"企业性质：",nature,"IP地址为：",ip)

        print("*"*60)

    except:

        print("没有查询到有效信息！")



    return result



strip_fun = lambda x:x.strip() if x is not None else ""



def parse_info(html):



    resp = Selector(text=html)

    title = strip_fun(resp.xpath('//div[@class="_chinaz-seo-t2l ellipsis"]/text()').extract_first())

    table = resp.xpath('//table[@class="_chinaz-seo-newt"]/tbody')

    

    if table[0].xpath('.//tr[4]/td[2]/span[1]/i'):

        beian_num=strip_fun(table[0].xpath('.//tr[4]/td[2]/span[1]/i/a/text()').extract_first())

    else:

        beian_num=strip_fun(table[0].xpath('.//tr[4]/td[2]/span[1]/a/text()').extract_first())



    name=strip_fun(table[0].xpath('.//tr[4]/td[2]/span[2]/i/text()').extract_first())

    if not name:

        print('---->',name)

        name=strip_fun(table[0].xpath('.//tr[4]/td[2]/span[2]/i/a/text()').extract_first())



    nature=strip_fun(table[0].xpath('.//tr[4]/td[2]/span[3]/i/text()').extract_first())

    ip=strip_fun(table[0].xpath('.//tr[5]/td[2]/div/span[1]/i/a/text()').extract_first())

    register=strip_fun(table[0].xpath('.//tr[3]/td[2]/div[1]/span[1]/i/text()').extract_first())

    years=strip_fun(table[0].xpath('.//tr[3]/td[2]/div[2]/span[1]/i/text()').extract_first())







    return title,beian_num,name,ip,nature,register,years





def crawl_info(site):

    return askurl(site)



if __name__ == '__main__':

    main()

B站视频下载

自动批量下载B站一个系列的视频



下载某个UP主的所有视频



使用：



下载you-get库，git clone https://github.com/soimort/you-get.git 复制其本地路径，比如/root/you-get/you-get



初次运行，删除history.db 文件， 修改配置文件config.py



START=1 # 下载系列视频的 第一个

END=1 # 下载系列视频的最后一个 ， 比如一个系列教程有30个视频， start=5 ,end = 20 下载从第5个到第20个

ID='BV1oK411L7au' # 视频的ID

YOU_GET_PATH='/home/xda/othergit/you-get/you-get' # 你的you-get路径

MINS=1 # 每次循环等待1分钟

user_id = '518973111' # UP主的ID

total_page = 3 # up主的视频的页数

执行 python downloader.py ，进行下载循环



python people.py ，把某个up主的视频链接加入到待下载队列



python add_data.py --id=BV1oK411L7au --start=4 --end=8 下载视频id为BV1oK411L7au的系列教程，从第4开始，到第8个结束，如果只有一个的话，start和end设为1即可。



可以不断地往队列里面添加下载链接。

# @Time : 2019/1/28 14:19

# @File : youtube_downloader.py



import logging

import os

import subprocess

import datetime

import sqlite3

import time

from config import YOU_GET_PATH,MINS

CMD = 'python {} {}'

filename = 'url.txt'





class SQLite():

    def __init__(self):

        self.conn = sqlite3.connect('history.db')

        self.cursor = self.conn.cursor()

        self.create_table()



    def create_table(self):

        create_sql = 'create table if not exists tb_download (url varchar(100),status tinyint,crawltime datetime)'

        create_record_tb = 'create table if not exists tb_record (idx varchar(100) PRIMARY KEY,start tinyint,end tinyint,status tinyint)'

        self.cursor.execute(create_record_tb)

        self.conn.commit()

        self.cursor.execute(create_sql)

        self.conn.commit()



    def exists(self,url):

        querySet = 'select * from tb_download where url = ? and status = 1'

        self.cursor.execute(querySet,(url,))

        ret = self.cursor.fetchone()

        return True if ret else False



    def insert_history(self,url,status):

        query = 'select * from tb_download where url=?'

        self.cursor.execute(query,(url,))

        ret = self.cursor.fetchone()

        current = datetime.datetime.now()



        if ret:

            insert_sql='update tb_download set status=?,crawltime=? where url = ?'

            args=(status,status,current,url)

        else:

            insert_sql = 'insert into tb_download values(?,?,?)'

