0

Author: injetlee

.gitignore

@@ -0,0 +1 @@
+/no_use

CpuToInfluxdb.py

@@ -0,0 +1,53 @@
+import psutil
+import os
+from influxdb import InfluxDBClient
+import time,math,random
+
+
+#获取当前运行的pid
+p1=psutil.Process(os.getpid()) 
+
+#打印本机的内存信息
+#print ('直接打印内存占用： '+(str)(psutil.virtual_memory))
+
+#打印内存的占用率
+
+
+
+
+
+
+from influxdb import InfluxDBClient
+import time,math,random
+while True:
+    # for i in range(360):
+  
+    #     sin = round(random.random()*1000,2)
+    #     print (sin)
+    a = psutil.virtual_memory().percent
+
+#本机cpu的总占用率
+    b = psutil.cpu_percent(interval=1.0)
+
+    json_body = [
+        {
+            "measurement": "cpu_load_short",
+            "tags": {
+                "host": "server01",
+                "region": "us-west"
+            },
+            #"time": "2009-11-10T23:00:00Z",
+            "fields": {
+                "cpu": b,
+                "mem": a
+            }
+        }
+    ]
+    client = InfluxDBClient('localhost', 8086, 'root', 'root', 'xxyyxx')
+    print('aaaaaa')
+    #client.create_database('xxyyxx',if_not_exists=False)
+    print('bbbbb')
+    client.write_points(json_body)
+    #result = client.query('select value from cpu_load_short;')
+    #print("Result: {0}".format(result))
+    time.sleep(2)

ModifyFilename.py

@@ -0,0 +1,10 @@
+import os
+dir = os.getcwd()
+subdir = os.listdir(dir)
+for i in subdir:
+	path = os.path.join(dir,i)
+	if os.path.isdir(path):
+	    end_dir = os.listdir(path)
+	    for i in range(len(end_dir)):
+	    	newname = end_dir[i][0:50]
+	    	os.rename(os.path.join(path,end_dir[i]),os.path.join(path,newname))

countFile.py

@@ -0,0 +1,16 @@
+import os
+result = []
+def get_all(cwd):
+    get_dir = os.listdir(cwd)  #遍历当前目录，获取文件列表
+    for i in get_dir:          
+        sub_dir = os.path.join(cwd,i)  # 把第一步获取的文件加入路径
+        if os.path.isdir(sub_dir):     #如果当前仍然是文件夹，递归调用
+            get_all(sub_dir)
+        else:
+            ax = os.path.basename(sub_dir)  #如果当前路径不是文件夹，则把文件名放入列表
+            result.append(ax)
+            print(len(result))   #对列表计数
+            
+if __name__ == "__main__": 
+    cur_path = os.getcwd()   #当前目录
+    get_all(cur_path)

countPm.py

@@ -0,0 +1,23 @@
+# -*- coding:utf-8 -*-
+def count_pm(*args):
+    alist = list([round(i*2-8,2) for i in args])  #计算三种颗粒浓度
+    result = []
+    for pm in alist:
+    	pm_abs = abs(pm)
+    	result.append(generate_iso_code(pm_abs))
+    print (result)
+    return result
+    	
+def generate_iso_code(x):
+	pm_value = [0.01,0.02,0.04,0.08,0.16,0.32,0.64,1.3,2.5,5,10,20,40,80]  #颗粒浓度
+	iso = list(range(1,25))   #iso级别，共24级
+	for i in range(len(pm_value)):           #for循环得到某个浓度范围的iso4006级别
+		if pm_value[i] < x <= pm_value[i+1]:
+			iso_code = iso[i]
+			break
+	return iso_code
+			
+if __name__ == '__main__':
+    count_pm(7.95,5.85,3.98)		
+    count_pm(7.918,5.949,5.456)	
+    count_pm(6.916,3.956,3.956)		

