add dry_infos

src/you_get/.idea/encodings.xml

@@ -0,0 +1,5 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Encoding" useUTFGuessing="true" native2AsciiForPropertiesFiles="false" />
+</project>
+

src/you_get/.idea/misc.xml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.4.0 (/usr/bin/python3.4)" project-jdk-type="Python SDK" />
+  <component name="PyConsoleOptionsProvider">
+    <option name="myPythonConsoleState">
+      <console-settings />
+    </option>
+  </component>
+</project>
+

src/you_get/.idea/modules.xml

@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/you_get.iml" filepath="$PROJECT_DIR$/.idea/you_get.iml" />
+    </modules>
+  </component>
+</project>
+

src/you_get/.idea/scopes/scope_settings.xml

@@ -0,0 +1,5 @@
+<component name="DependencyValidationManager">
+  <state>
+    <option name="SKIP_IMPORT_STATEMENTS" value="false" />
+  </state>
+</component>

src/you_get/.idea/vcs.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>
+

src/you_get/.idea/you_get.iml

@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>
+

src/you_get/common.py

@@ -18,6 +18,7 @@ force = False
 player = None
 extractor_proxy = None
 cookies_txt = None
+dry_infos = {}
 
 fake_headers = {
     'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
@@ -464,6 +465,7 @@ class PiecesProgressBar:
             print()
             self.displayed = False
 
+
 class DummyProgressBar:
     def __init__(self, *args):
         pass
@@ -477,7 +479,10 @@ class DummyProgressBar:
 def download_urls(urls, title, ext, total_size, output_dir='.', refer=None, merge=True, faker=False):
     assert urls
     if dry_run:
-        print('Real URLs:\n%s\n' % urls)
+        dry_infos.clear()
+        dry_infos.update({'urls':urls, 'ext':ext, 'total_size':total_size})
+
+        print('Real URLs dry_infos:\n%s\n' % dry_infos['urls'])
         return
 
     if player:
@@ -899,7 +904,7 @@ def script_main(script_name, download, download_playlist = None):
             sys.exit(1)
 
 def url_to_module(url):
-    from .extractors import netease, w56, acfun, baidu, baomihua, bilibili, blip, catfun, cntv, cbs, coursera, dailymotion, dongting, douban, douyutv, 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, videobam, vimeo, vine, vk, xiami, yinyuetai, youku, youtube
+    from .extractors import netease, w56, acfun, baidu, bilibili, blip, catfun, cntv, cbs, coursera, dailymotion, dongting, douban, douyutv, 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, videobam, vimeo, vine, vk, xiami, yinyuetai, youku, youtube
 
     video_host = r1(r'https?://([^/]+)/', url)
     video_url = r1(r'https?://[^/]+(.*)', url)
@@ -916,7 +921,6 @@ def url_to_module(url):
         '56': w56,
         'acfun': acfun,
         'baidu': baidu,
-        'baomihua': baomihua,
         'bilibili': bilibili,
         'blip': blip,
         'catfun': catfun,
@@ -984,9 +988,11 @@ def url_to_module(url):
             raise NotImplementedError(url)
         else:
             return url_to_module(location)
-
+extractor = []
 def any_download(url, **kwargs):
     m, url = url_to_module(url)
+    extractor.clear()
+    extractor.append(m)
     m.download(url, **kwargs)
 
 def any_download_playlist(url, **kwargs):

src/you_get/extractor.py

@@ -2,7 +2,6 @@
 
 from .common import match1, download_urls, parse_host, set_proxy, unset_proxy
 from .util import log
-
 class Extractor():
     def __init__(self, *args):
         self.url = None

src/you_get/extractors/bilibili.py

@@ -26,6 +26,7 @@ def get_srt_xml(id):
     url = 'http://comment.bilibili.com/%s.xml' % id
     return get_html(url)
 
+
 def parse_srt_p(p):
     fields = p.split(',')
     assert len(fields) == 8, fields
@@ -49,15 +50,31 @@ def parse_srt_p(p):
 
     font_size = int(font_size)
 
-    font_color = '#%06x' % int(font_color)
+    font_color = int(font_color)
 
