1 files changed, 56 insertions, 0 deletions
diff --git a/yt_dlp/extractor/bpb.py b/yt_dlp/extractor/bpb.py
new file mode 100644
index 0000000..f28e581
--- /dev/null
+++ b/yt_dlp/extractor/bpb.py
@@ -0,0 +1,56 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+    determine_ext,
+)
+
+
+class BpbIE(InfoExtractor):
+    IE_DESC = 'Bundeszentrale für politische Bildung'
+    _VALID_URL = r'https?://(?:www\.)?bpb\.de/mediathek/(?P<id>[0-9]+)/'
+
+    _TEST = {
+        'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr',
+        'md5': 'c4f84c8a8044ca9ff68bb8441d300b3f',
+        'info_dict': {
+            'id': '297',
+            'ext': 'mp4',
+            'title': 'Joachim Gauck zu 1989 und die Erinnerung an die DDR',
+            'description': 'Joachim Gauck, erster Beauftragter für die Stasi-Unterlagen, spricht auf dem Geschichtsforum über die friedliche Revolution 1989 und eine "gewisse Traurigkeit" im Umgang mit der DDR-Vergangenheit.'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(
+            r'<h2 class="white">(.*?)</h2>', webpage, 'title')
+        video_info_dicts = re.findall(
+            r"({\s*src\s*:\s*'https?://film\.bpb\.de/[^}]+})", webpage)
+
+        formats = []
+        for video_info in video_info_dicts:
+            video_info = self._parse_json(
+                video_info, video_id, transform_source=js_to_json, fatal=False)
+            if not video_info:
+                continue
+            video_url = video_info.get('src')
+            if not video_url:
+                continue
+            quality = 'high' if '_high' in video_url else 'low'
+            formats.append({
+                'url': video_url,
+                'quality': 10 if quality == 'high' else 0,
+                'format_note': quality,
+                'format_id': '%s-%s' % (quality, determine_ext(video_url)),
+            })
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title,
+            'description': self._og_search_description(webpage),
+        }