Merge tag 'upstream/2014.07.11'

[youtubedl] / youtube_dl / extractor / collegehumor.py

diff --git a/youtube_dl/extractor/collegehumor.py b/youtube_dl/extractor/collegehumor.py
index d10b7bd0cda2161838e83da741fe7a2f6c88f575..6f866e7fcee7f401362b24d69db2285e22cfa6a4 100644 (file)
--- a/youtube_dl/extractor/collegehumor.py
+++ b/youtube_dl/extractor/collegehumor.py
@@ -4,6 +4,7 @@ import json
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

+from ..utils import int_or_none

 
 
 class CollegeHumorIE(InfoExtractor):
 
 
 class CollegeHumorIE(InfoExtractor):


@@ -11,24 +12,46 @@ class CollegeHumorIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
 
     _TESTS = [{
         'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',

-        'file': '6902724.mp4',

         'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd',
         'info_dict': {
         'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd',
         'info_dict': {

+            'id': '6902724',
+            'ext': 'mp4',

             'title': 'Comic-Con Cosplay Catastrophe',
             'title': 'Comic-Con Cosplay Catastrophe',

-            'description': 'Fans get creative this year at San Diego.  Too',
+            'description': "Fans get creative this year at San Diego.  Too creative.  And yes, that's really Joss Whedon.",

             'age_limit': 13,
             'age_limit': 13,

+            'duration': 187,

         },
     },
     {
         'url': 'http://www.collegehumor.com/video/3505939/font-conference',
         },
     },
     {
         'url': 'http://www.collegehumor.com/video/3505939/font-conference',

-        'file': '3505939.mp4',

         'md5': '72fa701d8ef38664a4dbb9e2ab721816',
         'info_dict': {
         'md5': '72fa701d8ef38664a4dbb9e2ab721816',
         'info_dict': {

+            'id': '3505939',
+            'ext': 'mp4',

             'title': 'Font Conference',
             'title': 'Font Conference',

-            'description': 'This video wasn\'t long enough, so we made it double-spaced.',
+            'description': "This video wasn't long enough, so we made it double-spaced.",

             'age_limit': 10,
             'age_limit': 10,

+            'duration': 179,

         },
         },

-    }]
+    },
+    # embedded youtube video
+    {
+        'url': 'http://www.collegehumor.com/embed/6950306',
+        'info_dict': {
+            'id': 'Z-bao9fg6Yc',
+            'ext': 'mp4',
+            'title': 'Young Americans Think President John F. Kennedy Died THIS MORNING IN A CAR ACCIDENT!!!',
+            'uploader': 'Mark Dice',
+            'uploader_id': 'MarkDice',
+            'description': 'md5:62c3dab9351fac7bb44b53b69511d87f',
+            'upload_date': '20140127',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': ['Youtube'],
+    },
+    ]

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)


@@ -38,6 +61,12 @@ class CollegeHumorIE(InfoExtractor):
         data = json.loads(self._download_webpage(
             jsonUrl, video_id, 'Downloading info JSON'))
         vdata = data['video']
         data = json.loads(self._download_webpage(
             jsonUrl, video_id, 'Downloading info JSON'))
         vdata = data['video']

+        if vdata.get('youtubeId') is not None:
+            return {
+                '_type': 'url',
+                'url': vdata['youtubeId'],
+                'ie_key': 'Youtube',
+            }

 
         AGE_LIMITS = {'nc17': 18, 'r': 18, 'pg13': 13, 'pg': 10, 'g': 0}
         rating = vdata.get('rating')
 
         AGE_LIMITS = {'nc17': 18, 'r': 18, 'pg13': 13, 'pg': 10, 'g': 0}
         rating = vdata.get('rating')


@@ -49,7 +78,7 @@ class CollegeHumorIE(InfoExtractor):
         PREFS = {'high_quality': 2, 'low_quality': 0}
         formats = []
         for format_key in ('mp4', 'webm'):
         PREFS = {'high_quality': 2, 'low_quality': 0}
         formats = []
         for format_key in ('mp4', 'webm'):

-            for qname, qurl in vdata[format_key].items():
+            for qname, qurl in vdata.get(format_key, {}).items():

                 formats.append({
                     'format_id': format_key + '_' + qname,
                     'url': qurl,
                 formats.append({
                     'format_id': format_key + '_' + qname,
                     'url': qurl,


@@ -58,6 +87,9 @@ class CollegeHumorIE(InfoExtractor):
                 })
         self._sort_formats(formats)
 
                 })
         self._sort_formats(formats)
 

+        duration = int_or_none(vdata.get('duration'), 1000)
+        like_count = int_or_none(vdata.get('likes'))
+

         return {
             'id': video_id,
             'title': vdata['title'],
         return {
             'id': video_id,
             'title': vdata['title'],


@@ -65,4 +97,6 @@ class CollegeHumorIE(InfoExtractor):
             'thumbnail': vdata.get('thumbnail'),
             'formats': formats,
             'age_limit': age_limit,
             'thumbnail': vdata.get('thumbnail'),
             'formats': formats,
             'age_limit': age_limit,

+            'duration': duration,
+            'like_count': like_count,

         }
         }