-    return pool, mode, font_size, font_color
+    return time,font_color, mode, font_size, 'bilibili_'+user_id, pub_time
 
 def parse_srt_xml(xml):
-    d = re.findall(r'<d p="([^"]+)">(.*)</d>', xml)
-    for x, y in d:
-        p = parse_srt_p(x)
-    raise NotImplementedError()
+    ret = []
+    d = re.findall(r'<d p="([^"]+)">(.*?)</d>', xml)
+    if len(d) > 3000:
+        d = d[:3000]
+    for parameters, text in d:
+        item = {}
+        time,font_color, mode, font_size, uuid, publishTime = parse_srt_p(parameters)
+        item['text'] = text
+        item['color'] = font_color
+        item['fontSize'] = font_size
+        item['direct'] = mode
+        item['startTime'] = time
+        item['uuid'] = uuid
+        item['publishTime'] = publishTime
+        ret.append(item)
+
+    return ret
+
+def get_Danmu(id):
+    return parse_srt_xml(get_srt_xml(id))
 
 def parse_cid_playurl(xml):
     from xml.dom.minidom import parseString

src/you_get/extractors/douyutv.py

@@ -9,12 +9,10 @@ import json
 def douyutv_download(url, output_dir = '.', merge = True, info_only = False):
     html = get_html(url)
     room_id_patt = r'"room_id":(\d{1,99}),'
-    title_patt = r'<div class="headline clearfix">\s*<h1>([^<]{1,9999})</h1>'
-    title_patt_backup = r'<title>([^<]{1,9999})</title>'
+    title_patt = r'<div class="headline clearfix">\s*<h1>([^<]{1,9999})</h1>\s*</div>'
     
     roomid = re.findall(room_id_patt,html)[0]
-    title = r1_of([title_patt,title_patt_backup], html)
-    title = unescape_html(title)
+    title = unescape_html(re.findall(title_patt,html)[0])
 
     conf = get_html("http://www.douyutv.com/api/client/room/"+roomid)
     metadata = json.loads(conf)

src/you_get/extractors/qq.py

@@ -2,8 +2,8 @@
 
 __all__ = ['qq_download']
 
-from ..common import *
-import uuid
+from you_get.common import *
+import uuid, urllib
 #QQMUSIC
 #SINGLE
 #1. http://y.qq.com/#type=song&mid=000A9lMb0iEqwN
@@ -17,43 +17,49 @@ import uuid
 #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.tv/getinfo?vids=%s' % id)
-    from xml.dom.minidom import parseString
-    doc = parseString(xml)
-    doc_root = doc.getElementsByTagName('root')[0]
-    doc_vl = doc_root.getElementsByTagName('vl')[0]
-    doc_vi = doc_vl.getElementsByTagName('vi')[0]
-    fn = doc_vi.getElementsByTagName('fn')[0].firstChild.data
-    # fclip = doc_vi.getElementsByTagName('fclip')[0].firstChild.data
-    # fc=doc_vi.getElementsByTagName('fc')[0].firstChild.data
-    fvkey = doc_vi.getElementsByTagName('fvkey')[0].firstChild.data
-    doc_ul = doc_vi.getElementsByTagName('ul')
 
+def qq_download_by_id(id, title=None, output_dir='.', merge=True, info_only=False, urls_only=False):
+    data = {'vids': id, 'otype': 'json'}
+    url = urllib.request.Request('http://vv.video.qq.com/getinfo', urllib.parse.urlencode(data).encode('utf-8'))
+    f = urllib.request.urlopen(url)
+    json_str = f.read()
+    data = json.loads(json_str[13:-1].decode('utf-8'))
+    format_id = 10202
+    file_id = 1
+    for format_info in data['fl']['fi']:
+        if format_info['sl'] > 0:
+            format_id = format_info['id']
+            file_id = format_info['sl']
+            break
+    file_name = data['vl']['vi'][0]['fn']
+    split_pos = file_name.rfind('.')
+    file_name = file_name[:split_pos] + '.%d' % file_id + file_name[split_pos:]
+    video_urls = [ui['url'] for ui in data['vl']['vi'][0]['ul']['ui']]
 
-    url = doc_ul[0].getElementsByTagName('url')[1].firstChild.data
+    data = {'format': format_id, 'otype': 'json', 'vid': id, 'filename': file_name}
+    url = urllib.request.Request('http://vv.video.qq.com/getkey', urllib.parse.urlencode(data).encode('utf-8'))
+    f = urllib.request.urlopen(url)
+    json_str = f.read()
+    data = json.loads(json_str[13:-1].decode('utf-8'))
+    video_key = data['key']
 
