[videa] Improve and simplify (closes #8181, closes #11133)

youtube_dl/extractor/extractors.py

@@ -1064,10 +1064,7 @@ from .vice import (
 from .viceland import VicelandIE
 from .vidbit import VidbitIE
 from .viddler import ViddlerIE
-from .videa import (
+from .videa import VideaIE
-    VideaIE,
-    VideaEmbedIE,
-)
 from .videodetective import VideoDetectiveIE
 from .videofyme import VideofyMeIE
 from .videomega import VideoMegaIE

youtube_dl/extractor/videa.py

@@ -1,28 +1,32 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
-    parse_duration,
+    mimetype2ext,
+    parse_codecs,
     xpath_element,
     xpath_text,
-    xpath_attr,
-    urlencode_postdata,
-    unescapeHTML,
 )
 
 
 class VideaIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:.+?\.)?videa\.hu/videok/(?P<id>[^#?]+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        videa\.hu/
+                        (?:
+                            videok/(?:[^/]+/)*[^?#&]+-|
+                            player\?.*?\bv=|
+                            player/v/
+                        )
+                        (?P<id>[^?#&]+)
+                    '''
     _TESTS = [{
         'url': 'http://videa.hu/videok/allatok/az-orult-kigyasz-285-kigyot-kigyo-8YfIAjxwWGwT8HVQ',
         'md5': '97a7af41faeaffd9f1fc864a7c7e7603',
         'info_dict': {
             'id': '8YfIAjxwWGwT8HVQ',
-            'display_id': '8YfIAjxwWGwT8HVQ',
             'ext': 'mp4',
             'title': 'Az őrült kígyász 285 kígyót enged szabadon',
             'thumbnail': 'http://videa.hu/static/still/1.4.1.1007274.1204470.3',
@@ -31,68 +35,55 @@ class VideaIE(InfoExtractor):
     }, {
         'url': 'http://videa.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
         'only_matching': True,
+    }, {
+        'url': 'http://videa.hu/player?v=8YfIAjxwWGwT8HVQ',
+        'only_matching': True,
+    }, {
+        'url': 'http://videa.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        video_data = self._download_json("http://videa.hu/oembed/?" + urlencode_postdata({"url": url.split('?')[0], "format": "json"}), video_id)
+        info = self._download_xml(
-        video_url = self._search_regex(
+            'http://videa.hu/videaplayer_get_xml.php', video_id,
-            r'src="(.+?)"', video_data.get('html'), 'embed url')
+            query={'v': video_id})
+
+        video = xpath_element(info, './/video', 'video', fatal=True)
+        sources = xpath_element(info, './/video_sources', 'sources', fatal=True)
+
+        title = xpath_text(video, './title', fatal=True)
+
+        formats = []
+        for source in sources.findall('./video_source'):
+            source_url = source.text
+            if not source_url:
+                continue
+            f = parse_codecs(source.get('codecs'))
+            f.update({
+                'url': source_url,
+                'ext': mimetype2ext(source.get('mimetype')) or 'mp4',
+                'format_id': source.get('name'),
+                'width': int_or_none(source.get('width')),
+                'height': int_or_none(source.get('height')),
+            })
+            formats.append(f)
+        self._sort_formats(formats)
+
+        thumbnail = xpath_text(video, './poster_src')
+        duration = int_or_none(xpath_text(video, './duration'))
+
+        age_limit = None
+        is_adult = xpath_text(video, './is_adult_content', default=None)
+        if is_adult:
+            age_limit = 18 if is_adult == '1' else 0
 
         return {
-            '_type': 'url_transparent',
+            'id': video_id,
-            'url': video_url,
+            'title': title,
-            'ie_key': 'VideaEmbed'
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'age_limit': age_limit,
+            'formats': formats,
         }
-
-class VideaEmbedIE(InfoExtractor):
-    _VALID_URL = r'(?P<protocol>https?:)(?P<baseurl>//(?:.+?\.)?videa\.hu)/player(?:\?v=|/v/)(?P<id>[^/#?]+)';
-    _TESTS = [{
-        'url': 'http://videa.hu/player?v=8YfIAjxwWGwT8HVQ',
-        'md5': '97a7af41faeaffd9f1fc864a7c7e7603',
-        'info_dict': {
-            'id': '8YfIAjxwWGwT8HVQ',
-            'ext': 'mp4',
-            'title': 'Az őrült kígyász 285 kígyót enged szabadon',
-            'thumbnail': 'http://videa.hu/static/still/1.4.1.1007274.1204470.3',
-            'duration': 21
-        },
-    }, {
-        'url': 'http://videa.hu/player?v=jAHDWfWSJH5XuFhH',
-        'only_matching': True,
-    }];
-
-    @staticmethod
-    def _extract_url(webpage):
-        mobj = re.search(
-            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:.+?\.)?videa\.hu/player(?:\?v=|/v/)[^/#?]+)\1',
-            webpage)
-        if mobj:
-            return mobj.group('url')
-
-    def _real_extract(self, url):
-        protocol, base_url, display_id = re.search(self._VALID_URL, url).groups()
-        xml = self._download_xml(protocol + base_url + "/flvplayer_get_video_xml.php?v=" + display_id, display_id)
-
-        medias = []
-        
-        for xml_media in xml.findall('video') + xml.findall('audio'):
-            media_url = protocol + xpath_attr(xml_media, 'versions/version', 'video_url')
-            media = {
-                'id': display_id,
-                'ext': 'mp4',
-                'title': xpath_text(xml_media, 'title', 'title', True),
-                'duration': parse_duration(xpath_text(xml_media, 'duration')),
-                'thumbnail': protocol + xpath_text(xml_media, 'still', 'still', True),
-                'url': media_url,
-            }
-            medias.append(media)
-
-        if len(medias) > 1:
-            self._downloader.report_warning(
-                'found multiple medias; please '
-                'report this with the video URL to http://yt-dl.org/bug')
-        if not medias:
-            raise ExtractorError('No media entries found')
-        return medias[0]