yt_dlp/extractor/rbgtum.py

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5
   6 class RbgTumIE(InfoExtractor):
   7     _VALID_URL = r'https://live\.rbg\.tum\.de/w/(?P<id>.+)'
   8     _TESTS = [{
   9         # Combined view
  10         'url': 'https://live.rbg.tum.de/w/cpp/22128',
  11         'md5': '53a5e7b3e07128e33bbf36687fe1c08f',
  12         'info_dict': {
  13             'id': 'cpp/22128',
  14             'ext': 'mp4',
  15             'title': 'Lecture: October 18. 2022',
  16             'series': 'Concepts of C++ programming (IN2377)',
  17         }
  18     }, {
  19         # Presentation only
  20         'url': 'https://live.rbg.tum.de/w/I2DL/12349/PRES',
  21         'md5': '36c584272179f3e56b0db5d880639cba',
  22         'info_dict': {
  23             'id': 'I2DL/12349/PRES',
  24             'ext': 'mp4',
  25             'title': 'Lecture 3: Introduction to Neural Networks',
  26             'series': 'Introduction to Deep Learning (IN2346)',
  27         }
  28     }, {
  29         # Camera only
  30         'url': 'https://live.rbg.tum.de/w/fvv-info/16130/CAM',
  31         'md5': 'e04189d92ff2f56aedf5cede65d37aad',
  32         'info_dict': {
  33             'id': 'fvv-info/16130/CAM',
  34             'ext': 'mp4',
  35             'title': 'Fachschaftsvollversammlung',
  36             'series': 'Fachschaftsvollversammlung Informatik',
  37         }
  38     }, ]
  39
  40     def _real_extract(self, url):
  41         video_id = self._match_id(url)
  42         webpage = self._download_webpage(url, video_id)
  43
  44         m3u8 = self._html_search_regex(r'(https://.+?\.m3u8)', webpage, 'm3u8')
  45         lecture_title = self._html_search_regex(r'(?si)<h1.*?>(.*)</h1>', webpage, 'title')
  46         lecture_series_title = self._html_search_regex(
  47             r'(?s)<title\b[^>]*>\s*(?:TUM-Live\s\|\s?)?([^:]+):?.*?</title>', webpage, 'series')
  48
  49         formats = self._extract_m3u8_formats(m3u8, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
  50
  51         return {
  52             'id': video_id,
  53             'title': lecture_title,
  54             'series': lecture_series_title,
  55             'formats': formats,
  56         }
  57
  58
  59 class RbgTumCourseIE(InfoExtractor):
  60     _VALID_URL = r'https://live\.rbg\.tum\.de/course/(?P<id>.+)'
  61     _TESTS = [{
  62         'url': 'https://live.rbg.tum.de/course/2022/S/fpv',
  63         'info_dict': {
  64             'title': 'Funktionale Programmierung und Verifikation (IN0003)',
  65             'id': '2022/S/fpv',
  66         },
  67         'params': {
  68             'noplaylist': False,
  69         },
  70         'playlist_count': 13,
  71     }, {
  72         'url': 'https://live.rbg.tum.de/course/2022/W/set',
  73         'info_dict': {
  74             'title': 'SET FSMPIC',
  75             'id': '2022/W/set',
  76         },
  77         'params': {
  78             'noplaylist': False,
  79         },
  80         'playlist_count': 6,
  81     }, ]
  82
  83     def _real_extract(self, url):
  84         course_id = self._match_id(url)
  85         webpage = self._download_webpage(url, course_id)
  86
  87         lecture_series_title = self._html_search_regex(r'(?si)<h1.*?>(.*)</h1>', webpage, 'title')
  88
  89         lecture_urls = []
  90         for lecture_url in re.findall(r'(?i)href="/w/(.+)(?<!/cam)(?<!/pres)(?<!/chat)"', webpage):
  91             lecture_urls.append(self.url_result('https://live.rbg.tum.de/w/' + lecture_url, ie=RbgTumIE.ie_key()))
  92
  93         return self.playlist_result(lecture_urls, course_id, lecture_series_title)