-    # print(i.firstChild.data)
     urls = []
-    ext=fn[-3:]
     size = 0
-    for i in doc.getElementsByTagName("cs"):
-        size+=int(i.firstChild.data)
+    ext = ''
+    for url in video_urls:
+        try:
+            url = "%s%s?vkey=%s" % (url, file_name, video_key)
+            _, ext, size = url_info(url)
+            urls = [url]
+            break
+        except:
+            print(url)
 
-    # size=sum(map(int,doc.getElementsByTagName("cs")))
-    locid=str(uuid.uuid4())
-    for i in doc.getElementsByTagName("ci"):
-        urls.append(url+fn[:-4] + "." + i.getElementsByTagName("idx")[0].firstChild.data + fn[-4:] + '?vkey=' + fvkey+ '&sdtfrom=v1000&type='+ fn[-3:0] +'&locid=' + locid + "&&level=1&platform=11&br=133&fmt=hd&sp=0")
+    if urls_only:
+        return urls, size, ext, {}
 
-    # if int(fclip) > 0:
-    #     fn = fn[:-4] + "." + fclip + fn[-4:]
-    # url = url + fn + '?vkey=' + fvkey
-
-    # _, ext, size = url_info(url)
-
-    print_info(site_info, title, ext, size)
     if not info_only:
-        download_urls(urls, title, ext, size, output_dir=output_dir, merge=merge)
+        download_urls([url], title, 'flv', size, output_dir = output_dir, merge = merge)
 
 def qq_download(url, output_dir = '.', merge = True, info_only = False):
     if re.match(r'http://v.qq.com/([^\?]+)\?vid', url):
@@ -97,3 +103,9 @@ def qq_download(url, output_dir = '.', merge = True, info_only = False):
 site_info = "QQ.com"
 download = qq_download
 download_playlist = playlist_not_supported('qq')
+
+
+if __name__ == '__main__':
+    #print(qq_download('http://v.qq.com/cover/c/crfns95chw1snp2/t0012q2nz5m.html', urls_only = True))
+    # print(get_videoId('http://v.qq.com/cover/k/kuegopa6s70qeu1.html?vid=t0013jyqbo7'))
+    print(qq_download_by_id('u001428c4av', urls_only=True))

src/you_get/extractors/ted.py

@@ -3,7 +3,43 @@
 __all__ = ['ted_download']
 
 from ..common import *
-import json
+import json, os, inspect, logging, time
+from pprint import pprint
+#sys.path += [os.path.dirname(os.path.dirname(os.path.dirname(__file__)))]
+currentDir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
+parentDir = os.path.dirname(os.path.dirname(currentDir))
+se_parentDir = os.path.dirname(parentDir)
+sys.path.append(parentDir)
+sys.path.append(se_parentDir)
+#print currentDir
+#print parentDir
+#print se_parentDir
+# print sys.path
+
+from you_get.common import *
+
+TED_D_DINFO = False
+TED_D_DSUB = False
+TED_D_DFINFO = False
+
+TED_TALKS_URL_PAT = "http://www.ted.com/talks/%s"
+FOUND = False
+
+logger = logging.getLogger()
+logger.setLevel(logging.DEBUG)
+log_handle = logging.StreamHandler(sys.stdout)
+log_handle.setFormatter(logging.Formatter('%(asctime)-15s [%(levelname)s] %(message)s'))
+logger.addHandler(log_handle)
+
+fake_headers_here = {
+    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
+    #'Accept-Charset': 'UTF-8,*;q=0.5',
+    'Accept-Encoding': 'gzip,deflate,sdch',
+    'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6',
+    'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36',
+    'Connection': 'keep-alive',
+    'Cookie':'',
+    }
 
 def ted_download(url, output_dir='.', merge=True, info_only=False):
     html = get_html(url)
@@ -19,6 +55,298 @@ def ted_download(url, output_dir='.', merge=True, info_only=False):
                 download_urls([url], title, ext, size, output_dir, merge=merge)
             break
 
