Merge tag 'upstream/2015.05.15'

[youtubedl] / youtube_dl / extractor / viddler.py

diff --git a/youtube_dl/extractor/viddler.py b/youtube_dl/extractor/viddler.py
index 826804af37af54e308f90349e909d3e0e3aa5126..8516a2940cb38c7e030e504e6a29f88fcd3946a1 100644 (file)
--- a/youtube_dl/extractor/viddler.py
+++ b/youtube_dl/extractor/viddler.py
@@ -1,64 +1,118 @@
-import json
-import re
+from __future__ import unicode_literals

 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (

-    determine_ext,
+    float_or_none,
+    int_or_none,
+)
+from ..compat import (
+    compat_urllib_request

 )
 
 
 class ViddlerIE(InfoExtractor):
 )
 
 
 class ViddlerIE(InfoExtractor):

-    _VALID_URL = r'(?P<domain>https?://(?:www\.)?viddler.com)/(?:v|embed|player)/(?P<id>[a-z0-9]+)'
-    _TEST = {
-        u"url": u"http://www.viddler.com/v/43903784",
-        u'file': u'43903784.mp4',
-        u'md5': u'fbbaedf7813e514eb7ca30410f439ac9',
-        u'info_dict': {
-            u"title": u"Video Made Easy",
-            u"uploader": u"viddler",
-            u"duration": 100.89,
+    _VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P<id>[a-z0-9]+)'
+    _TESTS = [{
+        'url': 'http://www.viddler.com/v/43903784',
+        'md5': 'ae43ad7cb59431ce043f0ff7fa13cbf4',
+        'info_dict': {
+            'id': '43903784',
+            'ext': 'mp4',
+            'title': 'Video Made Easy',
+            'description': 'md5:6a697ebd844ff3093bd2e82c37b409cd',
+            'uploader': 'viddler',
+            'timestamp': 1335371429,
+            'upload_date': '20120425',
+            'duration': 100.89,
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'view_count': int,
+            'comment_count': int,
+            'categories': ['video content', 'high quality video', 'video made easy', 'how to produce video with limited resources', 'viddler'],
+        }
+    }, {
+        'url': 'http://www.viddler.com/v/4d03aad9/',
+        'md5': 'faa71fbf70c0bee7ab93076fd007f4b0',
+        'info_dict': {
+            'id': '4d03aad9',
+            'ext': 'mp4',
+            'title': 'WALL-TO-GORTAT',
+            'upload_date': '20150126',
+            'uploader': 'deadspin',
+            'timestamp': 1422285291,
+            'view_count': int,
+            'comment_count': int,
+        }
+    }, {
+        'url': 'http://www.viddler.com/player/221ebbbd/0/',
+        'md5': '0defa2bd0ea613d14a6e9bd1db6be326',
+        'info_dict': {
+            'id': '221ebbbd',
+            'ext': 'mp4',
+            'title': 'LETeens-Grammar-snack-third-conditional',
+            'description': ' ',
+            'upload_date': '20140929',
+            'uploader': 'BCLETeens',
+            'timestamp': 1411997190,
+            'view_count': int,
+            'comment_count': int,

         }
         }

-    }
+    }]

 
     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 = mobj.group('domain') + u'/embed/' + video_id
-        webpage = self._download_webpage(embed_url, video_id)
+        json_url = (
+            'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json?video_id=%s&key=v0vhrt7bg2xq1vyxhkct' %
+            video_id)
+        headers = {'Referer': 'http://static.cdn-ec.viddler.com/js/arpeggio/v2/embed.html'}
+        request = compat_urllib_request.Request(json_url, None, headers)
+        data = self._download_json(request, video_id)['video']

 
 

-        video_sources_code = self._search_regex(
-            r"(?ms)sources\s*:\s*(\{.*?\})", webpage, u'video URLs')
-        video_sources = json.loads(video_sources_code.replace("'", '"'))
+        formats = []
+        for filed in data['files']:
+            if filed.get('status', 'ready') != 'ready':
+                continue
+            format_id = filed.get('profile_id') or filed['profile_name']
+            f = {
+                'format_id': format_id,
+                'format_note': filed['profile_name'],
+                'url': self._proto_relative_url(filed['url']),
+                'width': int_or_none(filed.get('width')),
+                'height': int_or_none(filed.get('height')),
+                'filesize': int_or_none(filed.get('size')),
+                'ext': filed.get('ext'),
+                'source_preference': -1,
+            }
+            formats.append(f)

 
 

-        formats = [{
-            'url': video_url,
-            'format': format_id,
-        } for video_url, format_id in video_sources.items()]
+            if filed.get('cdn_url'):
+                f = f.copy()
+                f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:')
+                f['format_id'] = format_id + '-cdn'
+                f['source_preference'] = 1
+                formats.append(f)

 
 

-        title = self._html_search_regex(
-            r"title\s*:\s*'([^']*)'", webpage, u'title')
-        uploader = self._html_search_regex(
-            r"authorName\s*:\s*'([^']*)'", webpage, u'uploader', fatal=False)
-        duration_s = self._html_search_regex(
-            r"duration\s*:\s*([0-9.]*)", webpage, u'duration', fatal=False)
-        duration = float(duration_s) if duration_s else None
-        thumbnail = self._html_search_regex(
-            r"thumbnail\s*:\s*'([^']*)'",
-            webpage, u'thumbnail', fatal=False)
+            if filed.get('html5_video_source'):
+                f = f.copy()
+                f['url'] = self._proto_relative_url(filed['html5_video_source'])
+                f['format_id'] = format_id + '-html5'
+                f['source_preference'] = 0
+                formats.append(f)
+        self._sort_formats(formats)

 
 

-        info = {
-            '_type': 'video',
+        categories = [
+            t.get('text') for t in data.get('tags', []) if 'text' in t]
+
+        return {

             'id': video_id,
             'id': video_id,

-            'title': title,
-            'thumbnail': thumbnail,
-            'uploader': uploader,
-            'duration': duration,
+            'title': data['title'],

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

+            'description': data.get('description'),
+            'timestamp': int_or_none(data.get('upload_time')),
+            'thumbnail': self._proto_relative_url(data.get('thumbnail_url')),
+            'uploader': data.get('author'),
+            'duration': float_or_none(data.get('length')),
+            'view_count': int_or_none(data.get('view_count')),
+            'comment_count': int_or_none(data.get('comment_count')),
+            'categories': categories,

         }
         }

-
-        # TODO: Remove when #980 has been merged
-        info['formats'][-1]['ext'] = determine_ext(info['formats'][-1]['url'])
-        info.update(info['formats'][-1])
-
-        return info