            args=(url,status,current)



        try:

            self.cursor.execute(insert_sql,args)

        except:

            self.conn.rollback()

            return False

        else:

            self.conn.commit()

            return True



    def get(self):

        sql = 'select idx,start,end from tb_record where status=0'

        self.cursor.execute(sql)

        ret= self.cursor.fetchone()

        return ret



    def set(self,idx):

        print('set status =1')

        sql='update tb_record set status=1 where idx=?'

        self.cursor.execute(sql,(idx,))

        self.conn.commit()



def llogger(filename):

    logger = logging.getLogger(filename)  # 不加名称设置root logger



    logger.setLevel(logging.DEBUG)  # 设置输出级别



    formatter = logging.Formatter(

        '[%(asctime)s][%(filename)s][line: %(lineno)d]\[%(levelname)s] ## %(message)s)',

        datefmt='%Y-%m-%d %H:%M:%S')



    # 使用FileHandler输出到文件

    prefix = os.path.splitext(filename)[0]

    fh = logging.FileHandler(prefix + '.log')

    fh.setLevel(logging.DEBUG)

    fh.setFormatter(formatter)



    # 使用StreamHandler输出到屏幕

    ch = logging.StreamHandler()

    ch.setLevel(logging.DEBUG)

    ch.setFormatter(formatter)



    # 添加两个Handler

    logger.addHandler(ch)

    logger.addHandler(fh)

    return logger





logger = llogger('download.log')

sql_obj = SQLite()



def run():

    while 1:

        result = sql_obj.get()

        print(result)

        if result:

            idx=result[0]

            start=result[1]

            end=result[2]

            try:

                download_bilibili(idx,start,end)

            except:

                pass

            else:

                sql_obj.set(idx)

        else:

            time.sleep(MINS*60)



def download_bilibili(id,start_page,total_page):

    global doc



    bilibili_url = 'https://www.bilibili.com/video/{}?p={}'

    for i in range(start_page, total_page+1):



        next_url = bilibili_url.format(id, i)

        if sql_obj.exists(next_url):

            print('have download')

            continue



        try:

            command = CMD.format(YOU_GET_PATH, next_url)

            p = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE,

                                 shell=True)



            output, error = p.communicate()



        except Exception as e:

            print('has execption')

            sql_obj.insert_history(next_url,status=0)

            logger.error(e)

            continue

        else:

            output_str = output.decode()

            if len(output_str) == 0:

                sql_obj.insert_history(next_url,status=0)

                logger.info('下载失败')

                continue



            logger.info('{} has been downloaded !'.format(next_url))

            sql_obj.insert_history(next_url,status=1)



run()

def update_data(id,start,end):

    status=0

    conn = sqlite3.connect('history.db')

    cursor = conn.cursor()

    insert_sql ='insert into tb_record values(?,?,?,?)'



    try:

        cursor.execute(insert_sql,(id,start,end,status))

    except Exception as e:

        print(e)

        print('Error')

    else:

        conn.commit()

        print("successfully insert")

bv_list = []

for i in range(1, total_page + 1):

    bv_list.extend(visit(i))

    print(bv_list)

map(lambda x:update_data(x,1,1),bv_list)

Python pandas.DataFrame.items用法及代码示例

用法:

DataFrame.items()

迭代(列名，系列)对。



遍历 DataFrame 列，返回一个包含列名和内容的元组作为一个系列。



生成(Yield)：

label：对象

被迭代的 DataFrame 的列名。



content：Series

属于每个标签的列条目，作为一个系列。



例子：

>>> df = pd.DataFrame({'species':['bear', 'bear', 'marsupial'],

...                   'population':[1864, 22000, 80000]},

...                   index=['panda', 'polar', 'koala'])

>>> df

        species   population

panda   bear      1864

polar   bear      22000

koala   marsupial 80000

>>> for label, content in df.items():

...     print(f'label:{label}')

...     print(f'content:{content}', sep='\n')

...

label:species

content:

panda         bear

polar         bear

koala    marsupial

Name:species, dtype:object

label:population

content:

panda     1864

polar    22000

koala    80000

Name:population, dtype:int64

# coding=utf-8

import os

import subprocess

import datetime

import json, pprint

import re, time

import threading

import random

import shutil





class FFmpeg:



    def __init__(self, editvdo, addlogo=None, addmusic=None,

                 addvdohead=None, addvdotail=None):

        self.editvdo = editvdo

        self.addlogo = addlogo

        self.addmusic = addmusic

        self.addvdohead = addvdohead

        self.addvdotail = addvdotail

        self.vdo_time, self.vdo_width, self.vdo_height, self.attr_dict = self.get_attr()

        self.editvdo_path = os.path.dirname(editvdo)

        self.editvdo_name = os.path.basename(editvdo)



    def get_attr(self):

