[20detik] Extract 20detik embeds

youtube_dl/extractor/detik.py

@@ -0,0 +1,59 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class DuaPuluhDetikIE(InfoExtractor):
+    _VALID_URL = r'https?://20\.detik\.com/embed/(?P<video_id>\d+)'
+    IE_NAME = '20detik'
+    _TESTS = [{
+        'url': 'https://20.detik.com/embed/180403001?autostart=1',
+        'info_dict': {
+            'id': '180403001',
+            'title': 'Dahsyatnya Rudal Anti-balistik yang Diuji Coba Rusia',
+            'description': '',
+            'thumbnail': r're:^https?://.*\.jpg(\?.*)?$',
+            'ext': 'mp4'
+        }
+    }, {
+        'url': 'https://20.detik.com/embed/180326044',
+        'info_dict': {
+            'id': '180326044',
+            'title': 'md5:204cbc0b3b51b701ee9dc6a502f1e17b',
+            'description': 'md5:227d860110eda61876b243e23fe38538',
+            'thumbnail': r're:^https?://.*\.jpg(\?.*)?$',
+            'ext': 'mp4'
+        }
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('video_id')
+        webpage = self._download_webpage(url, video_id)
+        m3u8_url = self._html_search_regex(
+            r'["\']videoUrl["\']\s*:\s*["\'](?P<m3u8_url>.+)["\']',
+            webpage, 'm3u8_url')
+
+        if m3u8_url is None:
+            raise ExtractorError('Video not found')
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(
+            webpage, default='')
+        thumbnail = self._og_search_property(
+            'image', webpage)
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native')
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'formats': formats
+        }

youtube_dl/extractor/extractors.py

@@ -258,6 +258,7 @@ from .dbtv import DBTVIE
 from .dctp import DctpTvIE
 from .deezer import DeezerPlaylistIE
 from .democracynow import DemocracynowIE
+from .detik import DuaPuluhDetikIE
 from .dfb import DFBIE
 from .dhm import DHMIE
 from .digg import DiggIE

youtube_dl/extractor/generic.py

@@ -3155,11 +3155,6 @@ class GenericIE(InfoExtractor):
             if embed_url and embed_url != url:
                 return self.url_result(embed_url)
 
-        if not found:
-            # DetikFlow: It's basically a 'modified' FlowPlayer used in https://20.detik.com
-            found = re.findall(
-                r'["\']videoUrl["\']\s*:\s*["\']([^"\']+)["\']', webpage)
-
         if not found:
             raise UnsupportedError(url)