+# For ted_download_by_id
+re_url = re.compile('"nativeDownloads":.*"high":"(.+)\?.+},"sub')
+re_slug = re.compile('"slug":"(.*?)"')
+#re_vid = re.compile('http://.+\/(.*\.mp4)')
+re_name = re.compile('"external":.*?,"name":"(.*?)","title":')
+# Inner video ID
+re_in_id = re.compile('http://www.ted.com/talks/(.*?)')
+
+def ted_download_by_id(id, title, output_dir = '.', stream_type = None, merge = True, info_only = False, urls_only = False):
+    # ret: urls,size,ext,headers = callMap[videoType](videoId,"title", urls_only = True)
+
+    try:
+        url = TED_TALKS_URL_PAT % id
+        vpage = get_html(url)
+    except:
+        logger.info("###ted_download_by_id: TED id home can not be accessed")
+        return [url], 0, 'mp4', {}
+
+    logger.info("###ted_download_by_id")
+    logger.info("page url is" + url)
+
+    #print "page content is"
+    # print vpage
+
+    v_url = re.findall(re_url, vpage)[0]
+    v_title = re.findall(re_name, vpage)[0]
+    size = urls_size([v_url], True, None)
+    #size is not used
+    # size = -1
+    urls = [v_url]
+
+    logger.info("###ted_download_by_id")
+    #logger.info("name + v_url + size \n" )
+    #print "%r, %r, %r" % (v_title, v_url, size)
+    logger.info("name: " + str(v_title) + " url:" + str(v_url) + " size: " + str(size))
+
+    # print "ret is",(urls, size, 'mp4', 'fake_headers')
+
+    return urls, size, 'mp4', {}
+
+
+def ted_download(url, output_dir = '.', stream_type = None, merge = True, info_only = False, urls_only = False):
+
+    logger.info("###ted_download")
+    logger.info("page url is " + url)
+
+    vpage = get_html(url)
+    v_title = re.findall(re_name, vpage)[0]
+    v_url = re.findall(re_url, vpage)[0]
+
+    type, ext, size = url_info(v_url)
+    print_info(site_info, v_title, type, size)
+
+    logger.info("v_title is " + str(v_title) + "type is " + str(type) + "size is " + str(size) )
+
+    if not info_only:
+        download_urls([v_url], v_title, ext, size, output_dir, merge = merge)
+
+
+def get_videoId(url):
+    v_in_id = re.findall(re_in_id, url)[0]
+    return v_in_id
+
+
+def srt_time(tst):
+    """Format Time from TED Subtitles format to SRT time Format."""
+    secs, mins, hours = ((tst / 1000) % 60), (tst / 60000), (tst / 3600000)
+    right_srt_time = ("{0:02d}:{1:02d}:{2:02d},{3:3.0f}".
+                      format(int(hours), int(mins), int(secs),
+                             divmod(secs, 1)[1] * 1000))
+    return right_srt_time
+
+
+def srt_sec_time(tst):
+    """Format Time from TED Subtitles format to SRT time Format."""
+    secs = tst / 1000
+    return secs
+
+
+# regex expressions to search into the webpage
+re_dm_intro = re.compile('"introDuration":(\d+\.?\d+),')
+re_dm_id = re.compile('"id":(\d+),')
+re_dm_url = re.compile('"nativeDownloads":.*"high":"(.+)\?.+},"sub')
+re_dm_vid = re.compile('http://.+\/(.*\.mp4)')
+
+def ted_get_danmu(video_id):
+    """
+    Get Danmu for the unique video_id
+    """
+    logger.info("###ted_get_danmu")
+
+    url = TED_TALKS_URL_PAT % video_id
+    logger.info("page url is " + url)
+
+    try:
+        vpage = get_html(url)
+    except:
+        logger.info("###ted_get_danmu:request faild, ret null danmu list")
+        return []
+
+    ret_list = []
+
+    tt_intro = ((float(re_dm_intro.findall(vpage)[0]) + 1) * 1000)
+    tt_id = int(re_dm_id.findall(vpage)[0])
+    tt_url = re_dm_url.findall(vpage)[0]
+    tt_v_fname = re_dm_vid.findall(tt_url)[0]
+
+    #logger.info("###tt_intro is " + str(tt_intro))
+    subs = get_subs(tt_id, tt_intro, tt_v_fname)
+
+    # we only process english caption currrently
+    # 0(eng) 0(item list)
+    eng_sub = subs[0][0]
+
+    for i in eng_sub:
+        r_item = {}
+        p_item = parse_item(i)
+
+        r_item['text'] = p_item["content"]
+        r_item['color'] = p_item["font_color"]
+        r_item['fontSize'] = p_item["font_size"]
+        r_item['direct'] = p_item["mode"]
+        r_item['startTime'] = p_item["time"]
+        r_item['uuid'] = p_item["uuid"]
+        r_item['publishTime'] = p_item["pub_time"]
+
+        ret_list.append(r_item)
+        #logger.info("###parsed sub item")
+        #pprint(r_item)
+
+    logger.info("###ted_get_danmu:parsed sub item list info:" + " len: " + str(len(ret_list)))
+
+    if TED_D_DINFO:
+        logger.info("###ted_get_danmu:last two items" + " ret_list len " + str(len(ret_list) ) )
+        if len(ret_list) > 0:
+            pprint(ret_list[-1])
+        if len(ret_list) > 1:
+            pprint(ret_list[-2])
+        pass
+
+    if TED_D_DFINFO:
+        logger.info("###ted_get_danmu:full ret list" )
+        logger.info(str(ret_list))
+
+    return ret_list
+
+
+def parse_item(item):
+    """
+    Return a tuple for a+ danmu element
+    """