        """

        获取视频属性参数

        :return:

        """

        strcmd = r'ffprobe -print_format json -show_streams -i "{}"'.format(self.editvdo)

        status, output = subprocess.getstatusoutput(strcmd)

        agrs = eval(re.search('{.*}', output, re.S).group().replace("\n", "").replace(" ", ''))

        streams = agrs.get('streams', )

        agrs_dict = dict()

        [agrs_dict.update(x) for x in streams]

        vdo_time = agrs_dict.get('duration')

        vdo_width = agrs_dict.get('width')

        vdo_height = agrs_dict.get('height')

        attr = (vdo_time, vdo_width, vdo_height, agrs_dict)

        return attr



    def edit_head(self, start_time, end_time, deposit=None):

        """

        截取指定长度视频

        :param second: 去除开始的多少秒

        :param deposit: 另存为文件

        :return: True/Flase

        """

        if None == deposit:

            deposit = self.editvdo_path+'/'+'edit_head'+self.editvdo_name

        start = time.strftime('%H:%M:%S', time.gmtime(start_time))

        end = time.strftime('%H:%M:%S', time.gmtime(end_time))

        strcmd = 'ffmpeg  -i "{}" -vcodec copy -acodec copy -ss {} -to {} "{}" -y'.format(

            self.editvdo, start, end, deposit)

        result = subprocess.run(args=strcmd, stdout=subprocess.PIPE, shell=True)

        if os.path.exists(deposit):

            os.remove(self.editvdo)

            os.rename(deposit, self.editvdo)

            return True

        else:

            return False



    def edit_logo(self, deposit=None):

        """

        添加水印

        :param deposit:添加水印后另存为路径，为空则覆盖

        :return: True/False

        """

        if None == deposit:

            deposit = self.editvdo_path+'/'+'edit_logo'+self.editvdo_name

        strcmd = r'ffmpeg -i "{}" -vf "movie=\'{}\' [watermark];[in] ' \

                 r'[watermark] overlay=main_w-overlay_w-10:10 [out]"  "{}"'.format(

                    self.editvdo, self.addlogo, deposit)

        result = subprocess.run(args=strcmd, stdout=subprocess.PIPE, shell=True)

        if os.path.exists(deposit):

            os.remove(self.editvdo)

            os.rename(deposit, self.editvdo)

            return True

        else:

            return False



    def edit_music(self, deposit=None):

        if None == deposit:

            deposit = self.editvdo_path+'/'+'edit_music'+self.editvdo_name

        strcmd = r'ffmpeg -y -i "{}" -i "{}" -filter_complex "[0:a] ' \

                 r'pan=stereo|c0=1*c0|c1=1*c1 [a1], [1:a] ' \

                 r'pan=stereo|c0=1*c0|c1=1*c1 [a2],[a1][a2]amix=duration=first,' \

                 r'pan=stereo|c0<c0+c1|c1<c2+c3,pan=mono|c0=c0+c1[a]" ' \

                 r'-map "[a]" -map 0:v -c:v libx264 -c:a aac ' \

                 r'-strict -2 -ac 2 "{}"'.format(self.editvdo, self.addmusic, deposit)

        result = subprocess.run(args=strcmd, stdout=subprocess.PIPE, shell=True)

        if os.path.exists(deposit):

            os.remove(self.editvdo)

            os.rename(deposit, self.editvdo)

            return True

        else:

            return False



    def edit_rate(self, rete=30, deposit=None):

        """

        改变帧率

        :param rete: 修改大小帧率

        :param deposit: 修改后保存路径

        :return:

        """

        if None == deposit:

            deposit = self.editvdo_path+'/'+'edit_music'+self.editvdo_name

        strcmd = r'ffmpeg -i "{}" -r {} "{}"' % (self.editvdo, rete, deposit)

        result = subprocess.run(args=strcmd, stdout=subprocess.PIPE, shell=True)

        if os.path.exists(deposit):

            os.remove(self.editvdo)

            os.rename(deposit, self.editvdo)

            return True

        else:

            return False



    def edit_power(self, power='1280x720', deposit=None):

        """

        修改分辨率

        :param power: 分辨率

        :param deposit: 修改后保存路径，为空则覆盖

        :return:

