转知乎的文章 都用 Python 来做什么啊

# 网易云音乐批量下载# By Tsing# Python3.4.4importrequestsimporturllib# 榜单歌曲批量下载# r = requests.get(‘http://music.163.com/api/playlist/detail?id=2884035‘)	# 网易原创歌曲榜# r = requests.get(‘http://music.163.com/api/playlist/detail?id=19723756‘)	# 云音乐飙升榜# r = requests.get(‘http://music.163.com/api/playlist/detail?id=3778678‘)	# 云音乐热歌榜r=requests.get(‘http://music.163.com/api/playlist/detail?id=3779629‘)# 云音乐新歌榜# 歌单歌曲批量下载# r = requests.get(‘http://music.163.com/api/playlist/detail?id=123415635‘)	# 云音乐歌单——【华语】中国风的韵律，中国人的印记# r = requests.get(‘http://music.163.com/api/playlist/detail?id=122732380‘)	# 云音乐歌单——那不是爱，只是寂寞说的谎arr=r.json()[‘result‘][‘tracks‘]# 共有100首歌foriinrange(10):# 输入要下载音乐的数量，1到100。name=str(i+1)+‘ ‘+arr[i][‘name‘]+‘.mp3‘link=arr[i][‘mp3Url‘]urllib.request.urlretrieve(link,‘网易云音乐\\‘+name)# 提前要创建文件夹print(name+‘ 下载完成‘)

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# 保存读者杂志某一期的全部文章为TXT
# By Tsing
# Python 2.7.9

import urllib2
import os
from bs4 import BeautifulSoup

def urlBS(url):
    response = urllib2.urlopen(url)
    html = response.read()
    soup = BeautifulSoup(html)
    return soup

def main(url):
    soup = urlBS(url)
    link = soup.select(‘.booklist a‘)
    path = os.getcwd()+u‘/读者文章保存/‘
    if not os.path.isdir(path):
        os.mkdir(path)
    for item in link:
        newurl = baseurl + item[‘href‘]
        result = urlBS(newurl)
        title = result.find("h1").string
        writer = result.find(id="pub_date").string.strip()
        filename = path + title + ‘.txt‘
        print filename.encode("gbk")
        new=open(filename,"w")
        new.write("<<" + title.encode("gbk") + ">>\n\n")
        new.write(writer.encode("gbk")+"\n\n")
        text = result.select(‘.blkContainerSblkCon p‘)
        for p in text:
            context = p.text
            new.write(context.encode("gbk"))

        new.close()


if __name__ == ‘__main__‘:
    time = ‘2015_03‘
    baseurl = ‘http://www.52duzhe.com/‘ + time +‘/‘
    firsturl = baseurl + ‘index.html‘
    main(firsturl)
    

#!/usr/bin/env python# -*- coding: utf-8 -*-# 获取城市PM2.5浓度和排名# By Tsing# Python 2.7.9importurllib2importthreadingfromtimeimportctimefrombs4importBeautifulSoupdefgetPM25(cityname):site=‘http://www.pm25.com/‘+cityname+‘.html‘html=urllib2.urlopen(site)soup=BeautifulSoup(html)city=soup.find(class_=‘bi_loaction_city‘)# 城市名称aqi=soup.find("a",{"class","bi_aqiarea_num"})# AQI指数quality=soup.select(".bi_aqiarea_right span")# 空气质量等级result=soup.find("div",class_=‘bi_aqiarea_bottom‘)# 空气质量描述printcity.text+u‘AQI指数：‘+aqi.text+u‘\n空气质量：‘+quality[0].text+result.textprint‘*‘*20+ctime()+‘*‘*20defone_thread():# 单线程print‘One_thread Start: ‘+ctime()+‘\n‘getPM25(‘hefei‘)getPM25(‘shanghai‘)deftwo_thread():# 多线程print‘Two_thread Start: ‘+ctime()+‘\n‘threads=[]t1=threading.Thread(target=getPM25,args=(‘hefei‘,))threads.append(t1)t2=threading.Thread(target=getPM25,args=(‘shanghai‘,))threads.append(t2)fortinthreads:# t.setDaemon(True)t.start()if__name__==‘__main__‘:one_thread()print‘\n‘*2two_thread()

#!/usr/bin/env python
#coding:utf-8
# 根据易迅网的商品ID，爬取商品价格信息。
# By Tsing
# Python 2.7.9

import urllib2
from bs4 import BeautifulSoup
def get_yixun(id):
    price_origin,price_sale = ‘0‘,‘0‘
    url = ‘http://item.yixun.com/item-‘ + id + ‘.html‘
    html = urllib2.urlopen(url).read().decode(‘utf-8‘)
    soup = BeautifulSoup(html)
    title = unicode(soup.title.text.strip().strip(u‘【价格_报价_图片_行情】-易迅网‘).replace(u‘】‘,‘‘)).encode(‘utf-8‘).decode(‘utf-8‘)
    print title
    try:
        soup_origin = soup.find("dl", { "class" : "xbase_item xprice xprice_origin" })
        price_origin = soup_origin.find("span", { "class" : "mod_price xprice_val" }).contents[1].text 
        print  u‘原价：‘ + price_origin
    except:
        pass
    try:
        soup_sale= soup.find(‘dl‘,{‘class‘:‘xbase_item xprice‘})
        price_sale = soup_sale.find("span", { "class" : "mod_price xprice_val" }).contents[1] 
        print  u‘现价：‘+ price_sale
    except:
        pass
    
    print url
    return None

if __name__ == ‘__main__‘:
    get_yixun(‘2189654‘)

#!/usr/bin/env python# -*- coding: utf-8 -*-# 音悦台MV免积分下载# By Tsing# Python 2.7.9importurllib2importurllibimportremv_id=‘2278607‘# 这里输入mv的id，即http://v.yinyuetai.com/video/2275893最后的数字url="http://www.yinyuetai.com/insite/get-video-info?flex=true&videoId="+mv_idtimeout=30headers={‘User-Agent‘:‘Mozilla/5.0 (Windows NT 6.3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36‘,‘Accept‘:‘text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8‘}req=urllib2.Request(url,None,headers)res=urllib2.urlopen(req,None,timeout)html=res.read()reg=r"http://\w*?\.yinyuetai\.com/uploads/videos/common/.*?(?=&br)"pattern=re.compile(reg)findList=re.findall(pattern,html)# 找到mv所有版本的下载链接iflen(findList)>=3:mvurl=findList[2]# 含有流畅、高清、超清三个版本时下载超清else:mvurl=findList[0]# 版本少时下载流畅视频local=‘MV.flv‘try:print‘downloading...please wait...‘urllib.urlretrieve(mvurl,local)print"[:)] Great! The mv has been downloaded.\n"except:print"[:(] Sorry! The action is failed.\n"