diff --git a/youtube_dl/extractor/teletask.py b/youtube_dl/extractor/teletask.py index b9e2ef8ca..2de5b3bc7 100644 --- a/youtube_dl/extractor/teletask.py +++ b/youtube_dl/extractor/teletask.py @@ -1,13 +1,11 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import unified_strdate class TeleTaskIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tele-task\.de/archive/video/html5/(?P[0-9]+)' + _VALID_URL = r'https?://(?:www\.)?tele-task\.de/(archive|lecture)/video/(html5/)?(?P[0-9]+)' _TEST = { 'url': 'http://www.tele-task.de/archive/video/html5/26168/', 'info_dict': { @@ -15,7 +13,7 @@ class TeleTaskIE(InfoExtractor): 'title': 'Duplicate Detection', }, 'playlist': [{ - 'md5': '290ef69fb2792e481169c3958dbfbd57', + 'md5': 'bc7b130ebb52acca59dfb7d96570dee3', 'info_dict': { 'id': '26168-speaker', 'ext': 'mp4', @@ -23,7 +21,7 @@ class TeleTaskIE(InfoExtractor): 'upload_date': '20141218', } }, { - 'md5': 'e1e7218c5f0e4790015a437fcf6c71b4', + 'md5': '22a2da392d2e6a257230cf578df4aed4', 'info_dict': { 'id': '26168-slides', 'ext': 'mp4', @@ -38,16 +36,32 @@ class TeleTaskIE(InfoExtractor): webpage = self._download_webpage(url, lecture_id) title = self._html_search_regex( - r'itemprop="name">([^<]+)', webpage, 'title') + r'([^<]+)', webpage, 'title') upload_date = unified_strdate(self._html_search_regex( r'Date:([^<]+)', webpage, 'date', fatal=False)) - entries = [{ - 'id': '%s-%s' % (lecture_id, format_id), + video_url = self._html_search_regex(r'(https(?:(?!https).)*?(?:hls/video\.m3u8))', webpage, 'video_url') + video_formats = self._extract_m3u8_formats( + video_url, lecture_id, 'mp4', fatal=False) + + desktop_url = video_url.replace('video', 'desktop') + desktop_formats = self._extract_m3u8_formats(desktop_url, lecture_id, 'mp4', fatal=False) + + entries = [] + entries.append({ + 'id': '%s-speaker' % (lecture_id), 'url': video_url, 'title': title, 'upload_date': upload_date, - } for format_id, video_url in re.findall( - r'