码迷,mamicode.com
首页 > 编程语言 > 详细

下载8000首儿歌的python代码

时间:2014-07-07 14:43:22      阅读:216      评论:0      收藏:0      [点我收藏+]

标签:blog   http   os   art   html   for   

下载8000首儿歌的python的代码:

bubuko.com,布布扣
#-*- coding: UTF-8 -*-

from pyquery import PyQuery as py
from lxml import etree
import urllib
import re
import os
import sys
import logging

def format(filename):
    tuple=(‘ ‘,‘’‘,‘\‘‘)
    for char in tuple:
        if (filename.find(char)!=-1):
            filename=filename.replace(char,"_")
    return filename

def download_mp3(mp3_url, filename,dir):       
    f = dir+"\\"+filename
    if os.path.exists(f):
      logger.debug(f+" is existed.")
      return
      
    try:
        open(f, ‘wb‘).write(urllib.urlopen(mp3_url).read())
        logger.debug(  filename + ‘ is downloaded.‘)
    except:
        logger.debug( filename + ‘ is not downloaded.‘)

        
def download_all_mp3(start,end,dir,logger):
  for x in range(start,end):
    try:
        url = "http://www.youban.com/mp3-d" + str(x) + ".html"
        logger.debug(str(x) + ": "+url)
        doc = py(url=url)
        e = doc(‘.mp3downloadbox‘)
        if e is None or e == ‘‘: 
          logger.debug(url+" is not existed.")
          return
          
        e = unicode(e)
        #logger.debug( e)
        regex = re.compile(ur".*<h1>(.*)</h1>.*downloadboxlist.*?<a.*?\"(.*?)\"",re.UNICODE|re.S)
        m = regex.search(e)
        if m is not None:
          title = m.group(1).strip()
          title2 = str(x)+"_"+title + ".mp3" 
          #title2 = re.sub(‘ ‘,‘_‘,title2)
          title2 = format(title2)
          link = m.group(2)
          #logger.debug( "title:" + title + " link:" + link)
          if link == ‘‘ or title == ‘‘:
            logger.debug(url + " is not useful")
            continue
          logger.debug(str(x)+": "+link)
          download_mp3(link,title2,dir)
    except:
        logger.debug(url+" met exception.")
        continue
      

if __name__ == "__main__": dir_root = "e:\\song" if sys.argv[3] != ‘‘: dir_root=sys.argv[3] start,end = 1,8000 if sys.argv[1] >= 0 and sys.argv[2]>=0: start,end = int(sys.argv[1]),int(sys.argv[2]) print ("Download from %s to %s.\n" % (start,end)) dir = dir_root + "\\"+str(start)+"-"+str(end) if not os.path.exists(dir): os.mkdir(dir) print "Download to " + dir + ".\n" logger = logging.getLogger("simple") logger.setLevel(logging.DEBUG) fh = logging.FileHandler(dir+"\\"+"download.log") ch = logging.StreamHandler() formatter = logging.Formatter("%(message)s") ch.setFormatter(formatter) fh.setFormatter(formatter) logger.addHandler(ch) logger.addHandler(fh) download_all_mp3(start,end,dir,logger)
bubuko.com,布布扣

 

有需要的可以参考继续修改。

 

下载8000首儿歌的python代码,布布扣,bubuko.com

下载8000首儿歌的python代码

标签:blog   http   os   art   html   for   

原文地址:http://www.cnblogs.com/L-H-R-X-hehe/p/3815328.html

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!