add support: CBS & thePlatform

src/you_get/extractor/__init__.py

@@ -5,6 +5,7 @@ from .alive import *
 from .baidu import *
 from .bilibili import *
 from .blip import *
+from .cbs import *
 from .cntv import *
 from .coursera import *
 from .dailymotion import *
@@ -32,6 +33,7 @@ from .sina import *
 from .sohu import *
 from .songtaste import *
 from .soundcloud import *
+from .theplatform import *
 from .tudou import *
 from .tumblr import *
 from .vid48 import *

src/you_get/extractor/__main__.py

@@ -24,6 +24,7 @@ def url_to_module(url):
         'bilibili': bilibili,
         'blip': blip,
         'cntv': cntv,
+        'cbs': cbs,
         'coursera': coursera,
         'dailymotion': dailymotion,
         'douban': douban,
@@ -53,6 +54,7 @@ def url_to_module(url):
         'songtaste':songtaste,
         'soundcloud': soundcloud,
         'ted': ted,
+        'theplatform': theplatform,
         'tudou': tudou,
         'tumblr': tumblr,
         'vid48': vid48,

src/you_get/extractor/cbs.py

@@ -0,0 +1,21 @@
+#!/usr/bin/env python
+
+__all__ = ['cbs_download']
+
+from ..common import *
+
+from .theplatform import theplatform_download_by_pid
+
+def cbs_download(url, output_dir='.', merge=True, info_only=False):
+    """Downloads CBS videos by URL.
+    """
+
+    html = get_content(url)
+    pid = match1(html, r'video\.settings\.pid\s*=\s*\'([^\']+)\'')
+    title = match1(html, r'video\.settings\.title\s*=\s*\"([^\"]+)\"')
+
+    theplatform_download_by_pid(pid, title, output_dir=output_dir, merge=merge, info_only=info_only)
+
+site_info = "CBS.com"
+download = cbs_download
+download_playlist = playlist_not_supported('cbs')

src/you_get/extractor/theplatform.py

@@ -0,0 +1,26 @@
+#!/usr/bin/env python
+
+from ..common import *
+
+def theplatform_download_by_pid(pid, title, output_dir='.', merge=True, info_only=False):
+    smil_url = "http://link.theplatform.com/s/dJ5BDC/%s/meta.smil?format=smil&mbr=true" % pid
+    smil = get_content(smil_url)
+    smil_base = unescape_html(match1(smil, r'<meta base="([^"]+)"'))
+    smil_videos = {y:x for x,y in dict(re.findall(r'<video src="([^"]+)".+height="([^"]+)"', smil)).items()}
+    for height in ['1080', '720', '480', '360', '240', '216']:
+        if height in smil_videos:
+            smil_video = smil_videos[height]
+            break
+    assert smil_video
+
+    type, ext, size = 'mp4', 'mp4', 0
+
+    print_info(site_info, title, type, size)
+    if not info_only:
+        from ..processor.rtmpdump import has_rtmpdump_installed, download_rtmpdump_stream
+        assert has_rtmpdump_installed(), "RTMPDump not installed."
+        download_rtmpdump_stream(url=smil_base, playpath=ext+':'+smil_video, title=title, ext=ext, output_dir=output_dir)
+
+site_info = "thePlatform.com"
+download = theplatform_download_by_pid
+download_playlist = playlist_not_supported('theplatform')