[rbgtum] Add new extractor (#31305)
authorValentin Metz <31850924+Valentin-Metz@users.noreply.github.com>
Thu, 9 Feb 2023 11:25:28 +0000 (12:25 +0100)
committerdirkf <fieldhouse@gmx.net>
Mon, 13 Feb 2023 03:54:51 +0000 (03:54 +0000)
* [rbgtum] Add new extractor

* Small update, force CI

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>
youtube_dl/extractor/extractors.py
youtube_dl/extractor/rbgtum.py [new file with mode: 0644]

index 96b27b179f711df473b5854764377a5df2f1ce74..dfaef0cc33f13170850018d564874f8415e4c93e 100644 (file)
@@ -1010,6 +1010,10 @@ from .raywenderlich import (
     RayWenderlichIE,
     RayWenderlichCourseIE,
 )
+from .rbgtum import (
+    RbgTumIE,
+    RbgTumCourseIE,
+)
 from .rbmaradio import RBMARadioIE
 from .rds import RDSIE
 from .redbulltv import (
diff --git a/youtube_dl/extractor/rbgtum.py b/youtube_dl/extractor/rbgtum.py
new file mode 100644 (file)
index 0000000..da48ebb
--- /dev/null
@@ -0,0 +1,97 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class RbgTumIE(InfoExtractor):
+    _VALID_URL = r'https://live\.rbg\.tum\.de/w/(?P<id>.+)'
+    _TESTS = [{
+        # Combined view
+        'url': 'https://live.rbg.tum.de/w/cpp/22128',
+        'md5': '53a5e7b3e07128e33bbf36687fe1c08f',
+        'info_dict': {
+            'id': 'cpp/22128',
+            'ext': 'mp4',
+            'title': 'Lecture: October 18. 2022',
+            'series': 'Concepts of C++ programming (IN2377)',
+        }
+    }, {
+        # Presentation only
+        'url': 'https://live.rbg.tum.de/w/I2DL/12349/PRES',
+        'md5': '36c584272179f3e56b0db5d880639cba',
+        'info_dict': {
+            'id': 'I2DL/12349/PRES',
+            'ext': 'mp4',
+            'title': 'Lecture 3: Introduction to Neural Networks',
+            'series': 'Introduction to Deep Learning (IN2346)',
+        }
+    }, {
+        # Camera only
+        'url': 'https://live.rbg.tum.de/w/fvv-info/16130/CAM',
+        'md5': 'e04189d92ff2f56aedf5cede65d37aad',
+        'info_dict': {
+            'id': 'fvv-info/16130/CAM',
+            'ext': 'mp4',
+            'title': 'Fachschaftsvollversammlung',
+            'series': 'Fachschaftsvollversammlung Informatik',
+        }
+    }, ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        m3u8 = self._html_search_regex(r'(https://.+?\.m3u8)', webpage, 'm3u8')
+        lecture_title = self._html_search_regex(r'(?si)<h1.*?>(.*)</h1>', webpage, 'title')
+        lecture_series_title = self._html_search_regex(
+            r'(?s)<title\b[^>]*>\s*(?:TUM-Live\s\|\s?)?([^:]+):?.*?</title>', webpage, 'series')
+
+        formats = self._extract_m3u8_formats(m3u8, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': lecture_title,
+            'series': lecture_series_title,
+            'formats': formats,
+        }
+
+
+class RbgTumCourseIE(InfoExtractor):
+    _VALID_URL = r'https://live\.rbg\.tum\.de/course/(?P<id>.+)'
+    _TESTS = [{
+        'url': 'https://live.rbg.tum.de/course/2022/S/fpv',
+        'info_dict': {
+            'title': 'Funktionale Programmierung und Verifikation (IN0003)',
+            'id': '2022/S/fpv',
+        },
+        'params': {
+            'noplaylist': False,
+        },
+        'playlist_count': 13,
+    }, {
+        'url': 'https://live.rbg.tum.de/course/2022/W/set',
+        'info_dict': {
+            'title': 'SET FSMPIC',
+            'id': '2022/W/set',
+        },
+        'params': {
+            'noplaylist': False,
+        },
+        'playlist_count': 6,
+    }, ]
+
+    def _real_extract(self, url):
+        course_id = self._match_id(url)
+        webpage = self._download_webpage(url, course_id)
+
+        lecture_series_title = self._html_search_regex(r'(?si)<h1.*?>(.*)</h1>', webpage, 'title')
+
+        lecture_urls = []
+        for lecture_url in re.findall(r'(?i)href="/w/(.+)(?<!/cam)(?<!/pres)(?<!/chat)"', webpage):
+            lecture_urls.append(self.url_result('https://live.rbg.tum.de/w/' + lecture_url, ie=RbgTumIE.ie_key()))
+
+        return self.playlist_result(lecture_urls, course_id, lecture_series_title)