MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-24 21:56:53 +01:00
Code Issues Projects Releases Wiki Activity

fix test and remove lengthy description

Browse Source
This commit is contained in:
MaxReimann 2014-12-21 11:13:59 +01:00
parent ee45625290
commit 3f7421b71b
1 changed files with 2 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
youtube_dl/extractor/teletask.py
View File

@ -11,18 +11,12 @@ class TeleTaskIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?tele-task\.de/archive/video/html5/(?P<id>[0-9]+)/' _VALID_URL = r'http?://(?:www\.)?tele-task\.de/archive/video/html5/(?P<id>[0-9]+)/'
_TEST = { _TEST = {
'url': 'http://www.tele-task.de/archive/video/html5/26168/', 'url': 'http://www.tele-task.de/archive/video/html5/26168/',
'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)', 'md5': '290ef69fb2792e481169c3958dbfbd57',
'info_dict': { 'info_dict': {
'id': '26168', 'id': '26168',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Duplicate Detection', 'title': 'Duplicate Detection',
'thumbnail': 're:^https?://.*\.jpg$', 'upload_date': '20141218',
'date': '20141218',
# TODO more properties, either as:
# * A value
# * MD5 checksum; start the string with md5:
# * A regular expression; start the string with re:
# * Any Python type (for example int or float)
} }
} }
@ -30,19 +24,10 @@ def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
lecture_url = self._html_search_regex(
r'href="([^"]+)" itemprop="name">', webpage, 'title')
lecture_id = re.search("([0-9]+)/",lecture_url).group(1)
overview_page = self._download_webpage("http://www.tele-task.de" + lecture_url,
lecture_id)
title = self._html_search_regex( title = self._html_search_regex(
r'itemprop="name">([^"]+)</a>', webpage, 'title') r'itemprop="name">([^"]+)</a>', webpage, 'title')
url = self._html_search_regex( url = self._html_search_regex(
r'class="speaker".*?src="([^"]+)"', webpage, 'video_url', flags=re.DOTALL) r'class="speaker".*?src="([^"]+)"', webpage, 'video_url', flags=re.DOTALL)
description = self._html_search_regex(
r'Description of the series:</p>([^"]+)</div>', overview_page,
'description',flags=re.DOTALL)
date = self._html_search_regex( date = self._html_search_regex(
r'<td class="label">Date:</td><td>([^"]+)</td>', webpage, 'date') r'<td class="label">Date:</td><td>([^"]+)</td>', webpage, 'date')
@ -53,7 +38,6 @@ def _real_extract(self, url):
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'description': description,
'url': url, 'url': url,
'upload_date': date, 'upload_date': date,
} }