        """

        if None == deposit:

            deposit = self.editvdo_path+'/'+'edit_power'+self.editvdo_name

        strcmd = r'ffmpeg -i "{}" -s {} "{}"'.format(self.editvdo, power, deposit)

        result = subprocess.run(args=strcmd, stdout=subprocess.PIPE, shell=True)

        if os.path.exists(deposit):

            os.remove(self.editvdo)

            os.rename(deposit, self.editvdo)

            return True

        else:

            return False



    def rdit_marge(self, vdo_head, vdo_tail, deposit=None):

        if None == deposit:

            deposit = self.editvdo_path+'/'+'rdit_marge'+self.editvdo_name

        with open(self.editvdo_path+'/'+'rdit_marge.txt', 'w', encoding='utf-8') as f:

            f.write("file '{}' \nfile '{}' \nfile '{}'" .format(

                vdo_head, self.editvdo, vdo_tail))

        strcmd = r'ffmpeg -f concat -safe 0 -i "{}" -c copy "{}"'.format(

            self.editvdo_path + '/' + 'rdit_marge.txt', deposit)

        result = subprocess.run(args=strcmd, stdout=subprocess.PIPE, shell=True)

        if os.path.exists(deposit):

            os.remove(self.editvdo)

            os.rename(deposit, self.editvdo)

            return True

        else:

            return False







    # ffmpeg - i input.mkv - filter_complex "[0:v]setpts=0.5*PTS[v];[0:a]atempo=2.0[a]" - map"[v]" - map"[a]"  output.mkv







test = FFmpeg(r"D:\vdio\4.mp4")

ooking in indexes: https://pypi.douban.com/simple

Collecting demjson==2.2.4

  Downloading https://pypi.doubanio.com/pack ... ar.gz (131 kB)

     |████████████████████████████████| 131 kB 985 kB/s

    ERROR: Command errored out with exit status 1:

     command: /root/miniconda3/envs/py37/bin/python -c 'import io, os, sys, setuptools, tokenize; sys.argv[0] = '"'"'/tmp/pip-install-pj0ajcpl/demjson_86a1bab6643c4ed7a7b0c6bb6d3a43a2/setup.py'"'"'; __file__='"'"'/tmp/pip-install-pj0ajcpl/demjson_86a1bab6643c4ed7a7b0c6bb6d3a43a2/setup.py'"'"';f = getattr(tokenize, '"'"'open'"'"', open)(__file__) if os.path.exists(__file__) else io.StringIO('"'"'from setuptools import setup; setup()'"'"');code = f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, __file__, '"'"'exec'"'"'))' egg_info --egg-base /tmp/pip-pip-egg-info-7ve4tu87

         cwd: /tmp/pip-install-pj0ajcpl/demjson_86a1bab6643c4ed7a7b0c6bb6d3a43a2/

    Complete output (3 lines):

    /root/miniconda3/envs/py37/lib/python3.7/site-packages/setuptools/dist.py:760: UserWarning: Usage of dash-separated 'index-url' will not be supported in future versions. Please use the underscore name 'index_url' instead

      % (opt, underscore_opt)

    error in demjson setup command: use_2to3 is invalid.

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

# @Time : 2022/4/6 4:41

# @File : database_migrate.py

# @Author : Rocky C@www.30daydo.com

import time

from loguru import logger

import pymongo



ignore_db = ['admin', 'config', 'local',

             ] # 忽略更新的库



ignore_col = [('db_stock','dfcf_list_full')]



logger.add('mongo.log')



#  数据库同步

def get_client(user, password, host, port):

    connect_uri = f'mongodb://{user}:{password}@{host}:{port}'

    client = pymongo.MongoClient(connect_uri)

    return client





def origin():

    return get_client('admin', 'password', '127.0.0.1', '27017')





def target():

    return get_client('root', 'password', '127.0.0.1', '27017')





def transfer():

    origin_client = origin()

    target_client = target()

    dbs = get_db_name(origin_client)

    for db in dbs:

        for col in get_collection_name(origin_client, db):



            if (db,col) in ignore_col:

                continue

            items = []

            logger.info(f'正在更新{db} {col}')

            for i in get_item(origin_client, db, col):

                items.append(i)



            insert_item(target_client, db, col, items)

            logger.info(f'更新数据库 {db} {col}')