douban_book.py

@@ -0,0 +1,55 @@
+from bs4 import BeautifulSoup
+import requests
+from openpyxl import Workbook
+excel_name = "书籍.xlsx"
+wb = Workbook()
+ws1 = wb.active
+ws1.title='书籍'
+
+
+def get_html(url):
+    header = {
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:47.0) Gecko/20100101 Firefox/47.0'}
+    html = requests.get(url, headers=header).content
+    return html
+
+
+def get_con(html):
+    soup = BeautifulSoup(html,'html.parser')
+    book_list = soup.find('div', attrs={'class': 'article'})
+    page = soup.find('div', attrs={'class': 'paginator'})
+    next_page = page.find('span', attrs={'class': 'next'}).find('a')
+    name = []
+    for i in book_list.find_all('table'):
+        book_name = i.find('div', attrs={'class': 'pl2'})
+        m = list(book_name.find('a').stripped_strings)
+        if len(m)>1:
+            x = m[0]+m[1]
+        else:
+            x = m[0]
+        #print(x)
+        name.append(x)
+    if next_page:
+        return name, next_page.get('href')
+    else:
+        return name, None
+
+
+def main():
+    url = 'https://book.douban.com/top250'
+    name_list=[]
+    while url:
+        html = get_html(url)
+        name, url = get_con(html)
+        name_list = name_list + name
+    for i in name_list:
+        location = 'A%s'%(name_list.index(i)+1)
+        print(i)
+        print(location)
+        ws1[location]=i
+    wb.save(filename=excel_name)
+
+
+if __name__ == '__main__':
+    main()
+

douban_movie.py

@@ -0,0 +1,79 @@
+#!/usr/bin/env python
+# encoding=utf-8
+import requests,re
+import codecs
+from bs4 import BeautifulSoup
+from openpyxl import Workbook
+wb = Workbook()
+dest_filename = '电影.xlsx'
+ws1 = wb.active  
+ws1.title = "电影top250"
+
+DOWNLOAD_URL = 'http://movie.douban.com/top250/'
+
+
+def download_page(url):
+    """获取url地址页面内容"""
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.80 Safari/537.36'
+    }
+    data = requests.get(url, headers=headers).content
+    return data
+
+
+def get_li(doc):
+    soup = BeautifulSoup(doc, 'html.parser')
+    ol = soup.find('ol', class_='grid_view')
+    name = [] #名字
+    star_con = [] #评价人数
+    score = []  #评分
+    info_list = []  #短评
+    for i in ol.find_all('li'):
+        detail = i.find('div', attrs={'class': 'hd'})
+        movie_name = detail.find('span', attrs={'class': 'title'}).get_text() #电影名字
+        level_star = i.find('span',attrs={'class':'rating_num'}).get_text() #评分
+        star = i.find('div',attrs={'class':'star'})
+        star_num = star.find(text=re.compile('评价'))  #评价
+
+        info = i.find('span',attrs={'class':'inq'})  #短评
+        if info:     #判断是否有短评
+            info_list.append(info.get_text())
+        else:
+            info_list.append('无')
+        score.append(level_star)
+        
+
+        name.append(movie_name)
+        star_con.append(star_num)
+    page = soup.find('span', attrs={'class': 'next'}).find('a') #获取下一页
+    if page:
+        return name,star_con,score,info_list,DOWNLOAD_URL + page['href']
+    return name,star_con,score,info_list,None
+
+
+def main():
+    url = DOWNLOAD_URL
+    name = []
+    star_con=[]
+    score = []
+    info = []
+    while url:
+        doc = download_page(url)
+        movie,star,level_num,info_list,url = get_li(doc)
+        name = name + movie
+        star_con = star_con + star
+        score = score+level_num
+        info = info+ info_list
+    for (i,m,o,p) in zip(name,star_con,score,info):
+        col_A = 'A%s'%(name.index(i)+1)
+        col_B = 'B%s'%(name.index(i)+1)
+        col_C = 'C%s'%(name.index(i)+1)
+        col_D = 'D%s'%(name.index(i)+1)
+        ws1[col_A]=i
+        ws1[col_B] = m
+        ws1[col_C] = o
+        ws1[col_D] = p
+    wb.save(filename=dest_filename)
+
+if __name__ == '__main__':
+    main()

