My note

"""Count words."""

def count_words(s, n):
    """Return the n most frequently occuring words in s."""
    words = s.split(" ")
    # TODO: Count the number of occurences of each word in s
    counters = {}
    for word in words:
        if word in counters:
            counters[word] += 1
        else:
            counters[word] = 1
    # TODO: Sort the occurences in descending order (alphabetically in case of ties)
    top = sorted(counters.iteritems(), key=lambda d:(-d[1],d[0]))
    ##lambda中"-"为反序，意思是先把单词出现次数从大到小排列，
    ##然后再以单词的字母从小到大排列
    # TODO: Return the top n words as a list of tuples (<word>, <count>)
    top_n = top[:n]##返回前n个单词
    return top_n

def test_run():
    """Test count_words() with some inputs."""
    print count_words("cat bat mat cat bat cat", 3)
    print count_words("betty bought a bit of butter but the butter was bitter", 3)

if __name__ == "__main__":
    test_run()

from selenium import webdriver
browser = webdriver.Chrome()

browser.get("http://www.baidu.com")
browser.find_element_by_id("kw").send_keys("selenium")
browser.find_element_by_id("su").click()
browser.quit()

#coding=utf-8
#encoding=utf-8
import re
import requests
import json
import urllib 
def valifile(name):
    rstr = r"[/\:*?"<>|]"  # ';/:*?"<>|';
    valiname = re.sub(rstr, "", name)
    return valiname

def getkjlimages():
	for i in range(0,1000000):
		print(i)
		i = str(i*6)
		surl = ';http://yun.kujiale.com/api/openfps?query=beijing&amp;start=';+i+';&amp;num=6';
		ret=requests.get(url=surl) 
		ret.encoding=';utf-8';
		kjl = json.loads(ret.text)
		for j in range(0,49):
			itmes = kjl[';obsExFps';][j]
			name = json.dumps(itmes[';name';])[1:-1].decode("unicode-escape")
			src = json.dumps(itmes[';pics';])[1:-1]
			##name和src后面加了[1:-1]的原因是json数据中包含了前后两个引号,要将其去掉
			print(';img_src=';+json.dumps(itmes[';pics';]))
			img = urllib.urlopen(src).read()
			f = file(';imgs/';+validateTitle(name)+';.jpg';,"wb")
			f.write(img)
			f.close
getkjlimages()

def valifile(name):
    rstr = r"[/\:*?"<>|]"  # ';/:*?"<>|';
    valiname = re.sub(rstr, "", name)
    return valiname

#coding=utf-8
#encoding=utf-8
import re
import requests
import MySQLdb
import hashlib
from pyquery import PyQuery as pyq
def md5(text):
    m = hashlib.md5()
    m.update(text.encode('utf-8'))
    return m.hexdigest()

def getandupload():
	conn=MySQLdb.connect(host='localhost',user='root',passwd='',port=3306,charset='utf8')
	cur=conn.cursor()
	conn.select_db('pytest')
	ret=requests.get(url="http://jc.bjmemc.com.cn/IndexAirReport/AirDailyReport.aspx") 
	doc=pyq(ret.text)
	date = re.findall(r'(w*[0-9]+)w*',doc.find('#Label0').text())
	#正则,将数字提取出来(为了将yyyy年mm月dd日改成yyyy/mm/dd)
	date = date[0]+'/'+date[1]+'/'+date[2]
	table = pyq(pyq(doc.find('#marqueebox')).find('table'))
	stations = re.findall(r'<td style="width:126px">(.+?)</td>',table.html())
	aqis = re.findall(r'<td style="width:90px">(.+?)</td>',table.html())
	#通过正则将html代码中需要的数据提取出来并存在数组中.
	for i in range(0, 35):
		value=[md5(date+stations[i][1:]),date,stations[i][1:],aqis[2*i]]
		cur.execute('insert ignore into aqi_bjmemc values(%s,%s,%s,%s)',value)
	        #设置了md5id为主键,因此当传重复数据的时候md5id重复,避免了重复上传数据.
	conn.commit()
	cur.close()
	conn.close()
getandupload()

import os
import time
#对于时间进行处理需要引入time

def importcsv(filename,outfilename):
    print(filename)
    filenamerow = filename.split('-')
    filenamerow[2] = filenamerow[2][:-4]
    date = filenamerow[1]
    type = filenamerow[2]
    lctime = 1325347200.0
    #设定一个时间戳，对应的是某一天的00:00
    g=file(type+ '-' +date+ '.csv','w+')
    with open(filename, 'r') as f:
        line = f.readline()
        while line:
            line = line.replace('n','')
            line = line.replace('r','')
            line = line + ',,'
            row = line.split(',')
            row[2] = row[0]
            x = time.localtime(lctime)
            #对时间戳进行处理,得到
            #time.struct_time(tm_year=2012, tm_mon=1, tm_mday=1, tm_hour=0, tm_min=0, tm_sec=0, tm_wday=6, tm_yday=1, tm_isdst=0)
            row[1] = time.strftime('%H:%M',x)
            #对以上的时间进行格式化并写入第二列。格式为HH:MM
            row[0] = date
            for i in range(0, len(row)-1):
                row[i] = row[i] + ','
            g.writelines(row)
            g.writelines('n')
            lctime = lctime + 1800.0
            #时间戳加上1800，相当于加上了1800s = 30min
            line = f.readline()
    g.close()

def ListFiles():
    for i in os.listdir(data_folder):
        if i.endswith('.csv'):
            importcsv(i,i)