            # time.sleep(0.5)



def get_item(client, db_name, col):

    return client[db_name][col].find()







def insert_item(client, db_name, col, data):

    batch = 1000

    count = len(data)//batch + 1

    for i in range(count):

        item = data[i*batch:(i+1)*batch]



        if len(item)==0:

            continue



        try:

            client[db_name][col].insert_many(item)

        except Exception as e:

            logger.error(e)

            logger.error(f'{db_name} {col} 插入出错')





def get_db_name(client):

    db_name = client.list_database_names()

    dbs = []

    for db in db_name:

        if db not in ignore_db:

            dbs.append(db)

    return dbs



def delete_col(client,db,col):

    try:

        client[db][col].delete_many({})

    except Exception as e:

        logger.error(e)

        logger.error(db)

        logger.error(col)

        return False

    else:

        return True



def server_compare():

    '''

    比较2个数据库是否相同，只是单纯比较条数

    '''

    origin_client = origin()

    target_client = target()

    dbs = get_db_name(origin_client)



    for db in dbs:

        for col in get_collection_name(origin_client, db):

            origin_count = origin_client[db][col].count_documents({})

            target_count = target_client[db][col].count_documents({})

            if origin_count!=target_count:

                logger.info(f'collection {db} {col}有区别')

                #

                if delete_col(target_client,db,col):

                    items = []

                    logger.info(f'正在更新{db} {col}')

                    for i in get_item(origin_client, db, col):

                        items.append(i)



                    insert_item(target_client, db, col, items)

                    logger.info(f'更新数据库 {db} {col}')

                    time.sleep(1)









def get_collection_name(client, db_name):

    collection_names = client[db_name].list_collection_names(session=None)

    return collection_names



def main():

    server_compare()



if __name__ == '__main__':

    main()

  File "C:\anaconda\lib\site-packages\Crypto\Cipher\__init__.py", line 77, in _create_cipher

    raise TypeError("IV is not meaningful for the ECB mode")

TypeError: IV is not meaningful for the ECB mode

UnicodeDecodeError: 'utf-8' codec can't decode byte 0xe4 in position 1: invalid continuation byte

c=b'\x1e\xe4\xd5\x97\x9a#\x99kC\xadD\x7f\x9a\xc2G\x92'

b.decode('utf8',errors='replace')

failed to start INotebook in kernel, UI Disabled = false s [Error]: Unable to start Kernel 'base (Python 3.8.3)' due to connection timeout.  View Jupyter [log](command:jupyter.viewOutput) for further detail

pip install traitlets==4.3.3

from qiniu import Auth, put_file,BucketManager,build_batch_delete

import os

import fire



access_key = os.getenv('qiniu_access_key')

secret_key = os.getenv('qiniu_secret_key')



bucket_name = '' # 你的空间名称



HOST ='[url]http://xximg.xxx.com/{}'[/url]  # 可以不用填



TEMPLATE = '\n![{}]({})\n\n\n'



def upload(file,category=''):



    #构建鉴权对象

    q = Auth(access_key, secret_key)

    #要上传的空间



    #上传后保存的文件名

    key = category +'/' + os.path.split(file)[1]

    #生成上传 Token，可以指定过期时间等

    token = q.upload_token(bucket_name, key) # 永不过期



    #要上传文件的本地路径

    ret, info = put_file(token, key, file, version='v1') 

    print(ret)

    print(info)

    return HOST.format(ret['key'])



def bulk_upload(path,category=''):

    with open('qiniu_image.md','a+') as fp:

        for file in os.listdir(path):

            full_path = os.path.join(path,file)

            if os.path.isfile(full_path):



                host_url = upload(full_path,category)

                fp.write(TEMPLATE.format(host_url,host_url))





def get_file_info(prefix,limit = 10):

    q = Auth(access_key, secret_key)

    bucket = BucketManager(q)



    delimiter = None

    marker = None

    ret, eof, info = bucket.list(bucket_name, prefix, marker, limit, delimiter)



    # assert len(ret.get('items')) is not None

    url_list=[]

    for item in ret.get('items',):

        url_list.append(item['key'])

    # print(url_list)

    # print(len(url_list))

    return url_list,len(url_list)



def bulk_delete(prefix,limit=None):

    url_list,lens = get_file_info(prefix,limit=limit)

    q = Auth(access_key, secret_key)

    bucket = BucketManager(q)

    ops = build_batch_delete(bucket_name, url_list)

    ret, info = bucket.batch(ops)

    print(info)

    print(ret)



def delete_one(key):

    q = Auth(access_key, secret_key)

    #初始化BucketManager

    bucket = BucketManager(q)

