Merge pull request #989 from cnbeining/ckplayer

[CKPlayer]Extract by XML as helper

src/you_get/extractors/__init__.py

@@ -7,6 +7,7 @@ from .baidu import *
 from .bandcamp import *
 from .bilibili import *
 from .cbs import *
+from .ckplayer import *
 from .cntv import *
 from .dailymotion import *
 from .dilidili import *

src/you_get/extractors/ckplayer.py

@@ -0,0 +1,98 @@
+#!/usr/bin/env python
+#coding:utf-8
+# Author:  Beining --<i@cnbeining.com>
+# Purpose: A general extractor for CKPlayer
+# Created: 03/15/2016
+
+__all__ = ['ckplayer_download']
+
+from xml.etree import cElementTree as ET
+from copy import copy
+from ..common import *
+
+#----------------------------------------------------------------------
+def ckplayer_get_info_by_xml(ckinfo):
+    """str->dict
+    Information for CKPlayer API content."""
+    e = ET.XML(ckinfo)
+    video_dict = {'title': '',
+                  #'duration': 0,
+                  'links': [],
+                  'size': 0,
+                  'flashvars': '',}
+    if '_text' in dictify(e)['ckplayer']['info'][0]['title'][0]:  #title
+        video_dict['title'] = dictify(e)['ckplayer']['info'][0]['title'][0]['_text'].strip()
+
+    #if dictify(e)['ckplayer']['info'][0]['title'][0]['_text'].strip():  #duration
+        #video_dict['title'] = dictify(e)['ckplayer']['info'][0]['title'][0]['_text'].strip()
+
+    if '_text' in dictify(e)['ckplayer']['video'][0]['size'][0]:  #size exists for 1 piece
+        video_dict['size'] = sum([int(i['size'][0]['_text']) for i in dictify(e)['ckplayer']['video']])
+
+    if '_text' in dictify(e)['ckplayer']['video'][0]['file'][0]:  #link exist
+        video_dict['links'] = [i['file'][0]['_text'].strip() for i in dictify(e)['ckplayer']['video']]
+
+    if '_text' in dictify(e)['ckplayer']['flashvars'][0]:
+        video_dict['flashvars'] = dictify(e)['ckplayer']['flashvars'][0]['_text'].strip()
+
+    return video_dict
+
+#----------------------------------------------------------------------
+#helper
+#https://stackoverflow.com/questions/2148119/how-to-convert-an-xml-string-to-a-dictionary-in-python
+def dictify(r,root=True):
+    if root:
+        return {r.tag : dictify(r, False)}
+    d=copy(r.attrib)
+    if r.text:
+        d["_text"]=r.text
+    for x in r.findall("./*"):
+        if x.tag not in d:
+            d[x.tag]=[]
+        d[x.tag].append(dictify(x,False))
+    return d
+
+#----------------------------------------------------------------------
+def ckplayer_download_by_xml(ckinfo, output_dir = '.', merge = False, info_only = False, **kwargs):
+    #Info XML
+    video_info = ckplayer_get_info_by_xml(ckinfo)
+    
+    try:
+        title = kwargs['title']
+    except:
+        title = ''
+    type_ = ''
+    size = 0
+    
+    if len(video_info['links']) > 0:  #has link
+        type_, _ext, size = url_info(video_info['links'][0])  #use 1st to determine type, ext
+    
+    if 'size' in video_info:
+        size = int(video_info['size'])
+    else:
+        for i in video_info['links'][1:]:  #save 1st one
+            size += url_info(i)[2]
+    
+    print_info(site_info, title, type_, size)
+    if not info_only:
+        download_urls(video_info['links'], title, _ext, size, output_dir=output_dir, merge=merge)
+
+#----------------------------------------------------------------------
+def ckplayer_download(url, output_dir = '.', merge = False, info_only = False, is_xml = True, **kwargs):
+    if is_xml:  #URL is XML URL
+        try:
+            title = kwargs['title']
+        except:
+            title = ''
+        try:
+            headers = kwargs['headers']  #headers provided
+            ckinfo = get_content(url, headers = headers)
+        except NameError:
+            ckinfo = get_content(url)
+        
+        ckplayer_download_by_xml(ckinfo, output_dir, merge, 
+                                info_only, title = title)
+
+site_info = "CKPlayer General"
+download = ckplayer_download
+download_playlist = playlist_not_supported('ckplayer')