yt-dlp/youtube_dl/extractor/lecture2go.py

51 lines
1.5 KiB
Python
Raw Normal View History

2015-04-17 07:21:54 +00:00
# coding: utf-8
from __future__ import unicode_literals
2015-07-22 14:39:46 +00:00
import re
2015-04-17 07:21:54 +00:00
from .common import InfoExtractor
2015-07-22 14:39:46 +00:00
from ..utils import determine_ext
2015-04-17 07:21:54 +00:00
class Lecture2GoIE(InfoExtractor):
_VALID_URL = r'https?://lecture2go\.uni-hamburg\.de/veranstaltungen/-/v/(?P<id>\d+)'
2015-04-17 07:21:54 +00:00
_TEST = {
'url': 'https://lecture2go.uni-hamburg.de/veranstaltungen/-/v/17473',
2015-07-22 15:05:14 +00:00
'md5': 'ac02b570883020d208d405d5a3fd2f7f',
2015-04-17 07:21:54 +00:00
'info_dict': {
'id': '17473',
2015-07-22 15:05:14 +00:00
'ext': 'flv',
'title': '2 - Endliche Automaten und reguläre Sprachen',
'creator': 'Frank Heitmann',
2015-04-17 07:21:54 +00:00
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<em[^>]+class="title">(.+)</em>', webpage, 'title')
2015-07-22 14:39:46 +00:00
formats = []
for url in set(re.findall(r'"src","([^"]+)"', webpage)):
ext = determine_ext(url)
if ext == 'f4m':
formats.extend(self._extract_f4m_formats(url, video_id))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(url, video_id))
else:
formats.append({
'url': url,
})
self._sort_formats(formats)
creator = self._html_search_regex(r'<div[^>]+id="description">([^<]+)</div>', webpage, 'creator')
2015-04-17 07:21:54 +00:00
return {
'id': video_id,
'title': title,
2015-07-22 14:39:46 +00:00
'formats': formats,
2015-04-17 07:21:54 +00:00
'creator': creator
}