Merge tag 'upstream/2015.07.21'

[youtubedl] / youtube_dl / extractor / cinemassacre.py

diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py
index 31fe906b448669ae94c185546a5402314b975224..c949a481477c187d9433f39e6e851b87c97edf79 100644 (file)
--- a/youtube_dl/extractor/cinemassacre.py
+++ b/youtube_dl/extractor/cinemassacre.py
@@ -4,20 +4,18 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..utils import (
-    ExtractorError,
-    int_or_none,
-)
+from ..utils import ExtractorError
+from .bliptv import BlipTVIE

 
 
 class CinemassacreIE(InfoExtractor):
 
 
 class CinemassacreIE(InfoExtractor):

-    _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)'
+    _VALID_URL = 'https?://(?:www\.)?cinemassacre\.com/(?P<date_y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)'

     _TESTS = [
         {
             'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
             'md5': 'fde81fbafaee331785f58cd6c0d46190',
             'info_dict': {
     _TESTS = [
         {
             'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
             'md5': 'fde81fbafaee331785f58cd6c0d46190',
             'info_dict': {

-                'id': '19911',
+                'id': 'Cinemassacre-19911',

                 'ext': 'mp4',
                 'upload_date': '20121110',
                 'title': '“Angry Video Game Nerd: The Movie” – Trailer',
                 'ext': 'mp4',
                 'upload_date': '20121110',
                 'title': '“Angry Video Game Nerd: The Movie” – Trailer',


@@ -28,26 +26,71 @@ class CinemassacreIE(InfoExtractor):
             'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
             'md5': 'd72f10cd39eac4215048f62ab477a511',
             'info_dict': {
             'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
             'md5': 'd72f10cd39eac4215048f62ab477a511',
             'info_dict': {

-                'id': '521be8ef82b16',
+                'id': 'Cinemassacre-521be8ef82b16',

                 'ext': 'mp4',
                 'upload_date': '20131002',
                 'title': 'The Mummy’s Hand (1940)',
             },
                 'ext': 'mp4',
                 'upload_date': '20131002',
                 'title': 'The Mummy’s Hand (1940)',
             },

+        },
+        {
+            # blip.tv embedded video
+            'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/',
+            'md5': 'ca9b3c8dd5a66f9375daeb5135f5a3de',
+            'info_dict': {
+                'id': '4065369',
+                'ext': 'flv',
+                'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles',
+                'upload_date': '20061207',
+                'uploader': 'cinemassacre',
+                'uploader_id': '250778',
+                'timestamp': 1283233867,
+                'description': 'md5:0a108c78d130676b207d0f6d029ecffd',
+            }
+        },
+        {
+            # Youtube embedded video
+            'url': 'http://cinemassacre.com/2006/09/01/mckids/',
+            'md5': '6eb30961fa795fedc750eac4881ad2e1',
+            'info_dict': {
+                'id': 'FnxsNhuikpo',
+                'ext': 'mp4',
+                'upload_date': '20060901',
+                'uploader': 'Cinemassacre Extras',
+                'description': 'md5:de9b751efa9e45fbaafd9c8a1123ed53',
+                'uploader_id': 'Cinemassacre',
+                'title': 'AVGN: McKids',
+            }
+        },
+        {
+            'url': 'http://cinemassacre.com/2015/05/25/mario-kart-64-nintendo-64-james-mike-mondays/',
+            'md5': '1376908e49572389e7b06251a53cdd08',
+            'info_dict': {
+                'id': 'Cinemassacre-555779690c440',
+                'ext': 'mp4',
+                'description': 'Let’s Play Mario Kart 64 !! Mario Kart 64 is a classic go-kart racing game released for the Nintendo 64 (N64). Today James & Mike do 4 player Battle Mode with Kyle and Bootsy!',
+                'title': 'Mario Kart 64 (Nintendo 64) James & Mike Mondays',
+                'upload_date': '20150525',
+            }

         }
     ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         display_id = mobj.group('display_id')
         }
     ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         display_id = mobj.group('display_id')

