Update upstream source from tag 'upstream/2017.11.06'

[youtubedl] / youtube_dl / extractor / revision3.py

diff --git a/youtube_dl/extractor/revision3.py b/youtube_dl/extractor/revision3.py
index b1b8800b97c9eb8caad2c03f999f1bc8f304c4da..833d8a2f0d3813014224e39a8d2d41fb0e51d515 100644 (file)
--- a/youtube_dl/extractor/revision3.py
+++ b/youtube_dl/extractor/revision3.py
@@ -13,13 +13,69 @@ from ..utils import (
 )
 
 
 )
 
 

+class Revision3EmbedIE(InfoExtractor):
+    IE_NAME = 'revision3:embed'
+    _VALID_URL = r'(?:revision3:(?:(?P<playlist_type>[^:]+):)?|https?://(?:(?:(?:www|embed)\.)?(?:revision3|animalist)|(?:(?:api|embed)\.)?seekernetwork)\.com/player/embed\?videoId=)(?P<playlist_id>\d+)'
+    _TEST = {
+        'url': 'http://api.seekernetwork.com/player/embed?videoId=67558',
+        'md5': '83bcd157cab89ad7318dd7b8c9cf1306',
+        'info_dict': {
+            'id': '67558',
+            'ext': 'mp4',
+            'title': 'The Pros & Cons Of Zoos',
+            'description': 'Zoos are often depicted as a terrible place for animals to live, but is there any truth to this?',
+            'uploader_id': 'dnews',
+            'uploader': 'DNews',
+        }
+    }
+    _API_KEY = 'ba9c741bce1b9d8e3defcc22193f3651b8867e62'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('playlist_id')
+        playlist_type = mobj.group('playlist_type') or 'video_id'
+        video_data = self._download_json(
+            'http://revision3.com/api/getPlaylist.json', playlist_id, query={
+                'api_key': self._API_KEY,
+                'codecs': 'h264,vp8,theora',
+                playlist_type: playlist_id,
+            })['items'][0]
+
+        formats = []
+        for vcodec, media in video_data['media'].items():
+            for quality_id, quality in media.items():
+                if quality_id == 'hls':
+                    formats.extend(self._extract_m3u8_formats(
+                        quality['url'], playlist_id, 'mp4',
+                        'm3u8_native', m3u8_id='hls', fatal=False))
+                else:
+                    formats.append({
+                        'url': quality['url'],
+                        'format_id': '%s-%s' % (vcodec, quality_id),
+                        'tbr': int_or_none(quality.get('bitrate')),
+                        'vcodec': vcodec,
+                    })
+        self._sort_formats(formats)
+
+        return {
+            'id': playlist_id,
+            'title': unescapeHTML(video_data['title']),
+            'description': unescapeHTML(video_data.get('summary')),
+            'uploader': video_data.get('show', {}).get('name'),
+            'uploader_id': video_data.get('show', {}).get('slug'),
+            'duration': int_or_none(video_data.get('duration')),
+            'formats': formats,
+        }
+
+

 class Revision3IE(InfoExtractor):
 class Revision3IE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:revision3|testtube|animalist)\.com)/(?P<id>[^/]+(?:/[^/?#]+)?)'
+    IE_NAME = 'revision'
+    _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:revision3|animalist)\.com)/(?P<id>[^/]+(?:/[^/?#]+)?)'

     _TESTS = [{
         'url': 'http://www.revision3.com/technobuffalo/5-google-predictions-for-2016',
         'md5': 'd94a72d85d0a829766de4deb8daaf7df',
         'info_dict': {
     _TESTS = [{
         'url': 'http://www.revision3.com/technobuffalo/5-google-predictions-for-2016',
         'md5': 'd94a72d85d0a829766de4deb8daaf7df',
         'info_dict': {

-            'id': '73034',
+            'id': '71089',

             'display_id': 'technobuffalo/5-google-predictions-for-2016',
             'ext': 'webm',
             'title': '5 Google Predictions for 2016',
             'display_id': 'technobuffalo/5-google-predictions-for-2016',
             'ext': 'webm',
             'title': '5 Google Predictions for 2016',


@@ -31,89 +87,76 @@ class Revision3IE(InfoExtractor):
             'uploader_id': 'technobuffalo',
         }
     }, {
             'uploader_id': 'technobuffalo',
         }
     }, {

-        'url': 'http://testtube.com/brainstuff',
-        'info_dict': {
-            'id': '251',
-            'title': 'BrainStuff',
-            'description': 'Whether the topic is popcorn or particle physics, you can count on the HowStuffWorks team to explore-and explain-the everyday science in the world around us on BrainStuff.',
-        },
-        'playlist_mincount': 93,
+        # Show
+        'url': 'http://revision3.com/variant',
+        'only_matching': True,

     }, {
     }, {

-        'url': 'https://testtube.com/dnews/5-weird-ways-plants-can-eat-animals?utm_source=FB&utm_medium=DNews&utm_campaign=DNewsSocial',
-        'info_dict': {
-            'id': '60163',
-            'display_id': 'dnews/5-weird-ways-plants-can-eat-animals',
-            'duration': 275,
-            'ext': 'webm',
-            'title': '5 Weird Ways Plants Can Eat Animals',
-            'description': 'Why have some plants evolved to eat meat?',
-            'upload_date': '20150120',
-            'timestamp': 1421763300,
-            'uploader': 'DNews',
-            'uploader_id': 'dnews',
-        },
+        # Tag
+        'url': 'http://revision3.com/vr',
+        'only_matching': True,

