[unauthorizedtv] Add new extractor

youtube_dl/extractor/extractors.py

@@ -1246,6 +1246,7 @@ from .dlive import (
     DLiveStreamIE,
 )
 from .umg import UMGDeIE
+from .unauthorizedtv import UnauthorizedTvIE
 from .unistra import UnistraIE
 from .unity import UnityIE
 from .uol import UOLIE

youtube_dl/extractor/unauthorizedtv.py

@@ -0,0 +1,82 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class UnauthorizedTvIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?unauthorized\.tv/programs/(?P<id>.+)'
+    _TEST = {
+        'url': 'https://www.unauthorized.tv/programs/owens-shorts?cid=231148',
+        'md5': 'dd9a5b81b9704c68942c2584086dd73f',
+        'info_dict': {
+            'id': 'owens-shorts?cid=231148',
+            'ext': 'mp4',
+            'title': 'Millennials',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        cid = None
+
+        if "?cid=" in video_id:
+            cid = int(video_id[video_id.find('=') + 1:])
+
+        if self._downloader.params.get('verbose', False):
+            print(video_id)
+
+        html = self._download_webpage(url, video_id)
+
+        csrf_token = self._html_search_meta(
+            'csrf-token',
+            html,
+            'csrf token',
+            default=None
+        )
+
+        headers = {
+            'Referer': url,
+            'X-Requested-With': 'XMLHttpRequest',
+            'X-CSRF-Token': csrf_token,
+        }
+
+        chaptersJson = self._download_json(
+            'https://www.unauthorized.tv/api/contents/%s' % video_id,
+            video_id,
+            headers=headers
+        )
+
+        if self._downloader.params.get('verbose', False):
+            print(chaptersJson)
+
+        chapters = '&ids[]='.join([str(x) for x in chaptersJson['chapters']])
+
+        metadata = self._download_json(
+            'https://www.unauthorized.tv/api/chapters?ids[]=%s' % chapters,
+            video_id,
+            headers=headers
+        )
+
+        if cid is None:
+            video_title = metadata[0]['title']
+            video_url = metadata[0]['subject']['versions']['hls']
+        else:
+            for item in metadata:
+                if item["id"] == cid:
+                    video_title = item['title']
+                    video_url = item['subject']['versions']['hls']
+
+        if self._downloader.params.get('verbose', False):
+            print(metadata)
+            print(video_title)
+            print(video_url)
+
+        return {
+            'id': video_id,
+            'title': video_title,
+            'formats': [{
+                'url': video_url,
+                'ext': 'mp4',
+            }],
+        }