    #你要测试的空间， 并且这个key在你空间中存在

    # key = 'python-logo.png'

    #删除bucket_name 中的文件 key

    ret, info = bucket.delete(bucket_name, key)

    print(info)

    print(ret)

    # assert ret == {}





def bulk_delete_ones(prefix):

    url_list,lens = get_file_info(prefix,limit=10)

    for url in url_list:

        delete_one(url)

        # print(url)



def main(path,category):



    if os.path.isdir(path):



         bulk_upload(path,category)

    elif os.path.isfile(path):

         upload(path,category)

    else:

         raise ValueError('文件不存在')



    get_file_info()

    bulk_delete('resource')

    bulk_delete_ones('resource')

    delete_one('resource/data_beauty.png')



if __name__ == '__main__':

    fire.Fire(main)

import pyecharts.options as opts

from pyecharts.charts import Bar, Line



x_data = ["1月", "2月", "3月", "4月", "5月", "6月", "7月", "8月", "9月", "10月", "11月", "12月"]



bar = (

    Bar(init_opts=opts.InitOpts(width="1600px", height="800px"))

    .add_xaxis(xaxis_data=x_data)

    .add_yaxis(

        series_name="蒸发量",

        y_axis=[

            2.0,

            4.9,

            7.0,

            23.2,

            25.6,

            76.7,

            135.6,

            162.2,

            32.6,

            20.0,

            6.4,

            3.3,

        ],

        label_opts=opts.LabelOpts(is_show=False),

    )

    .add_yaxis(

        series_name="降水量",

        y_axis=[

            2.6,

            5.9,

            9.0,

            26.4,

            28.7,

            70.7,

            175.6,

            182.2,

            48.7,

            18.8,

            6.0,

            2.3,

        ],

        label_opts=opts.LabelOpts(is_show=False),

    )

    .extend_axis(

        yaxis=opts.AxisOpts(

            name="温度",

            type_="value",

            min_=0,

            max_=25,

            interval=5,

            axislabel_opts=opts.LabelOpts(formatter="{value} °C"),

        )

    )

    .set_global_opts(

        tooltip_opts=opts.TooltipOpts(

            is_show=True, trigger="axis", axis_pointer_type="cross"

        ),

        xaxis_opts=opts.AxisOpts(

            type_="category",

            axispointer_opts=opts.AxisPointerOpts(is_show=True, type_="shadow"),

        ),

        yaxis_opts=opts.AxisOpts(

            name="水量",

            type_="value",

            min_=0,

            max_=250,

            interval=50,

            axislabel_opts=opts.LabelOpts(formatter="{value} ml"),

            axistick_opts=opts.AxisTickOpts(is_show=True),

            splitline_opts=opts.SplitLineOpts(is_show=True),

        ),

    )

)

line = (

    Line()

    .add_xaxis(xaxis_data=x_data)

    .add_yaxis(

        series_name="平均温度",

        yaxis_index=1,

        y_axis=[2.0, 2.2, 3.3, 4.5, 6.3, 10.2, 20.3, 23.4, 23.0, 16.5, 12.0, 6.2],

        label_opts=opts.LabelOpts(is_show=False),

    )

)

bar.overlap(line).render_notebook()

auth = pika.PlainCredentials(user,password)

connection = pika.BlockingConnection(pika.ConnectionParameters(host,port,'/',auth))

auth = pika.PlainCredentials(user,password)

connection = pika.BlockingConnection(pika.ConnectionParameters(host=host,port=port,virtual_host='/',credentials=auth))

 tickerBond  closePriceBond  bondPremRatio secShortNameBond tickerEqu  \

secID                                                                         

110066     110066          199.94        -1.2442             盛屯转债    600711   

110067     110067          119.53        25.9204             华安转债    600909   

113021     113021          105.81        45.0989             中信转债    601998   

113024     113024          101.94        36.6668             核建转债    601611   

113025     113025          129.16         0.0409             明泰转债    601677

        ROE tickerEqu

0  2.642931    600711

1  4.425438    600909

2  6.259092    601998

3  4.432315    601611

4  6.454054    601677

先 df1 = df1.reset_index()，合并之后再把 secID 那一列设为 index 。

    ERROR: Command errored out with exit status 1:

     command: 'C:\anaconda\python.exe' -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'C:\\Users\\xda\\AppData\

\Local\\Temp\\pip-install-ftotbzih\\peewee\\setup.py'"'"'; __file__='"'"'C:\\Users\\xda\\AppData\\Local\\Temp\\pip-insta

ll-ftotbzih\\peewee\\setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(__file__);code=f.read().replace('"'"'\r\n'"

