From c7bab7c39fd51c0812f70020172766303191bc01 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sun, 5 May 2024 19:37:42 +0200 Subject: Adding upstream version 2023.03.04. Signed-off-by: Daniel Baumann --- yt_dlp/extractor/lecture2go.py | 66 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 66 insertions(+) create mode 100644 yt_dlp/extractor/lecture2go.py (limited to 'yt_dlp/extractor/lecture2go.py') diff --git a/yt_dlp/extractor/lecture2go.py b/yt_dlp/extractor/lecture2go.py new file mode 100644 index 0000000..3a9b30a --- /dev/null +++ b/yt_dlp/extractor/lecture2go.py @@ -0,0 +1,66 @@ +import re + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + determine_protocol, + parse_duration, + int_or_none, +) + + +class Lecture2GoIE(InfoExtractor): + _VALID_URL = r'https?://lecture2go\.uni-hamburg\.de/veranstaltungen/-/v/(?P\d+)' + _TEST = { + 'url': 'https://lecture2go.uni-hamburg.de/veranstaltungen/-/v/17473', + 'md5': 'ac02b570883020d208d405d5a3fd2f7f', + 'info_dict': { + 'id': '17473', + 'ext': 'mp4', + 'title': '2 - Endliche Automaten und reguläre Sprachen', + 'creator': 'Frank Heitmann', + 'duration': 5220, + }, + 'params': { + # m3u8 download + 'skip_download': True, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex(r']+class="title">(.+)', webpage, 'title') + + formats = [] + for url in set(re.findall(r'var\s+playerUri\d+\s*=\s*"([^"]+)"', webpage)): + ext = determine_ext(url) + protocol = determine_protocol({'url': url}) + if ext == 'f4m': + formats.extend(self._extract_f4m_formats(url, video_id, f4m_id='hds')) + elif ext == 'm3u8': + formats.extend(self._extract_m3u8_formats(url, video_id, ext='mp4', m3u8_id='hls')) + else: + if protocol == 'rtmp': + continue # XXX: currently broken + formats.append({ + 'format_id': protocol, + 'url': url, + }) + + creator = self._html_search_regex( + r']+id="description">([^<]+)', webpage, 'creator', fatal=False) + duration = parse_duration(self._html_search_regex( + r'Duration:\s*\s*]*>([^<]+)', webpage, 'duration', fatal=False)) + view_count = int_or_none(self._html_search_regex( + r'Views:\s*\s*]+>(\d+)', webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'creator': creator, + 'duration': duration, + 'view_count': view_count, + } -- cgit v1.2.3