X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fteletask.py;h=b9e2ef8cab9a0e3a63bf5a46baf2b70a39afa1cb;hb=56667d622c3f6e7594a04f8cd5f4371875940725;hp=1c42ac6f4abcd01f0d805522b4aa43e5ff82c9ba;hpb=ee45625290c678c53b7ee86d2adba40847b79573;p=youtube-dl
diff --git a/youtube_dl/extractor/teletask.py b/youtube_dl/extractor/teletask.py
index 1c42ac6f4..b9e2ef8ca 100644
--- a/youtube_dl/extractor/teletask.py
+++ b/youtube_dl/extractor/teletask.py
@@ -1,59 +1,53 @@
-# coding: utf-8
from __future__ import unicode_literals
-import re
-import datetime
+import re
from .common import InfoExtractor
+from ..utils import unified_strdate
class TeleTaskIE(InfoExtractor):
- _VALID_URL = r'http?://(?:www\.)?tele-task\.de/archive/video/html5/(?P[0-9]+)/'
+ _VALID_URL = r'https?://(?:www\.)?tele-task\.de/archive/video/html5/(?P[0-9]+)'
_TEST = {
- '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)',
+ 'url': 'http://www.tele-task.de/archive/video/html5/26168/',
'info_dict': {
'id': '26168',
- 'ext': 'mp4',
'title': 'Duplicate Detection',
- 'thumbnail': 're:^https?://.*\.jpg$',
- '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)
- }
+ },
+ 'playlist': [{
+ 'md5': '290ef69fb2792e481169c3958dbfbd57',
+ 'info_dict': {
+ 'id': '26168-speaker',
+ 'ext': 'mp4',
+ 'title': 'Duplicate Detection',
+ 'upload_date': '20141218',
+ }
+ }, {
+ 'md5': 'e1e7218c5f0e4790015a437fcf6c71b4',
+ 'info_dict': {
+ 'id': '26168-slides',
+ 'ext': 'mp4',
+ 'title': 'Duplicate Detection',
+ 'upload_date': '20141218',
+ }
+ }]
}
def _real_extract(self, url):
- video_id = self._match_id(url)
- 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)
-
+ lecture_id = self._match_id(url)
+ webpage = self._download_webpage(url, lecture_id)
+
title = self._html_search_regex(
- r'itemprop="name">([^"]+)', webpage, 'title')
- url = self._html_search_regex(
- r'class="speaker".*?src="([^"]+)"', webpage, 'video_url', flags=re.DOTALL)
- description = self._html_search_regex(
- r'Description of the series:
([^"]+)', overview_page,
- 'description',flags=re.DOTALL)
-
- date = self._html_search_regex(
- r'Date: | ([^"]+) | ', webpage, 'date')
- date = datetime.datetime.strptime(date, '%d.%m.%Y').strftime('%Y%m%d')
-
-
-
- return {
- 'id': video_id,
+ r'itemprop="name">([^<]+)', webpage, 'title')
+ upload_date = unified_strdate(self._html_search_regex(
+ r'Date:([^<]+) | ', webpage, 'date', fatal=False))
+
+ entries = [{
+ 'id': '%s-%s' % (lecture_id, format_id),
+ 'url': video_url,
'title': title,
- 'description': description,
- 'url': url,
- 'upload_date': date,
- }
\ No newline at end of file
+ 'upload_date': upload_date,
+ } for format_id, video_url in re.findall(
+ r'