'"', '"'"'\n'"'"');f.close();exec(compile(code, __file__, '"'"'exec'"'"'))' egg_info --egg-base 'C:\Users\xda\AppData\Lo

cal\Temp\pip-pip-egg-info-8ou7yi3i'

         cwd: C:\Users\xda\AppData\Local\Temp\pip-install-ftotbzih\peewee\

    Complete output (15 lines):

    Traceback (most recent call last):

      File "<string>", line 1, in <module>

      File "C:\Users\xda\AppData\Local\Temp\pip-install-ftotbzih\peewee\setup.py", line 99, in <module>

        elif not _have_sqlite_extension_support():

      File "C:\Users\xda\AppData\Local\Temp\pip-install-ftotbzih\peewee\setup.py", line 76, in _have_sqlite_extension_su

pport

        compiler.compile([src_file], output_dir=tmp_dir),

      File "C:\anaconda\lib\distutils\_msvccompiler.py", line 327, in compile

        self.initialize()

      File "C:\anaconda\lib\distutils\_msvccompiler.py", line 224, in initialize

        vc_env = _get_vc_env(plat_spec)

      File "C:\anaconda\lib\site-packages\setuptools\msvc.py", line 314, in msvc14_get_vc_env

        return _msvc14_get_vc_env(plat_spec)

      File "C:\anaconda\lib\site-packages\setuptools\msvc.py", line 273, in _msvc14_get_vc_env

        out = subprocess.check_output(

    AttributeError: 'str' object has no attribute 'decode'

    ----------------------------------------

ERROR: Command errored out with exit status 1: python setup.py egg_info Check the logs for full command output.

        out = subprocess.check_output(

            'cmd /u /c "{}" {} && set'.format(vcvarsall, plat_spec),

            stderr=subprocess.STDOUT,

        )

        # ).decode('utf-16le', errors='replace')

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

# @Time : 2021/4/24 20:50

# @File : baidu_voice_service.py

# @Author : Rocky C@www.30daydo.com



import os

import requests

import sys

import pickle

sys.path.append('..')

from config import API_KEY,SECRET_KEY

from base64 import b64encode

from pathlib import PurePath





BASE = PurePath(__file__).parent



# 需要识别的文件

AUDIO_FILE = r'C:\OtherGit\speech-demo\rest-api-asr\python\audio\2.m4a'  # 只支持 pcm/wav/amr 格式，极速版额外支持m4a 格式

# 文件格式

FORMAT = AUDIO_FILE[-3:]  # 文件后缀只支持 pcm/wav/amr 格式，极速版额外支持m4a 格式



CUID = '24057753'

# 采样率

RATE = 16000  # 固定值





ASR_URL = 'http://vop.baidu.com/server_api'



#测试自训练平台需要打开以下信息， 自训练平台模型上线后，您会看见 第二步：“”获取专属模型参数pid:8001，modelid:1234”，按照这个信息获取 dev_pid=8001，lm_id=1234

'''

http://vop.baidu.com/server_api

1537	普通话(纯中文识别)	输入法模型	有标点	支持自定义词库

1737	英语	英语模型	无标点	不支持自定义词库

1637	粤语	粤语模型	有标点	不支持自定义词库

1837	四川话	四川话模型	有标点	不支持自定义词库

1936	普通话远场

'''

DEV_PID = 1737



SCOPE = 'brain_enhanced_asr'  # 有此scope表示有asr能力，没有请在网页里开通极速版





class DemoError(Exception):

    pass





TOKEN_URL = 'http://openapi.baidu.com/oauth/2.0/token'



def fetch_token():



    params = {'grant_type': 'client_credentials',

              'client_id': API_KEY,

              'client_secret': SECRET_KEY}

    r = requests.post(

        url=TOKEN_URL,

        data=params

    )



    result = r.json()

    if ('access_token' in result.keys() and 'scope' in result.keys()):

        if SCOPE and (not SCOPE in result['scope'].split(' ')):  # SCOPE = False 忽略检查

            raise DemoError('scope is not correct')



        return result['access_token']



    else:

        raise DemoError('MAYBE API_KEY or SECRET_KEY not correct: access_token or scope not found in token response')