+    s_time = float(item["start"])
+
+    # Mode is the direct opt
+    # mode 1~3: scrolling
+    # mode 4: bottom
+    # mode 5: top
+    # mode 6: reverse?
+    # mode 7: position
+    # mode 8: advanced
+    mode = 4
+    assert 1 <= mode <= 8
+
+    # pool 0: normal
+    # pool 1: srt
+    # pool 2: special?
+    #pool = int(pool)
+    pool = 0
+    assert 0 <= pool <= 2
+
+    font_size = 25
+    font_color = 16777215
+    pub_time = str(int(time.time() * 1000000 ))[-10:]
+
+    return {"time":s_time, "font_color":font_color, "mode":mode, "font_size":font_size,
+            "uuid":"s_defuuid_z9", "pub_time":pub_time, "content":item["content"]}
+
+
+def get_subs(tt_id, tt_intro, tt_video_fname):
+    """
+    Get the sutitles, currently for english
+    """
+
+    subs = ["{0}.{1}.srt".format(tt_video_fname[:-4], lang) for lang in ('eng', 'chi')]
+    ret_subs = []
+
+    for sub in subs:
+        #logger.info("###get_subs:pls input to continue s sub getting:")
+        #raw_input()
+
+        subtitle = get_single_sub(tt_id, tt_intro, sub)
+        if subtitle:
+            ret_subs.append(subtitle)
+            #logger.info("###get_subs:Subtitle '{0}' downloaded.".format(sub) )
+
+    if TED_D_DSUB:
+        # raw_input()
+        logger.info("\n")
+        for idx, sub in enumerate(subs):
+
+            with open(sub, 'w') as srt_file:
+                for item in ret_subs[idx][0]:
+                    srt_file.write(str(item))
+
+                srt_file.write("\n#############\n")
+                srt_file.write("\nSRT formated data\n")
+                srt_file.write(ret_subs[idx][1])
+
+            logger.info("###get_subs:Debug:Subtitle '{0}' downloaded.".format(sub))
+
+    return ret_subs
+
+
+def get_single_sub(tt_id, tt_intro, sub):
+    """
+    Get TED Subtitle in JSON format & convert it to SRT Subtitle.
+    """
+
+    srt_content = ''
+    srt_items = []
+    tt_url = 'http://www.ted.com/talks'
+    sub_url = '{0}/subtitles/id/{1}/lang/{2}'.format(tt_url, tt_id, sub[-7:-4])
+
+    # Get JSON sub
+    json_file = request.urlopen(sub_url).readlines()
+    logger.info("###get_single_sub: sub url is " + sub_url)
+
+    if json_file:
+        try:
+            json_object = json.loads(json_file[0].decode('utf-8'))
+            logger.info("###get_single_sub: json load orig data")
+            #logger.info(json_object)
+            if 'captions' in json_object:
+                caption_idx = 1
+                if not json_object['captions']:
+                    logger.info("Subtitle '{0}' not available.".format(sub))
+                for caption in json_object['captions']:
+                    start = tt_intro + caption['startTime']
+                    end = start + caption['duration']
+                    idx_line = '{0}'.format(caption_idx)
+                    time_line = '{0} --> {1}'.format(srt_time(start),
+                                                     srt_time(end))
+                    text_line = '{0}'.format(caption['content'].encode("utf-8"))
+
+                    # Append the srt items and content parellelly
+                    srt_items.append({"index":caption_idx, "start":srt_sec_time(start),
+                                      "duration":srt_sec_time(caption['duration']), "content":text_line})
+                    srt_content += '\n'.join([idx_line, time_line, text_line, '\n'])
+                    caption_idx += 1
+
+            elif 'status' in json_object:
+                logger.info("This is an error message returned by TED:{0}{0} - "
+                      "{1}{0}{0}Probably because the subtitle '{2}' is not "
+                      "available.{0}".format(os.linesep, json_object['status']['message'], sub))
+
+        except ValueError:
+            logger.info("Subtitle '{0}' it's a malformed json file.".format(sub))
+
+    return (srt_items, srt_content)
+
+
+def options():
+    """Defines the command line arguments and options for the script."""
+
+    desc = "Downloads the subtitles and the video (optional) for a TED Talk."
+    usage = "Beautifull TED"
+    parser = optparse.OptionParser(usage=usage, version="%prog " + __version__,
+                                   description=desc)
+
+    parser.add_option("-s", "--only_subs", action='store_true',
+                      dest="no_video",
+                      help="download only the subs, not the video ",
+                      default=False)
+    return parser
+
+
+def check_exec_posix(prog):
+    """
+    Check if the program is installed in a *NIX platform.
+    """
+    return True
+
+
+def main():
+    """main section"""
+    pass
+
+
+# module info
+get_Danmu = ted_get_danmu
+
+
 site_info = "TED.com"
 download = ted_download
 download_playlist = playlist_not_supported('ted')

