Merge branch 'jackyzy823-develop' into develop, fix #257 and close #266

src/you_get/common.py

@@ -922,7 +922,7 @@ def script_main(script_name, download, download_playlist = None):
             sys.exit(1)
 
 def url_to_module(url):
-    from .extractors import netease, w56, acfun, baidu, bilibili, blip, catfun, cntv, cbs, coursera, dailymotion, douban, ehow, facebook, freesound, google, sina, ifeng, alive, instagram, iqiyi, joy, jpopsuki, khan, ku6, kugou, kuwo, letv, magisto, miomio, mixcloud, mtv81, nicovideo, pptv, qq, sohu, songtaste, soundcloud, ted, theplatform, tudou, tumblr, vid48, vimeo, vine, vk, xiami, yinyuetai, youku, youtube
+    from .extractors import netease, w56, acfun, baidu, bilibili, blip, catfun, cntv, cbs, coursera, dailymotion, douban, ehow, facebook, freesound, google, sina, ifeng, alive, instagram, iqiyi, joy, jpopsuki, khan, ku6, kugou, kuwo, letv, magisto, miomio, mixcloud, mtv81, nicovideo, pptv, qq, sohu, songtaste, soundcloud, ted, theplatform, tudou, tucao, tumblr, vid48, vimeo, vine, vk, xiami, yinyuetai, youku, youtube
 
     video_host = r1(r'https?://([^/]+)/', url)
     video_url = r1(r'https?://[^/]+(.*)', url)
@@ -978,6 +978,7 @@ def url_to_module(url):
         'soundcloud': soundcloud,
         'ted': ted,
         'theplatform': theplatform,
+        "tucao":tucao,
         'tudou': tudou,
         'tumblr': tumblr,
         'vid48': vid48,

src/you_get/extractors/__init__.py

@@ -37,6 +37,7 @@ from .sohu import *
 from .songtaste import *
 from .soundcloud import *
 from .theplatform import *
+from .tucao import *
 from .tudou import *
 from .tumblr import *
 from .vid48 import *

src/you_get/extractors/qq.py

@@ -4,8 +4,21 @@ __all__ = ['qq_download']
 
 from ..common import *
 
+#QQMUSIC
+#SINGLE
+#1. http://y.qq.com/#type=song&mid=000A9lMb0iEqwN
+#2. http://y.qq.com/#type=song&id=4754713
+#3. http://s.plcloud.music.qq.com/fcgi-bin/fcg_yqq_song_detail_info.fcg?songmid=002NqCeX3owQIw
+#4. http://s.plcloud.music.qq.com/fcgi-bin/fcg_yqq_song_detail_info.fcg?songid=4754713
+#ALBUM
+#1. http://y.qq.com/y/static/album/3/c/00385vBa0n3O3c.html?pgv_ref=qqmusic.y.index.music.pic1
+#2. http://y.qq.com/#type=album&mid=004c62RC2uujor
+#MV
+#can download as video through qq_download_by_id
+#1. http://y.qq.com/y/static/mv/mv_play.html?vid=i0014ufczcw
+
 def qq_download_by_id(id, title=None, output_dir='.', merge=True, info_only=False):
-    xml = get_html('http://www.acfun.com/getinfo?vids=%s' % id)
+    xml = get_html('http://www.acfun.tv/getinfo?vids=%s' % id)
     from xml.dom.minidom import parseString
     doc = parseString(xml)
     doc_root = doc.getElementsByTagName('root')[0]

src/you_get/extractors/tucao.py

@@ -0,0 +1,54 @@
+#!/usr/bin/env python
+
+__all__ = ['tucao_download']
+from ..common import *
+# import re
+import random
+import time
+from xml.dom import minidom
+
+#1. <li>type=tudou&vid=199687639</li>
+#2. <li>type=tudou&vid=199506910|</li>
+#3. <li>type=video&file=http://xiaoshen140731.qiniudn.com/lovestage04.flv|</li>
+#4 may ? <li>type=video&file=http://xiaoshen140731.qiniudn.com/lovestage04.flv|xx**type=&vid=?</li>
+#5. <li>type=tudou&vid=200003098|07**type=tudou&vid=200000350|08</li>
+
+# re_pattern=re.compile(r"(type=(.+?)&(vid|file)=(.*?))[\|<]")
+
+def tucao_single_download(type_link, title, output_dir=".", merge=True, info_only=False):
+    if "file" in type_link:
+        url=type_link[type_link.find("file=")+5:]
+        vtype, ext, size=url_info(url)
+        print_info(site_info, title, vtype, size)
+        if not info_only:
+            download_urls([url], title, ext, size, output_dir)
+    else:
+        u="http://www.tucao.cc/api/playurl.php?{}&key=tucao{:07x}.cc&r={}".format(type_link,random.getrandbits(28),int(time.time()*1000))
+        xml=minidom.parseString(get_content(u))
+        urls=[]
+        size=0
+        for i in xml.getElementsByTagName("url"):
+            urls.append(i.firstChild.nodeValue)
+            vtype, ext, _size=url_info(i.firstChild.nodeValue)
+            size+=_size
+        print_info(site_info, title, vtype, size)
+        if not info_only:
+            download_urls(urls, title, ext, size, output_dir) 
+
+def tucao_download(url, output_dir=".", merge=True, info_only=False):
+    html=get_content(url)
+    title=match1(html,r'<h1 class="show_title">(.*?)<\w')
+    raw_list=match1(html,r"<li>(type=.+?)</li>")
+    raw_l=raw_list.split("**")
+    if len(raw_l)==1:
+        format_link=raw_l[0][:-1] if raw_l[0].endswith("|") else raw_l[0]
+        tucao_single_download(format_link,title,output_dir,merge,info_only)
+    else:
+        for i in raw_l:
+            format_link,sub_title=i.split("|")
+            tucao_single_download(format_link,title+"-"+sub_title,output_dir,merge,info_only)
+
+
+site_info = "tucao.cc"
+download = tucao_download
+download_playlist = playlist_not_supported("tucao")