Update downloadFromLuoow.com.py

5 下载落网音乐/downloadFromLuoow.com.py

@@ -11,34 +11,65 @@
 from pyquery import PyQuery as pq
 import requests as rq
 
+luooUrl = "http://www.luoow.com/r/{}/"
+
 def parse_javascript(js):
     '''解析js文本中的mp3数据,以字典形式返回：{'name':mp3Name,'url':}'''
     patternName = re.compile(r'"name":"(.*?)"') #name
     patternMp3 = re.compile(r'"src":"(.*?.mp3)"') #mp3Url
     namesList = patternName.findall(js)
     mp3List = patternMp3.findall(js)
 
-    musicDictList = [{"name":name[:2],"url":url} for name,url in zip(namesList,mp3List)]
+    musicDictList = [{"name":name,"url":url} for name,url in zip(namesList,mp3List)]
 
     return musicDictList
 
 class LuooMusic(object):
     '''下载落网'''
-    def __init__(self,issueNum):
-        self.url = "http://www.luoow.com/{}/".format(issueNum)
-        self.html = pq(url = self.url)
+    def __init__(self,url):
+        self.url = url
+        try:
+            self.html = pq(url = self.url)
+        except:
+            self.html = ""
 
     def get_title(self):
         '''获取每一期的标题'''
-        return self.html("title").text()
+
+        if self.html:
+            return self.html("title").text()
+        else:
+            return ""
 
     def get_coverUrl(self):
         '''获取每一期封面'''
-        return self.html(".container .cover_img img").attr("src")
+        if self.html:
+            return self.html(".container .cover_img img").attr("src")
+        else:
+            return ""
 
     def get_musicDictList(self):
         '''获取每一期音乐列表'''
-        return parse_javascript(self.html("script")[1].text)
+        if self.html:
+            return parse_javascript(self.html("script")[1].text)
+        else:
+            return ""
+
+class DownloadCoverThread(threading.Thread):
+    ''' 下载线程'''
+    def __init__(self,name,url):
+        super(DownloadThread,self).__init__()
+        self.name = name
+        self.url = url
+
+    def run(self):
+        ''' 下载封面 '''
+        ABSPATH = os.path.dirname(os.path.realpath(__file__))
+        COVERPATH = os.path.join(ABSPATH,"%s-cover.jpg"%self.name)
+        if not os.path.exists(COVERPATH):
+            with open(COVERPATH,"wb") as f:
+                f.write(rq.get(self.url).content)
+            print("%s was downloaded"%self.name)
 
 class DownloadThread(threading.Thread):
     ''' 下载线程'''
@@ -62,21 +93,46 @@ def run(self):
                 f.write(rq.get(self.url).content)
             #urllib.request.urlretrieve(self.url, MUSICPATH)    #乱码bug还未处理
             print("%s was downloaded"%self.name)
+
+
+def download_cover_thread(name,url):
+    ''' 下载封面 '''
+    ABSPATH = os.path.dirname(os.path.realpath(__file__))
+    COVERPATH = os.path.join(ABSPATH,"%s-cover.jpg"%name)
+    if not os.path.exists(COVERPATH):
+        with open(COVERPATH,"wb") as f:
+            f.write(rq.get(url).content)
+        print("%s was downloaded"%name)
+
+def download_music_thread(dirname,name,url):
+    ''' 下载音乐 '''
+    ABSPATH = os.path.dirname(os.path.realpath(__file__))
+    DOWNDIR = os.path.join(os.path.join(ABSPATH,"Luoo"),"%s"%dirname)
+    MUSICPATH = os.path.join(DOWNDIR,"%s.mp3"%name)
+    try:
+        os.mkdir(DOWNDIR)
+    except:
+        pass
+    #if not os.path.exists(MUSICPATH):
+    with open(MUSICPATH,"wb") as f:
+        f.write(rq.get(url).content)
+    print("%s was downloaded"%name)
+
+if __name__ == "__main__":
+    luooUrl = "http://www.luoow.com/mi/{}/"       #单曲
+    for i in range(1,50):
+        r = LuooMusic(luooUrl.format(i))
+        dirname = "mi {} - {}".format(i,r.get_title())
+        musicList = r.get_musicDictList()
+        trs = []
+        for music in musicList:
+            trs.append(threading.Thread(target=download_music_thread,args=(dirname,music["name"],music["url"])))
+            print("add %s thread"%music["name"])
+
+        for tr in trs:
+            tr.start()
 
-for i in range(993,1000):
-    r = LuooMusic(i)
-    name = r.get_title()
-    tds = []
-    index = 1
-    for j in r.get_musicDictList():
-        tds.append(DownloadThread(name,j["name"],j["url"]))
-        index += 1
-    print("start download %s"%name)
-    for td in tds:
-        td.start()
-    for tj in tds:
-        tj.join()
-    print("%s download complate"%name)
-    print("=========================")
+        for tr in trs:
+            tr.join()
 
-print("All have downloaded")
+    print("All have downloaded")