Imported Upstream version 2015.11.27.1

[youtubedl] / youtube_dl / extractor / fivemin.py

diff --git a/youtube_dl/extractor/fivemin.py b/youtube_dl/extractor/fivemin.py
index 3a50bab5c9bd04c9d176a88be080033368fe46c7..2955965d908c15f21b3f8880993530779f97ec15 100644 (file)
--- a/youtube_dl/extractor/fivemin.py
+++ b/youtube_dl/extractor/fivemin.py
@@ -1,19 +1,24 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import re
-

 from .common import InfoExtractor
 from .common import InfoExtractor

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

     compat_urllib_parse,
     compat_urllib_parse,

+    compat_parse_qs,
+    compat_urllib_parse_urlparse,
+    compat_urlparse,
+)
+from ..utils import (

     ExtractorError,
     ExtractorError,

+    parse_duration,
+    replace_extension,

 )
 
 
 class FiveMinIE(InfoExtractor):
     IE_NAME = '5min'
     _VALID_URL = r'''(?x)
 )
 
 
 class FiveMinIE(InfoExtractor):
     IE_NAME = '5min'
     _VALID_URL = r'''(?x)

-        (?:https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(.*?&)?playList=|
+        (?:https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(?:.*?&)?playList=|
+            https?://(?:(?:massively|www)\.)?joystiq\.com/video/|

             5min:)
         (?P<id>\d+)
         '''
             5min:)
         (?P<id>\d+)
         '''


@@ -27,6 +32,7 @@ class FiveMinIE(InfoExtractor):
                 'id': '518013791',
                 'ext': 'mp4',
                 'title': 'iPad Mini with Retina Display Review',
                 'id': '518013791',
                 'ext': 'mp4',
                 'title': 'iPad Mini with Retina Display Review',

+                'duration': 177,

             },
         },
         {
             },
         },
         {


@@ -37,20 +43,58 @@ class FiveMinIE(InfoExtractor):
                 'id': '518086247',
                 'ext': 'mp4',
                 'title': 'How to Make a Next-Level Fruit Salad',
                 'id': '518086247',
                 'ext': 'mp4',
                 'title': 'How to Make a Next-Level Fruit Salad',

+                'duration': 184,

             },
         },
     ]
             },
         },
     ]

-
-    @classmethod
-    def _build_result(cls, video_id):
-        return cls.url_result('5min:%s' % video_id, cls.ie_key())
+    _ERRORS = {
+        'ErrorVideoNotExist': 'We\'re sorry, but the video you are trying to watch does not exist.',
+        'ErrorVideoNoLongerAvailable': 'We\'re sorry, but the video you are trying to watch is no longer available.',
+        'ErrorVideoRejected': 'We\'re sorry, but the video you are trying to watch has been removed.',
+        'ErrorVideoUserNotGeo': 'We\'re sorry, but the video you are trying to watch cannot be viewed from your current location.',
+        'ErrorVideoLibraryRestriction': 'We\'re sorry, but the video you are trying to watch is currently unavailable for viewing at this domain.',
+        'ErrorExposurePermission': 'We\'re sorry, but the video you are trying to watch is currently unavailable for viewing at this domain.',
+    }
+    _QUALITIES = {
+        1: {
+            'width': 640,
+            'height': 360,
+        },
+        2: {
+            'width': 854,
+            'height': 480,
+        },
+        4: {
+            'width': 1280,
+            'height': 720,
+        },
+        8: {
+            'width': 1920,
+            'height': 1080,
+        },
+        16: {
+            'width': 640,
+            'height': 360,
+        },
+        32: {
+            'width': 854,
+            'height': 480,
+        },
+        64: {
+            'width': 1280,
+            'height': 720,
+        },
+        128: {
+            'width': 640,
+            'height': 360,
+        },
+    }

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

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)

         embed_url = 'https://embed.5min.com/playerseed/?playList=%s' % video_id
         embed_page = self._download_webpage(embed_url, video_id,
         embed_url = 'https://embed.5min.com/playerseed/?playList=%s' % video_id
         embed_page = self._download_webpage(embed_url, video_id,

-            'Downloading embed page')
+                                            'Downloading embed page')

         sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid')
         query = compat_urllib_parse.urlencode({
             'func': 'GetResults',
         sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid')
         query = compat_urllib_parse.urlencode({
             'func': 'GetResults',


@@ -63,26 +107,36 @@ class FiveMinIE(InfoExtractor):
             'https://syn.5min.com/handlers/SenseHandler.ashx?' + query,
             video_id)
         if not response['success']:
             'https://syn.5min.com/handlers/SenseHandler.ashx?' + query,
             video_id)
         if not response['success']:

-            err_msg = response['errorMessage']
-            if err_msg == 'ErrorVideoUserNotGeo':
-                msg = 'Video not available from your location'
-            else:
-                msg = 'Aol said: %s' % err_msg
-            raise ExtractorError(msg, expected=True, video_id=video_id)
+            raise ExtractorError(
+                '%s said: %s' % (
+                    self.IE_NAME,
+                    self._ERRORS.get(response['errorMessage'], response['errorMessage'])),
+                expected=True)

         info = response['binding'][0]
 
         info = response['binding'][0]
 

-        second_id = compat_str(int(video_id[:-2]) + 1)

         formats = []
         formats = []

-        for quality, height in [(1, 320), (2, 480), (4, 720), (8, 1080)]:
-            if any(r['ID'] == quality for r in info['Renditions']):
+        parsed_video_url = compat_urllib_parse_urlparse(compat_parse_qs(
+            compat_urllib_parse_urlparse(info['EmbededURL']).query)['videoUrl'][0])
+        for rendition in info['Renditions']:
+            if rendition['RenditionType'] == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(rendition['Url'], video_id, m3u8_id='hls'))
+            elif rendition['RenditionType'] == 'aac':
+                continue
+            else:
+                rendition_url = compat_urlparse.urlunparse(parsed_video_url._replace(path=replace_extension(parsed_video_url.path.replace('//', '/%s/' % rendition['ID']), rendition['RenditionType'])))
+                quality = self._QUALITIES.get(rendition['ID'], {})

                 formats.append({
                 formats.append({

-                    'format_id': compat_str(quality),
-                    'url': 'http://avideos.5min.com/%s/%s/%s_%s.mp4' % (second_id[-3:], second_id, video_id, quality),
-                    'height': height,
+                    'format_id': '%s-%d' % (rendition['RenditionType'], rendition['ID']),
+                    'url': rendition_url,
+                    'width': quality.get('width'),
+                    'height': quality.get('height'),

                 })
                 })

+        self._sort_formats(formats)

 
         return {
             'id': video_id,
             'title': info['Title'],
 
         return {
             'id': video_id,
             'title': info['Title'],

+            'thumbnail': info.get('ThumbURL'),
+            'duration': parse_duration(info.get('Duration')),

             'formats': formats,
         }
             'formats': formats,
         }