src/you_get/extractors/tudou.py

@@ -7,7 +7,7 @@ from xml.dom.minidom import parseString
 
 def tudou_download_by_iid(iid, title, output_dir = '.', merge = True, info_only = False):
     data = json.loads(get_decoded_html('http://www.tudou.com/outplay/goto/getItemSegs.action?iid=%s' % iid))
-    temp = max([data[i] for i in data if 'size' in data[i][0]], key=lambda x:x[0]["size"])
+    temp = max([data[i] for i in data], key=lambda x:x[0]["size"])
     vids, size = [t["k"] for t in temp], sum([t["size"] for t in temp])
     urls = [[n.firstChild.nodeValue.strip()
              for n in

src/you_get/extractors/tumblr.py

@@ -7,23 +7,15 @@ from ..common import *
 import re
 
 def tumblr_download(url, output_dir = '.', merge = True, info_only = False):
-    html = parse.unquote(get_html(url)).replace('\/', '/')
-    feed = r1(r'<meta property="og:type" content="tumblr-feed:(\w+)" />', html)
-
-    if feed == 'audio':
-        real_url = r1(r'source src=\\x22([^\\]+)\\', html)
-        if not real_url:
-            real_url = r1(r'audio_file=([^&]+)&', html) + '?plead=please-dont-download-this-or-our-lawyers-wont-let-us-host-audio'
-    elif feed == 'video':
-        iframe_url = r1(r'<iframe src=\'([^\']*)\'', html)
-        iframe_html = get_html(iframe_url)
-        real_url = r1(r'<source src="([^"]*)"', iframe_html)
-    else:
-        real_url = r1(r'<source src="([^"]*)"', html)
+    html = get_html(url)
+    html = parse.unquote(html).replace('\/', '/')
     
     title = unescape_html(r1(r'<meta property="og:title" content="([^"]*)" />', html) or
         r1(r'<meta property="og:description" content="([^"]*)" />', html) or
         r1(r'<title>([^<\n]*)', html)).replace('\n', '')
+    real_url = r1(r'source src=\\x22([^\\]+)\\', html)
+    if not real_url:
+        real_url = r1(r'audio_file=([^&]+)&', html) + '?plead=please-dont-download-this-or-our-lawyers-wont-let-us-host-audio'
     
     type, ext, size = url_info(real_url)
     

src/you_get/extractors/youku.py

@@ -55,14 +55,14 @@ class Youku(VideoExtractor):
     def get_vid_from_url(url):
         """Extracts video ID from URL.
         """
-        return match1(url, r'youku\.com/v_show/id_([a-zA-Z0-9=]+)') or \
-          match1(url, r'player\.youku\.com/player\.php/sid/([a-zA-Z0-9=]+)/v\.swf') or \
-          match1(url, r'loader\.swf\?VideoIDS=([a-zA-Z0-9=]+)')
+        return match1(url, r'youku\.com/v_show/id_([\w=]+)') or \
+          match1(url, r'player\.youku\.com/player\.php/sid/([\w=]+)/v\.swf') or \
+          match1(url, r'loader\.swf\?VideoIDS=([\w=]+)')
 
