[indavideo] Split in two extractors, extract all formats and fix timestamp

youtube_dl/extractor/__init__.py

@@ -242,7 +242,10 @@
 )
 from .imgur import ImgurIE
 from .ina import InaIE
-from .indavideo import IndavideoIE
+from .indavideo import (
+    IndavideoIE,
+    IndavideoEmbedIE,
+)
 from .infoq import InfoQIE
 from .instagram import InstagramIE, InstagramUserIE
 from .internetvideoarchive import InternetVideoArchiveIE

youtube_dl/extractor/indavideo.py

@@ -3,77 +3,127 @@
 
 from .. import utils
 from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_age_limit,
+    parse_iso8601,
+)
+
+
+class IndavideoEmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:embed\.)?indavideo\.hu/player/video/|assets\.indavideo\.hu/swf/player\.swf\?.*\b(?:v(?:ID|id))=)(?P<id>[\da-f]+)'
+    _TESTS = [{
+        'url': 'http://indavideo.hu/player/video/1bdc3c6d80/',
+        'md5': 'f79b009c66194acacd40712a6778acfa',
+        'info_dict': {
+            'id': '1837039',
+            'ext': 'mp4',
+            'title': 'Cicatánc',
+            'description': '',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'cukiajanlo',
+            'uploader_id': '83729',
+            'timestamp': 1439193826,
+            'upload_date': '20150810',
+            'duration': 72,
+            'age_limit': 0,
+            'tags': ['tánc', 'cica', 'cuki', 'cukiajanlo', 'newsroom'],
+        },
+    }, {
+        'url': 'http://embed.indavideo.hu/player/video/1bdc3c6d80?autostart=1&hide=1',
+        'only_matching': True,
+    }, {
+        'url': 'http://assets.indavideo.hu/swf/player.swf?v=fe25e500&vID=1bdc3c6d80&autostart=1&hide=1&i=1',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video = self._download_json(
+            'http://amfphp.indavideo.hu/SYm0json.php/player.playerHandler.getVideoData/%s' % video_id,
+            video_id)['data']
+
+        video_id = video['id']
+        title = video['title']
+
+        video_urls = video.get('video_files', [])
+        video_file = video.get('video_file')
+        if video:
+            video_urls.append(video_file)
+        video_urls = list(set(video_urls))
+
+        video_prefix = video_urls[0].rsplit('/', 1)[0]
+
+        for flv_file in video.get('flv_files', []):
+            flv_url = '%s/%s' % (video_prefix, flv_file)
+            if flv_url not in video_urls:
+                video_urls.append(flv_url)
+
+        formats = [{
+            'url': video_url,
+            'height': self._search_regex(r'\.(\d{3,4})\.mp4$', video_url, 'height', default=None),
+        } for video_url in video_urls]
+        self._sort_formats(formats)
+
+        timestamp = video.get('date')
+        if timestamp:
+            # upload date is in CEST
+            timestamp = parse_iso8601(timestamp + ' +0200', ' ')
+
+        thumbnails = [{
+            'url': self._proto_relative_url(thumbnail)
+        } for thumbnail in video.get('thumbnails', [])]
+
+        tags = [tag['title'] for tag in video.get('tags', [])]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video.get('description'),
+            'thumbnails': thumbnails,
+            'uploader': video.get('user_name'),
+            'uploader_id': video.get('user_id'),
+            'timestamp': timestamp,
+            'duration': int_or_none(video.get('length')),
+            'age_limit': parse_age_limit(video.get('age_limit')),
+            'tags': tags,
+            'formats': formats,
+        }
 
 
 class IndavideoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?indavideo\.hu/video/(?P<id>.+)'
+    _VALID_URL = r'https?://(?:www\.)?indavideo\.hu/video/(?P<id>[^/#?]+)'
-    _TESTS = [
+    _TEST = {
-        {
-            'url': 'http://indavideo.hu/video/Cicatanc',
-            'md5': 'c8a507a1c7410685f83a06eaeeaafeab',
-            'info_dict': {
-                'id': '1837039',
-                'title': 'Cicatánc',
-                'ext': 'mp4',
-                'display_id': 'Cicatanc',
-                'thumbnail': 're:^https?://.*\.jpg$',
-                'description': '',
-                'uploader': 'cukiajanlo',
-                'uploader_id': '83729',
-                'duration': 72,
-                'age_limit': 0,
-                'tags': ['tánc', 'cica', 'cuki', 'cukiajanlo', 'newsroom']
-            },
-        },
-        {
         'url': 'http://indavideo.hu/video/Vicces_cica_1',
         'md5': '8c82244ba85d2a2310275b318eb51eac',
         'info_dict': {
             'id': '1335611',
-                'title': 'Vicces cica',
-                'ext': 'mp4',
             'display_id': 'Vicces_cica_1',
-                'thumbnail': 're:^https?://.*\.jpg$',
+            'ext': 'mp4',
+            'title': 'Vicces cica',
             'description': 'Játszik a tablettel. :D',
+            'thumbnail': 're:^https?://.*\.jpg$',
             'uploader': 'Jet_Pack',
             'uploader_id': '491217',
+            'timestamp': 1390821212,
+            'upload_date': '20140127',
             'duration': 7,
             'age_limit': 0,
             'tags': ['vicces', 'macska', 'cica', 'ügyes', 'nevetés', 'játszik', 'Cukiság', 'Jet_Pack'],
         },
-        },
+    }
-    ]
 
     def _real_extract(self, url):
-        video_disp_id = self._match_id(url)
+        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_disp_id)
 
-        embed_url = self._html_search_regex(r'<link rel="video_src" href="(.+?)"/>', webpage, 'embed_url')
+        webpage = self._download_webpage(url, display_id)
-        video_hash = embed_url.split('/')[-1]
+        embed_url = self._search_regex(
-
+            r'<link[^>]+rel="video_src"[^>]+href="(.+?)"', webpage, 'embed url')
-        payload = self._download_json('http://amfphp.indavideo.hu/SYm0json.php/player.playerHandler.getVideoData/' + video_hash, video_disp_id)
-        video_info = payload['data']
-
-        thumbnails = video_info.get('thumbnails')
-        if thumbnails:
-            thumbnails = [{'url': self._proto_relative_url(x)} for x in thumbnails]
-
-        tags = video_info.get('tags')
-        if tags:
-            tags = [x['title'] for x in tags]
 
         return {
-            'id': video_info.get('id'),
+            '_type': 'url_transparent',
-            'title': video_info['title'],
+            'ie_key': 'IndavideoEmbed',
-            'url': video_info['video_file'],
+            'url': embed_url,
-            'ext': 'mp4',
+            'display_id': display_id,
-            'display_id': video_disp_id,
-            'thumbnails': thumbnails,
-            'description': video_info.get('description'),
-            'uploader': video_info.get('user_name'),
-            # TODO: upload date (it's in CET/CEST)
-            'uploader_id': video_info.get('user_id'),
-            'duration': utils.int_or_none(video_info.get('length')),
-            'age_limit': utils.int_or_none(video_info.get('age_limit')),
-            'tags': tags,
         }