debian/README.source: Change 'markup'.

[youtubedl] / youtube_dl / extractor / veoh.py

diff --git a/youtube_dl/extractor/veoh.py b/youtube_dl/extractor/veoh.py
index a7953a7e7c5d33b154435cd7b4afa354994f4bf5..1c44c145c66898134fa0294e53de15df16edc466 100644 (file)
--- a/youtube_dl/extractor/veoh.py
+++ b/youtube_dl/extractor/veoh.py
@@ -1,80 +1,57 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import re
-import json
-

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

-    compat_urllib_request,

     int_or_none,
     int_or_none,

-    ExtractorError,
+    parse_duration,
+    qualities,

 )
 
 
 class VeohIE(InfoExtractor):
 )
 
 
 class VeohIE(InfoExtractor):

-    _VALID_URL = r'http://(?:www\.)?veoh\.com/(?:watch|iphone/#_Watch)/(?P<id>(?:v|yapi-)[\da-zA-Z]+)'
+    _VALID_URL = r'https?://(?:www\.)?veoh\.com/(?:watch|embed|iphone/#_Watch)/(?P<id>(?:v|e|yapi-)[\da-zA-Z]+)'

 
 

-    _TESTS = [
-        {
-            'url': 'http://www.veoh.com/watch/v56314296nk7Zdmz3',
-            'md5': '620e68e6a3cff80086df3348426c9ca3',
-            'info_dict': {
-                'id': '56314296',
-                'ext': 'mp4',
-                'title': 'Straight Backs Are Stronger',
-                'uploader': 'LUMOback',
-                'description': 'At LUMOback, we believe straight backs are stronger.  The LUMOback Posture & Movement Sensor:  It gently vibrates when you slouch, inspiring improved posture and mobility.  Use the app to track your data and improve your posture over time. ',
-            },
+    _TESTS = [{
+        'url': 'http://www.veoh.com/watch/v56314296nk7Zdmz3',
+        'md5': '9e7ecc0fd8bbee7a69fe38953aeebd30',
+        'info_dict': {
+            'id': 'v56314296nk7Zdmz3',
+            'ext': 'mp4',
+            'title': 'Straight Backs Are Stronger',
+            'uploader': 'LUMOback',
+            'description': 'At LUMOback, we believe straight backs are stronger.  The LUMOback Posture & Movement Sensor:  It gently vibrates when you slouch, inspiring improved posture and mobility.  Use the app to track your data and improve your posture over time. ',

         },
         },

-        {
-            'url': 'http://www.veoh.com/watch/v27701988pbTc4wzN?h1=Chile+workers+cover+up+to+avoid+skin+damage',
-            'md5': '4a6ff84b87d536a6a71e6aa6c0ad07fa',
-            'info_dict': {
-                'id': '27701988',
-                'ext': 'mp4',
-                'title': 'Chile workers cover up to avoid skin damage',
-                'description': 'md5:2bd151625a60a32822873efc246ba20d',
-                'uploader': 'afp-news',
-                'duration': 123,
-            },
+    }, {
+        'url': 'http://www.veoh.com/embed/v56314296nk7Zdmz3',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.veoh.com/watch/v27701988pbTc4wzN?h1=Chile+workers+cover+up+to+avoid+skin+damage',
+        'md5': '4a6ff84b87d536a6a71e6aa6c0ad07fa',
+        'info_dict': {
+            'id': '27701988',
+            'ext': 'mp4',
+            'title': 'Chile workers cover up to avoid skin damage',
+            'description': 'md5:2bd151625a60a32822873efc246ba20d',
+            'uploader': 'afp-news',
+            'duration': 123,

