yt-dlp/yt_dlp/extractor/lecture2go.py

72 lines
2.3 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 15:22:19 +00:00
from ..utils import (
determine_ext,
determine_protocol,
2015-07-22 15:22:19 +00:00
parse_duration,
int_or_none,
)
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',
'ext': 'mp4',
2015-07-22 15:05:14 +00:00
'title': '2 - Endliche Automaten und reguläre Sprachen',
'creator': 'Frank Heitmann',
2015-07-22 15:22:19 +00:00
'duration': 5220,
},
'params': {
# m3u8 download
'skip_download': True,
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'var\s+playerUri\d+\s*=\s*"([^"]+)"', webpage)):
2015-07-22 14:39:46 +00:00
ext = determine_ext(url)
protocol = determine_protocol({'url': url})
2015-07-22 14:39:46 +00:00
if ext == 'f4m':
formats.extend(self._extract_f4m_formats(url, video_id, f4m_id='hds'))
2015-07-22 14:39:46 +00:00
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(url, video_id, ext='mp4', m3u8_id='hls'))
2015-07-22 14:39:46 +00:00
else:
if protocol == 'rtmp':
continue # XXX: currently broken
2015-07-22 14:39:46 +00:00
formats.append({
'format_id': protocol,
2015-07-22 14:39:46 +00:00
'url': url,
})
self._sort_formats(formats)
creator = self._html_search_regex(
r'<div[^>]+id="description">([^<]+)</div>', webpage, 'creator', fatal=False)
2015-07-22 15:22:19 +00:00
duration = parse_duration(self._html_search_regex(
r'Duration:\s*</em>\s*<em[^>]*>([^<]+)</em>', webpage, 'duration', fatal=False))
view_count = int_or_none(self._html_search_regex(
r'Views:\s*</em>\s*<em[^>]+>(\d+)</em>', webpage, 'view count', fatal=False))
2015-04-17 07:21:54 +00:00
return {
'id': video_id,
'title': title,
2015-07-22 14:39:46 +00:00
'formats': formats,
2015-07-22 15:22:19 +00:00
'creator': creator,
'duration': duration,
'view_count': view_count,
2015-04-17 07:21:54 +00:00
}