+        video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d')

 
         webpage = self._download_webpage(url, display_id)
 
         webpage = self._download_webpage(url, display_id)

-        video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
-        mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<full_video_id>(?:Cinemassacre-)?(?P<video_id>.+?)))"', webpage)
-        if not mobj:
-            raise ExtractorError('Can\'t extract embed url and video id')
-        playerdata_url = mobj.group('embed_url')
-        video_id = mobj.group('video_id')
-        full_video_id = mobj.group('full_video_id')
+
+        playerdata_url = self._search_regex(
+            [
+                r'src="(http://(?:player2\.screenwavemedia\.com|player\.screenwavemedia\.com/play)/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
+                r'<iframe[^>]+src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
+            ],
+            webpage, 'player data URL', default=None)
+        if not playerdata_url:
+            playerdata_url = BlipTVIE._extract_url(webpage)
+        if not playerdata_url:
+            raise ExtractorError('Unable to find player data')

 
         video_title = self._html_search_regex(
             r'<title>(?P<title>.+?)\|', webpage, 'title')
 
         video_title = self._html_search_regex(
             r'<title>(?P<title>.+?)\|', webpage, 'title')


@@ -56,63 +99,12 @@ class CinemassacreIE(InfoExtractor):
             webpage, 'description', flags=re.DOTALL, fatal=False)
         video_thumbnail = self._og_search_thumbnail(webpage)
 
             webpage, 'description', flags=re.DOTALL, fatal=False)
         video_thumbnail = self._og_search_thumbnail(webpage)
 

-        playerdata = self._download_webpage(playerdata_url, video_id, 'Downloading player webpage')
-
-        vidurl = self._search_regex(
-            r'\'vidurl\'\s*:\s*"([^\']+)"', playerdata, 'vidurl').replace('\\/', '/')
-
-        videolist_url = None
-
-        mobj = re.search(r"'videoserver'\s*:\s*'(?P<videoserver>[^']+)'", playerdata)
-        if mobj:
-            videoserver = mobj.group('videoserver')
-            mobj = re.search(r'\'vidid\'\s*:\s*"(?P<vidid>[^\']+)"', playerdata)
-            vidid = mobj.group('vidid') if mobj else full_video_id
-            videolist_url = 'http://%s/vod/smil:%s.smil/jwplayer.smil' % (videoserver, vidid)
-        else:
-            mobj = re.search(r"file\s*:\s*'(?P<smil>http.+?/jwplayer\.smil)'", playerdata)
-            if mobj:
-                videolist_url = mobj.group('smil')
-
-        if videolist_url:
-            videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML')
-            formats = []
-            baseurl = vidurl[:vidurl.rfind('/')+1]
-            for video in videolist.findall('.//video'):
-                src = video.get('src')
-                if not src:
-                    continue
-                file_ = src.partition(':')[-1]
-                width = int_or_none(video.get('width'))
-                height = int_or_none(video.get('height'))
-                bitrate = int_or_none(video.get('system-bitrate'))
-                format = {
-                    'url': baseurl + file_,
-                    'format_id': src.rpartition('.')[0].rpartition('_')[-1],
-                }
-                if width or height:
-                    format.update({
-                        'tbr': bitrate // 1000 if bitrate else None,
-                        'width': width,
-                        'height': height,
-                    })
-                else:
-                    format.update({
-                        'abr': bitrate // 1000 if bitrate else None,
-                        'vcodec': 'none',
-                    })
-                formats.append(format)
-            self._sort_formats(formats)
-        else:
-            formats = [{
-                'url': vidurl,
-            }]
-

         return {
         return {

-            'id': video_id,
+            '_type': 'url_transparent',
+            'display_id': display_id,

             'title': video_title,
             'title': video_title,

-            'formats': formats,

             'description': video_description,
             'upload_date': video_date,
             'thumbnail': video_thumbnail,
             'description': video_description,
             'upload_date': video_date,
             'thumbnail': video_thumbnail,

+            'url': playerdata_url,

         }
         }