add support for PPTV (download not supported)

you_get/common.py

@@ -106,7 +106,6 @@ def url_info(url):
         'video/webm': 'webm',
         'video/x-flv': 'flv'
     }
-    #assert type in mapping, type
     if type in mapping:
         ext = mapping[type]
     else:

you_get/downloader/__init__.py

@@ -2,6 +2,7 @@
 
 from .cntv import *
 from .ku6 import *
+from .pptv import *
 from .sohu import *
 from .tudou import *
 from .w56 import *

you_get/downloader/pptv.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python
+
+__all__ = ['pptv_download', 'pptv_download_by_id']
+
+from ..common import *
+
+import re
+import urllib
+import hashlib
+
+def pptv_download_by_id(id, title = None, output_dir = '.', merge = True, info_only = False):
+    xml = get_html('http://web-play.pptv.com/webplay3-151-%s.xml' % id)
+    host = r1(r'<sh>([^<>]+)</sh>', xml)
+    port = 8080
+    st = r1(r'<st>([^<>]+)</st>', xml).encode('utf-8')
+    key = hashlib.md5(st).hexdigest() # FIXME: incorrect key
+    rids = re.findall(r'rid="([^"]+)"', xml)
+    rid = r1(r'rid="([^"]+)"', xml)
+    title = r1(r'nm="([^"]+)"', xml)
+    pieces = re.findall('<sgm no="(\d+)".*fs="(\d+)"', xml)
+    numbers, fs = zip(*pieces)
+    urls = ['http://%s:%s/%s/%s?key=%s' % (host, port, i, rid, key) for i in numbers]
+    urls = ['http://pptv.vod.lxdns.com/%s/%s?key=%s' % (i, rid, key) for i in numbers]
+    total_size = sum(map(int, fs))
+    assert rid.endswith('.mp4')
+    
+    print_info(site_info, title, 'mp4', total_size)
+    if not info_only:
+        download_urls(urls, title, 'mp4', total_size, output_dir = output_dir, merge = merge)
+
+def pptv_download(url, output_dir = '.', merge = True, info_only = False):
+    assert re.match(r'http://v.pptv.com/show/(\w+)\.html$', url)
+    html = get_html(url)
+    id = r1(r'webcfg\s*=\s*{"id":\s*(\d+)', html)
+    assert id
+    pptv_download_by_id(id, output_dir = output_dir, merge = merge, info_only = info_only)
+
+site_info = "PPTV.com"
+download = pptv_download
+download_playlist = playlist_not_supported('pptv')

you_get/downloader/w56.py

@@ -7,7 +7,7 @@ from ..common import *
 import json
 
 def w56_download_by_id(id, title = None, output_dir = '.', merge = True, info_only = False):
-    info = json.loads(get_html('http://vxml.56.com/json/%s/?src=site'%id))['info']
+    info = json.loads(get_html('http://vxml.56.com/json/%s/?src=site' % id))['info']
     title = title or info['Subject']
     assert title
     hd = info['hd']

you_get/main.py

@@ -19,6 +19,7 @@ def url_to_module(url):
         '56': w56,
         'cntv': cntv,
         'ku6': ku6,
+        'pptv': pptv,
         'sohu': sohu,
         'tudou': tudou,
         'yinyuetai': yinyuetai,
@@ -30,7 +31,6 @@ def url_to_module(url):
         # 'kankanews': bilibili,
         # 'iask': iask,
         # 'sina': iask,
-        # 'pptv': pptv,
         # 'iqiyi': iqiyi,
     }
     if k in downloads: