Merge tag 'upstream/2015.11.10'

[youtubedl] / youtube_dl / extractor / myvideo.py

diff --git a/youtube_dl/extractor/myvideo.py b/youtube_dl/extractor/myvideo.py
index b2a7b1df04dd86cc12a4a3f94b7712cd201ae706..c96f472a39e569c7dfb88682d36fad9ed6ce2c10 100644 (file)
--- a/youtube_dl/extractor/myvideo.py
+++ b/youtube_dl/extractor/myvideo.py
@@ -1,36 +1,40 @@
+from __future__ import unicode_literals
+

 import binascii
 import base64
 import hashlib
 import re
 import binascii
 import base64
 import hashlib
 import re

+import json

 
 from .common import InfoExtractor
 
 from .common import InfoExtractor

-from ..utils import (
+from ..compat import (

     compat_ord,
     compat_urllib_parse,
     compat_ord,
     compat_urllib_parse,

-
+    compat_urllib_parse_unquote,
+    compat_urllib_request,
+)
+from ..utils import (

     ExtractorError,
 )
 
 
     ExtractorError,
 )
 
 

-

 class MyVideoIE(InfoExtractor):
 class MyVideoIE(InfoExtractor):

-    """Information Extractor for myvideo.de."""
-
-    _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
-    IE_NAME = u'myvideo'
+    _VALID_URL = r'http://(?:www\.)?myvideo\.de/(?:[^/]+/)?watch/(?P<id>[0-9]+)/[^?/]+.*'
+    IE_NAME = 'myvideo'

     _TEST = {
     _TEST = {

-        u'url': u'http://www.myvideo.de/watch/8229274/bowling_fail_or_win',
-        u'file': u'8229274.flv',
-        u'md5': u'2d2753e8130479ba2cb7e0a37002053e',
-        u'info_dict': {
-            u"title": u"bowling-fail-or-win"
+        'url': 'http://www.myvideo.de/watch/8229274/bowling_fail_or_win',
+        'md5': '2d2753e8130479ba2cb7e0a37002053e',
+        'info_dict': {
+            'id': '8229274',
+            'ext': 'flv',
+            'title': 'bowling-fail-or-win',

         }
     }
 
     # Original Code from: https://github.com/dersphere/plugin.video.myvideo_de.git
     # Released into the Public Domain by Tristan Fischer on 2013-05-19
     # https://github.com/rg3/youtube-dl/pull/842
         }
     }
 
     # Original Code from: https://github.com/dersphere/plugin.video.myvideo_de.git
     # Released into the Public Domain by Tristan Fischer on 2013-05-19
     # https://github.com/rg3/youtube-dl/pull/842

-    def __rc4crypt(self,data, key):
+    def __rc4crypt(self, data, key):

         x = 0
         box = list(range(256))
         for i in list(range(256)):
         x = 0
         box = list(range(256))
         for i in list(range(256)):


@@ -46,20 +50,17 @@ class MyVideoIE(InfoExtractor):
             out += chr(compat_ord(char) ^ box[(box[x] + box[y]) % 256])
         return out
 
             out += chr(compat_ord(char) ^ box[(box[x] + box[y]) % 256])
         return out
 

-    def __md5(self,s):
+    def __md5(self, s):

         return hashlib.md5(s).hexdigest().encode()
 
         return hashlib.md5(s).hexdigest().encode()
 

-    def _real_extract(self,url):
+    def _real_extract(self, url):

         mobj = re.match(self._VALID_URL, url)
         mobj = re.match(self._VALID_URL, url)

-        if mobj is None:
-            raise ExtractorError(u'invalid URL: %s' % url)
-
-        video_id = mobj.group(1)
+        video_id = mobj.group('id')

 
         GK = (
 
         GK = (

-          b'WXpnME1EZGhNRGhpTTJNM01XVmhOREU0WldNNVpHTTJOakpt'
-          b'TW1FMU5tVTBNR05pWkRaa05XRXhNVFJoWVRVd1ptSXhaVEV3'
-          b'TnpsbA0KTVRkbU1tSTRNdz09'
+            b'WXpnME1EZGhNRGhpTTJNM01XVmhOREU0WldNNVpHTTJOakpt'
+            b'TW1FMU5tVTBNR05pWkRaa05XRXhNVFJoWVRVd1ptSXhaVEV3'
+            b'TnpsbA0KTVRkbU1tSTRNdz09'

         )
 
         # Get video webpage
         )
 
         # Get video webpage


@@ -72,23 +73,33 @@ class MyVideoIE(InfoExtractor):
             video_url = mobj.group(1) + '.flv'
 
             video_title = self._html_search_regex('<title>([^<]+)</title>',
             video_url = mobj.group(1) + '.flv'
 
             video_title = self._html_search_regex('<title>([^<]+)</title>',

-                webpage, u'title')
+                                                  webpage, 'title')

 
 

-            video_ext = self._search_regex('[.](.+?)$', video_url, u'extension')
+            return {
+                'id': video_id,
+                'url': video_url,
+                'title': video_title,
+            }

 
 

-            return [{
-                'id':       video_id,
-                'url':      video_url,
-                'uploader': None,
-                'upload_date':  None,
-                'title':    video_title,
-                'ext':      video_ext,
-            }]
+        mobj = re.search(r'data-video-service="/service/data/video/%s/config' % video_id, webpage)
+        if mobj is not None:
+            request = compat_urllib_request.Request('http://www.myvideo.de/service/data/video/%s/config' % video_id, '')
+            response = self._download_webpage(request, video_id,
+                                              'Downloading video info')
+            info = json.loads(base64.b64decode(response).decode('utf-8'))
+            return {
+                'id': video_id,
+                'title': info['title'],
+                'url': info['streaming_url'].replace('rtmpe', 'rtmpt'),
+                'play_path': info['filename'],
+                'ext': 'flv',
+                'thumbnail': info['thumbnail'][0]['url'],
+            }

 
         # try encxml
         mobj = re.search('var flashvars={(.+?)}', webpage)
         if mobj is None:
 
         # try encxml
         mobj = re.search('var flashvars={(.+?)}', webpage)
         if mobj is None:

-            raise ExtractorError(u'Unable to extract video')
+            raise ExtractorError('Unable to extract video')

 
         params = {}
         encxml = ''
 
         params = {}
         encxml = ''


@@ -97,12 +108,12 @@ class MyVideoIE(InfoExtractor):
             if not a == '_encxml':
                 params[a] = b
             else:
             if not a == '_encxml':
                 params[a] = b
             else:

-                encxml = compat_urllib_parse.unquote(b)
+                encxml = compat_urllib_parse_unquote(b)

         if not params.get('domain'):
             params['domain'] = 'www.myvideo.de'
         xmldata_url = '%s?%s' % (encxml, compat_urllib_parse.urlencode(params))
         if 'flash_playertype=MTV' in xmldata_url:
         if not params.get('domain'):
             params['domain'] = 'www.myvideo.de'
         xmldata_url = '%s?%s' % (encxml, compat_urllib_parse.urlencode(params))
         if 'flash_playertype=MTV' in xmldata_url:

-            self._downloader.report_warning(u'avoiding MTV player')
+            self._downloader.report_warning('avoiding MTV player')

             xmldata_url = (
                 'http://www.myvideo.de/dynamic/get_player_video_xml.php'
                 '?flash_playertype=D&ID=%s&_countlimit=4&autorun=yes'
             xmldata_url = (
                 'http://www.myvideo.de/dynamic/get_player_video_xml.php'
                 '?flash_playertype=D&ID=%s&_countlimit=4&autorun=yes'


@@ -125,48 +136,41 @@ class MyVideoIE(InfoExtractor):
         video_url = None
         mobj = re.search('connectionurl=\'(.*?)\'', dec_data)
         if mobj:
         video_url = None
         mobj = re.search('connectionurl=\'(.*?)\'', dec_data)
         if mobj:

-            video_url = compat_urllib_parse.unquote(mobj.group(1))
+            video_url = compat_urllib_parse_unquote(mobj.group(1))

             if 'myvideo2flash' in video_url:
             if 'myvideo2flash' in video_url:

-                self._downloader.report_warning(u'forcing RTMPT ...')
-                video_url = video_url.replace('rtmpe://', 'rtmpt://')
+                self.report_warning(
+                    'Rewriting URL to use unencrypted rtmp:// ...',
+                    video_id)
+                video_url = video_url.replace('rtmpe://', 'rtmp://')

 
         if not video_url:
             # extract non rtmp videos
             mobj = re.search('path=\'(http.*?)\' source=\'(.*?)\'', dec_data)
             if mobj is None:
 
         if not video_url:
             # extract non rtmp videos
             mobj = re.search('path=\'(http.*?)\' source=\'(.*?)\'', dec_data)
             if mobj is None:

-                raise ExtractorError(u'unable to extract url')
-            video_url = compat_urllib_parse.unquote(mobj.group(1)) + compat_urllib_parse.unquote(mobj.group(2))
+                raise ExtractorError('unable to extract url')
+            video_url = compat_urllib_parse_unquote(mobj.group(1)) + compat_urllib_parse_unquote(mobj.group(2))

 
 

-        video_file = self._search_regex('source=\'(.*?)\'', dec_data, u'video file')
-        video_file = compat_urllib_parse.unquote(video_file)
+        video_file = self._search_regex('source=\'(.*?)\'', dec_data, 'video file')
+        video_file = compat_urllib_parse_unquote(video_file)

 
         if not video_file.endswith('f4m'):
             ppath, prefix = video_file.split('.')
             video_playpath = '%s:%s' % (prefix, ppath)
 
         if not video_file.endswith('f4m'):
             ppath, prefix = video_file.split('.')
             video_playpath = '%s:%s' % (prefix, ppath)

-            video_hls_playlist = ''

         else:
             video_playpath = ''
         else:
             video_playpath = ''

-            video_hls_playlist = (
-                video_file
-            ).replace('.f4m', '.m3u8')

 
 

-        video_swfobj = self._search_regex('swfobject.embedSWF\(\'(.+?)\'', webpage, u'swfobj')
-        video_swfobj = compat_urllib_parse.unquote(video_swfobj)
+        video_swfobj = self._search_regex('swfobject.embedSWF\(\'(.+?)\'', webpage, 'swfobj')
+        video_swfobj = compat_urllib_parse_unquote(video_swfobj)

 
         video_title = self._html_search_regex("<h1(?: class='globalHd')?>(.*?)</h1>",
 
         video_title = self._html_search_regex("<h1(?: class='globalHd')?>(.*?)</h1>",

-            webpage, u'title')
-
-        return [{
-            'id':                 video_id,
-            'url':                video_url,
-            'tc_url':             video_url,
-            'uploader':           None,
-            'upload_date':        None,
-            'title':              video_title,
-            'ext':                u'flv',
-            'play_path':          video_playpath,
-            'video_file':         video_file,
-            'video_hls_playlist': video_hls_playlist,
-            'player_url':         video_swfobj,
-        }]
-
+                                              webpage, 'title')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'tc_url': video_url,
+            'title': video_title,
+            'ext': 'flv',
+            'play_path': video_playpath,
+            'player_url': video_swfobj,
+        }