"""  TOKEN end """



def dump_token(token):

    with open(os.path.join(BASE,'token.pkl'),'wb') as fp:

        pickle.dump({'token':token},fp)



def load_token(filename):



    if not os.path.exists(filename):

        token=fetch_token()

        dump_token(token)

        return token

    else:

        with open(filename,'rb') as fp:

            token = pickle.load(fp)

            return token['token']



def recognize_service(token,filename):



    with open(filename, 'rb') as speech_file:

        speech_data = speech_file.read()



    length = len(speech_data)

    if length == 0:

        raise DemoError('file %s length read 0 bytes' % AUDIO_FILE)



    b64_data = b64encode(speech_data)

    params = {'cuid': CUID, 'token': token, 'dev_pid': DEV_PID,'speech':b64_data,'len':length,'format':FORMAT,'rate':RATE,'channel':1}



    headers = {

        'Content-Type':'application/json',

    }

    r = requests.post(url=ASR_URL,json=params,headers=headers)

    return r.json()





def main():

    filename = 'token.pkl'

    token = load_token(filename)

    result = recognize_service(token,AUDIO_FILE)

    print(result['result'])



if __name__ == '__main__':

    main()

find . -type f -name "*.py" | xargs grep "redis"

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

# @Time : 2021/4/14 1:46

# @File : search_string_in_folder.py

# @Author : Rocky C@www.30daydo.com



'''

搜索代码脚本

'''

import fire

import glob

import re



# TODO 用PYQT重写一个



PATH_LIST = [r'C:\git\\',r'C:\OtherGit\\',r'C:\OneDrive\viewed_code\\']

POST_FIX = 'py' # 后缀文件

# 关键词

WORDS=[]



EXCLUDE_PATH=[r'C:\OtherGit\cpython']



DEBUG = True



class FileSearcher:



    def __init__(self,kw):

        self.root_path_list = PATH_LIST

        self.default_coding ='utf-8'

        self.exception_handle_coding='gbk'

        self.kw=[]

        if not isinstance(kw,tuple):

            kw=(kw,)



        for k in kw:

            k=k.strip()

            self.kw.append(k)



    def search(self,file,encoding):

        match_dict = dict()



        for w in self.kw:

            match_dict.setdefault(w, False)



        line_number = 0

        line_list=list()

        with open(file, 'r', encoding=encoding) as fp:



            while 1:

                try:

                    line = fp.readline()



                except UnicodeDecodeError as e:



                    if DEBUG:

                        print(f'Error coding in file {file}')

                        print(e)



                    return None,None,None



                except Exception as e:

                    if DEBUG:

                        print(f'Error in file {file}')

                        print(e)

                    break



                if not line:

                    break



                line = line.strip()

                if not line:

                    continue



                for w in self.kw:

                    m=re.search(w,line,re.IGNORECASE)

                    if m:

                        match_dict.update({w:True})

                        line_list.append(line_number)



                line_number+=1



        return True,match_dict.copy(),line_list.copy()



    def print_match_result(self,file,line_list,encoding):



        with open(file, 'r', encoding=encoding) as fp:

            line_number = 0

            while 1:

                try:

                    line = fp.readline()

                except Exception as e:

                    if DEBUG:

                        print(f'Error in file {file}')

                        print(e)

                    break



                if not line:

                    break

                line=line.strip()



                if not line:

                    continue



                if line_number in line_list:

                    print(f'{file} :: {line_number} ====>\n {line[:50]}\n')



                line_number += 1



    def run(self):

        for path in self.root_path_list:



            search_path=path+'**/*.'+POST_FIX



            for file in glob.iglob(search_path,recursive=True):



                for ex_path in EXCLUDE_PATH:

                    ex_path=ex_path.replace('\\','')

                    temp_file=file.replace('\\','')

                    if ex_path in temp_file:

                        continue



                    use_encoding=self.default_coding

                    encode_proper,match_dict,line_list=self.search(file,use_encoding)



                    if not encode_proper:

                        use_encoding = self.exception_handle_coding

                        encode_proper,match_dict,line_list=self.search(file, use_encoding)



                    if match_dict is not None and len(match_dict)>0 and all(match_dict.values()):

                        # print(match_dict.values())

                        self.print_match_result(file,line_list,use_encoding)

                        # print(line_list)





def test_error_file():

    path=r'C:\git\CodePool\example-code\19-dyn-attr-prop\oscon\schedule2.py'

    with open(path,'r',encoding='utf8') as fp:

        while 1:

            x=fp.readline()

            if not x:

                break

            print(x)



def main(kw):

    app = FileSearcher(kw)

    app.run()



if __name__ == '__main__':

    fire.Fire(main)