excelToDatabase.py

@@ -0,0 +1,32 @@
+from openpyxl import load_workbook
+import pymysql
+config = {
+	'host': '127.0.0.1',
+	'port':3306,
+	'user': 'root',
+	'password': 'root',
+	'charset': 'utf8mb4',
+	#'cursorclass': pymysql.cursors.DictCursor
+
+}
+conn = pymysql.connect(**config)
+conn.autocommit(1)
+cursor = conn.cursor()
+name = 'lyexcel'
+cursor.execute('create database if not exists %s' %name)
+conn.select_db(name)
+table_name = 'info'
+cursor.execute('create table if not exists %s(id MEDIUMINT NOT NULL AUTO_INCREMENT,name varchar(30),tel varchar(30),primary key (id))'%table_name)
+
+wb2 = load_workbook('hpu.xlsx')
+ws=wb2.get_sheet_names()
+for row in wb2:
+	print("1")
+	for cell in row:
+		value1=(cell[0].value,cell[4].value)
+		cursor.execute('insert into info (name,tel) values(%s,%s)',value1)
+
+print("overing...")
+# for row in A:
+# 	print(row)
+#print (wb2.get_sheet_names())

lagouSpider.py

@@ -0,0 +1,37 @@
+import requests
+from openpyxl import Workbook
+
+def get_json(url, page, lang_name):
+    data = {'first': 'true', 'pn': page, 'kd': lang_name}
+    json = requests.post(url, data).json()
+    list_con = json['content']['positionResult']['result']
+    info_list = []
+    for i in list_con:
+        info = []
+        info.append(i['companyShortName'])
+        info.append(i['companyName'])
+        info.append(i['salary'])
+        info.append(i['city'])
+        info.append(i['education'])
+        info_list.append(info)
+    return info_list
+
+
+def main():
+    lang_name = input('职位名：')
+    page = 1
+    url = 'http://www.lagou.com/jobs/positionAjax.json?needAddtionalResult=false'
+    info_result = []
+    while page < 31:
+        info = get_json(url, page, lang_name)
+        info_result = info_result + info
+        page += 1
+    wb = Workbook()
+    ws1 = wb.active
+    ws1.title = lang_name
+    for row in info_result:
+        ws1.append(row)
+    wb.save('职位信息.xlsx')
+
+if __name__ == '__main__':
+    main()

login_zhihu.py

@@ -0,0 +1,30 @@
+import requests,time
+from bs4 import BeautifulSoup
+url = 'https://www.zhihu.com/login/email'
+def get_captcha(data):
+    with open('captcha.gif','wb') as fb:
+        fb.write(data)
+    return input('captcha')
+
+def login(username,password,oncaptcha):
+    sessiona = requests.Session()
+    print(sessiona)
+    print('aaaa')
+    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:47.0) Gecko/20100101 Firefox/47.0'}
+    xyz = sessiona.get('https://www.zhihu.com/#signin',headers=headers).content
+    _xsrf = BeautifulSoup(sessiona.get('https://www.zhihu.com/#signin',headers=headers).content,'html.parser').find('input',attrs={'name':'_xsrf'}).get('value')
+    captcha_content = sessiona.get('https://www.zhihu.com/captcha.gif?r=%d&type=login'%(time.time()*1000),headers=headers).content
+    data = {
+        "_xsrf":_xsrf,
+        "email":username,
+        "password":password,
+        "remember_me":True,
+        "captcha":oncaptcha(captcha_content)
+    }
+    print(data)
+    resp = sessiona.post('https://www.zhihu.com/login/email',data,headers=headers).content
+    print(resp)
+    return resp 
+
+if __name__ == "__main__":
+    login('email','password',get_captcha)

readExcel.py

@@ -0,0 +1,17 @@
+from openpyxl import Workbook
+from openpyxl.compat import range
+from openpyxl.cell import get_column_letter
+wb = Workbook()
+dest_filename = 'empty_book2.xlsx'
+ws1 = wb.active              #第一个表
+ws1.title = "range names"    #第一个表命名
+#遍历第一个表的1到40行，赋值一个600内的随机数。
+for row in range(1,40):
+    ws1.append(range(60))
+ws2 = wb.create_sheet(title="Pi")
+ws2['F5'] = 3.14
+ws3 = wb.create_sheet(title="Data")
+for row in range(10,20):
+    for col in range(27,54):
+        _=ws3.cell(column=col,row=row,value="%s" % get_column_letter(col))
+wb.save(filename=dest_filename)