     }]
     _PAGE_DATA_TEMPLATE = 'http://www.%s/apiProxy/ddn/%s?domain=%s'
     }]
     _PAGE_DATA_TEMPLATE = 'http://www.%s/apiProxy/ddn/%s?domain=%s'

-    _API_KEY = 'ba9c741bce1b9d8e3defcc22193f3651b8867e62'

 
     def _real_extract(self, url):
         domain, display_id = re.match(self._VALID_URL, url).groups()
 
     def _real_extract(self, url):
         domain, display_id = re.match(self._VALID_URL, url).groups()

+        site = domain.split('.')[0]

         page_info = self._download_json(
             self._PAGE_DATA_TEMPLATE % (domain, display_id, domain), display_id)
 
         page_info = self._download_json(
             self._PAGE_DATA_TEMPLATE % (domain, display_id, domain), display_id)
 

-        if page_info['data']['type'] == 'episode':
-            episode_data = page_info['data']
-            video_id = compat_str(episode_data['video']['data']['id'])
-            video_data = self._download_json(
-                'http://revision3.com/api/getPlaylist.json?api_key=%s&codecs=h264,vp8,theora&video_id=%s' % (self._API_KEY, video_id),
-                video_id)['items'][0]
-
-            formats = []
-            for vcodec, media in video_data['media'].items():
-                for quality_id, quality in media.items():
-                    if quality_id == 'hls':
-                        formats.extend(self._extract_m3u8_formats(
-                            quality['url'], video_id, 'mp4',
-                            'm3u8_native', m3u8_id='hls', fatal=False))
-                    else:
-                        formats.append({
-                            'url': quality['url'],
-                            'format_id': '%s-%s' % (vcodec, quality_id),
-                            'tbr': int_or_none(quality.get('bitrate')),
-                            'vcodec': vcodec,
-                        })
-            self._sort_formats(formats)
+        page_data = page_info['data']
+        page_type = page_data['type']
+        if page_type in ('episode', 'embed'):
+            show_data = page_data['show']['data']
+            page_id = compat_str(page_data['id'])
+            video_id = compat_str(page_data['video']['data']['id'])

 
             preference = qualities(['mini', 'small', 'medium', 'large'])
             thumbnails = [{
                 'url': image_url,
                 'id': image_id,
                 'preference': preference(image_id)
 
             preference = qualities(['mini', 'small', 'medium', 'large'])
             thumbnails = [{
                 'url': image_url,
                 'id': image_id,
                 'preference': preference(image_id)

-            } for image_id, image_url in video_data.get('images', {}).items()]
+            } for image_id, image_url in page_data.get('images', {}).items()]

 
 

-            return {
-                'id': video_id,
+            info = {
+                'id': page_id,

                 'display_id': display_id,
                 'display_id': display_id,

-                'title': unescapeHTML(video_data['title']),
-                'description': unescapeHTML(video_data.get('summary')),
-                'timestamp': parse_iso8601(episode_data.get('publishTime'), ' '),
-                'author': episode_data.get('author'),
-                'uploader': video_data.get('show', {}).get('name'),
-                'uploader_id': video_data.get('show', {}).get('slug'),
-                'duration': int_or_none(video_data.get('duration')),
+                'title': unescapeHTML(page_data['name']),
+                'description': unescapeHTML(page_data.get('summary')),
+                'timestamp': parse_iso8601(page_data.get('publishTime'), ' '),
+                'author': page_data.get('author'),
+                'uploader': show_data.get('name'),
+                'uploader_id': show_data.get('slug'),

                 'thumbnails': thumbnails,
                 'thumbnails': thumbnails,

-                'formats': formats,
+                'extractor_key': site,

             }
             }

+
+            if page_type == 'embed':
+                info.update({
+                    '_type': 'url_transparent',
+                    'url': page_data['video']['data']['embed'],
+                })
+                return info
+
+            info.update({
+                '_type': 'url_transparent',
+                'url': 'revision3:%s' % video_id,
+            })
+            return info

         else:
         else:

-            show_data = page_info['show']['data']
+            list_data = page_info[page_type]['data']

             episodes_data = page_info['episodes']['data']
             num_episodes = page_info['meta']['totalEpisodes']
             processed_episodes = 0
             entries = []
             page_num = 1
             while True:
             episodes_data = page_info['episodes']['data']
             num_episodes = page_info['meta']['totalEpisodes']
             processed_episodes = 0
             entries = []
             page_num = 1
             while True:

-                entries.extend([self.url_result(
-                    'http://%s/%s/%s' % (domain, display_id, episode['slug'])) for episode in episodes_data])
+                entries.extend([{
+                    '_type': 'url',
+                    'url': 'http://%s%s' % (domain, episode['path']),
+                    'id': compat_str(episode['id']),
+                    'ie_key': 'Revision3',
+                    'extractor_key': site,
+                } for episode in episodes_data])

                 processed_episodes += len(episodes_data)
                 if processed_episodes == num_episodes:
                     break
                 processed_episodes += len(episodes_data)
                 if processed_episodes == num_episodes:
                     break


@@ -123,5 +166,5 @@ class Revision3IE(InfoExtractor):
                     display_id)['episodes']['data']
 
             return self.playlist_result(
                     display_id)['episodes']['data']
 
             return self.playlist_result(

-                entries, compat_str(show_data['id']),
-                show_data.get('name'), show_data.get('summary'))
+                entries, compat_str(list_data['id']),
+                list_data.get('name'), list_data.get('summary'))