         },
         },

-        {
-            'url': 'http://www.veoh.com/watch/v69525809F6Nc4frX',
-            'md5': '4fde7b9e33577bab2f2f8f260e30e979',
-            'note': 'Embedded ooyala video',
-            'info_dict': {
-                'id': '69525809',
-                'ext': 'mp4',
-                'title': 'Doctors Alter Plan For Preteen\'s Weight Loss Surgery',
-                'description': 'md5:f5a11c51f8fb51d2315bca0937526891',
-                'uploader': 'newsy-videos',
-            },
-            'skip': 'This video has been deleted.',
+        'skip': 'This video has been deleted.',
+    }, {
+        'url': 'http://www.veoh.com/watch/v69525809F6Nc4frX',
+        'md5': '4fde7b9e33577bab2f2f8f260e30e979',
+        'note': 'Embedded ooyala video',
+        'info_dict': {
+            'id': '69525809',
+            'ext': 'mp4',
+            'title': 'Doctors Alter Plan For Preteen\'s Weight Loss Surgery',
+            'description': 'md5:f5a11c51f8fb51d2315bca0937526891',
+            'uploader': 'newsy-videos',

         },
         },

-    ]
-
-    def _extract_formats(self, source):
-        formats = []
-        link = source.get('aowPermalink')
-        if link:
-            formats.append({
-                'url': link,
-                'ext': 'mp4',
-                'format_id': 'aow',
-            })
-        link = source.get('fullPreviewHashLowPath')
-        if link:
-            formats.append({
-                'url': link,
-                'format_id': 'low',
-            })
-        link = source.get('fullPreviewHashHighPath')
-        if link:
-            formats.append({
-                'url': link,
-                'format_id': 'high',
-            })
-        return formats
+        'skip': 'This video has been deleted.',
+    }, {
+        'url': 'http://www.veoh.com/watch/e152215AJxZktGS',
+        'only_matching': True,
+    }]

 
     def _extract_video(self, source):
         return {
 
     def _extract_video(self, source):
         return {


@@ -90,38 +67,37 @@ class VeohIE(InfoExtractor):
         }
 
     def _real_extract(self, url):
         }
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
-        if video_id.startswith('v'):
-            rsp = self._download_xml(
-                r'http://www.veoh.com/api/findByPermalink?permalink=%s' % video_id, video_id, 'Downloading video XML')
-            stat = rsp.get('stat')
-            if stat == 'ok':
-                return self._extract_video(rsp.find('./videoList/video'))
-            elif stat == 'fail':
-                raise ExtractorError(
-                    '%s said: %s' % (self.IE_NAME, rsp.find('./errorList/error').get('errorMessage')), expected=True)
-
-        webpage = self._download_webpage(url, video_id)
-        age_limit = 0
-        if 'class="adultwarning-container"' in webpage:
-            self.report_age_confirmation()
-            age_limit = 18
-            request = compat_urllib_request.Request(url)
-            request.add_header('Cookie', 'confirmedAdult=true')
-            webpage = self._download_webpage(request, video_id)
+        video_id = self._match_id(url)
+        video = self._download_json(
+            'https://www.veoh.com/watch/getVideo/' + video_id,
+            video_id)['video']
+        title = video['title']

 
 

-        m_youtube = re.search(r'http://www\.youtube\.com/v/(.*?)(\&|"|\?)', webpage)
-        if m_youtube is not None:
-            youtube_id = m_youtube.group(1)
-            self.to_screen('%s: detected Youtube video.' % video_id)
-            return self.url_result(youtube_id, 'Youtube')
-
-        info = json.loads(
-            self._search_regex(r'videoDetailsJSON = \'({.*?})\';', webpage, 'info').replace('\\\'', '\''))
-
-        video = self._extract_video(info)
-        video['age_limit'] = age_limit
+        thumbnail_url = None
+        q = qualities(['HQ', 'Regular'])
+        formats = []
+        for f_id, f_url in video.get('src', {}).items():
+            if not f_url:
+                continue
+            if f_id == 'poster':
+                thumbnail_url = f_url
+            else:
+                formats.append({
+                    'format_id': f_id,
+                    'quality': q(f_id),
+                    'url': f_url,
+                })
+        self._sort_formats(formats)

 
 

-        return video
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video.get('description'),
+            'thumbnail': thumbnail_url,
+            'uploader': video.get('author', {}).get('nickname'),
+            'duration': int_or_none(video.get('lengthBySec')) or parse_duration(video.get('length')),
+            'view_count': int_or_none(video.get('views')),
+            'formats': formats,
+            'average_rating': int_or_none(video.get('rating')),
+            'comment_count': int_or_none(video.get('numOfComments')),
+        }