     def get_playlist_id_from_url(url):
         """Extracts playlist ID from URL.
         """
-        return match1(url, r'youku\.com/playlist_show/id_([a-zA-Z0-9=]+)')
+        return match1(url, r'youku\.com/playlist_show/id_([\w=]+)')
 
     def download_playlist_by_url(self, url, **kwargs):
         self.url = url

src_bak/you_get/__init__.py

@@ -0,0 +1,18 @@
+#!/usr/bin/env python
+# This file is Python 2 compliant.
+
+import sys
+
+if sys.version_info[0] == 3:
+    #from .extractor import Extractor, VideoExtractor
+    #from .util import log
+
+    from .__main__ import *
+
+    #from .common import *
+    #from .version import *
+    #from .cli_wrapper import *
+    #from .extractor import *
+else:
+    # Don't import anything.
+    pass

src_bak/you_get/__main__.py

@@ -0,0 +1,91 @@
+#!/usr/bin/env python
+
+import getopt
+import os
+import platform
+import sys
+from .version import script_name, __version__
+from .util import git, log
+
+_options = [
+    'help',
+    'version',
+    'gui',
+    'force',
+    'playlists',
+]
+_short_options = 'hVgfl'
+
+_help = """Usage: {} [OPTION]... [URL]...
+TODO
+""".format(script_name)
+
+def main_dev(**kwargs):
+    """Main entry point.
+    you-get-dev
+    """
+
+    # Get (branch, commit) if running from a git repo.
+    head = git.get_head(kwargs['repo_path'])
+
+    # Get options and arguments.
+    try:
+        opts, args = getopt.getopt(sys.argv[1:], _short_options, _options)
+    except getopt.GetoptError as e:
+        log.wtf("""
+    [Fatal] {}.
+    Try '{} --help' for more options.""".format(e, script_name))
+
+    if not opts and not args:
+        # Display help.
+        print(_help)
+        # Enter GUI mode.
+        #from .gui import gui_main
+        #gui_main()
+    else:
+        conf = {}
+        for opt, arg in opts:
+            if opt in ('-h', '--help'):
+                # Display help.
+                print(_help)
+
+            elif opt in ('-V', '--version'):
+                # Display version.
+                log.println("you-get:", log.BOLD)
+                log.println("    version:  {}".format(__version__))
+                if head is not None:
+                    log.println("    branch:   {}\n    commit:   {}".format(*head))
+                else:
+                    log.println("    branch:   {}\n    commit:   {}".format("(stable)", "(tag v{})".format(__version__)))
+
+                log.println("    platform: {}".format(platform.platform()))
+                log.println("    python:   {}".format(sys.version.split('\n')[0]))
+
+            elif opt in ('-g', '--gui'):
+                # Run using GUI.
+                conf['gui'] = True
+
+            elif opt in ('-f', '--force'):
+                # Force download.
+                conf['force'] = True
+
+            elif opt in ('-l', '--playlist', '--playlists'):
+                # Download playlist whenever possible.
+                conf['playlist'] = True
+
+        if args:
+            if 'gui' in conf and conf['gui']:
+                # Enter GUI mode.
+                from .gui import gui_main
+                gui_main(*args, **conf)
+            else:
+                # Enter console mode.
+                from .console import console_main
+                console_main(*args, **conf)
+
+def main(**kwargs):
+    """Main entry point.
+    you-get (legacy)
+    """
+    from .common import main
+    main()

src_bak/you_get/cli_wrapper/player/__init__.py

@@ -0,0 +1,3 @@
+#!/usr/bin/env python
+
+from .mplayer import *

src_bak/you_get/cli_wrapper/player/__main__.py

@@ -0,0 +1,7 @@
+#!/usr/bin/env python
+
+def main():
+    script_main('you-get', any_download, any_download_playlist)
+
+if __name__ == "__main__":
+    main()

src_bak/you_get/cli_wrapper/player/vlc.py

@@ -0,0 +1 @@
+#!/usr/bin/env python