yt-dlp/yt_dlp/extractor/rtl2.py

96 lines
3.6 KiB
Python
Raw Permalink Normal View History

2015-08-21 07:20:32 +02:00
import re
2015-01-24 18:28:16 +01:00
from .common import InfoExtractor
from ..utils import int_or_none
2015-01-24 18:28:16 +01:00
class RTL2IE(InfoExtractor):
IE_NAME = 'rtl2'
2019-04-03 02:00:02 +02:00
_VALID_URL = r'https?://(?:www\.)?rtl2\.de/sendung/[^/]+/(?:video/(?P<vico_id>\d+)[^/]+/(?P<vivi_id>\d+)-|folge/)(?P<id>[^/?#]+)'
2015-01-24 18:28:16 +01:00
_TESTS = [{
'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0',
'info_dict': {
'id': 'folge-203-0',
'ext': 'f4v',
'title': 'GRIP sucht den Sommerkönig',
'description': 'md5:e3adbb940fd3c6e76fa341b8748b562f',
2015-01-24 18:28:16 +01:00
},
2015-08-21 07:00:08 +02:00
'params': {
# rtmp download
'skip_download': True,
},
2019-04-03 02:00:02 +02:00
'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
}, {
'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/',
'info_dict': {
2019-04-03 02:00:02 +02:00
'id': 'anna-erwischt-alex',
'ext': 'mp4',
'title': 'Anna erwischt Alex!',
'description': 'Anna nimmt ihrem Vater nicht ab, dass er nicht spielt. Und tatsächlich erwischt sie ihn auf frischer Tat.',
2015-01-24 18:28:16 +01:00
},
2015-08-21 07:20:32 +02:00
'params': {
# rtmp download
'skip_download': True,
},
2019-04-03 02:00:02 +02:00
'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
}]
2015-01-24 18:28:16 +01:00
def _real_extract(self, url):
vico_id, vivi_id, display_id = self._match_valid_url(url).groups()
2019-04-03 02:00:02 +02:00
if not vico_id:
webpage = self._download_webpage(url, display_id)
mobj = re.search(
r'data-collection="(?P<vico_id>\d+)"[^>]+data-video="(?P<vivi_id>\d+)"',
webpage)
if mobj:
vico_id = mobj.group('vico_id')
vivi_id = mobj.group('vivi_id')
else:
vico_id = self._html_search_regex(
r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id')
vivi_id = self._html_search_regex(
r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id')
2015-01-24 18:28:16 +01:00
info = self._download_json(
2019-04-03 02:00:02 +02:00
'https://service.rtl2.de/api-player-vipo/video.php',
display_id, query={
'vico_id': vico_id,
'vivi_id': vivi_id,
})
video_info = info['video']
title = video_info['titel']
2015-01-24 18:28:16 +01:00
formats = []
rtmp_url = video_info.get('streamurl')
if rtmp_url:
rtmp_url = rtmp_url.replace('\\', '')
stream_url = 'mp4:' + self._html_search_regex(r'/ondemand/(.+)', rtmp_url, 'stream URL')
rtmp_conn = ['S:connect', 'O:1', 'NS:pageUrl:' + url, 'NB:fpad:0', 'NN:videoFunction:1', 'O:0']
formats.append({
'format_id': 'rtmp',
'url': rtmp_url,
'play_path': stream_url,
2019-04-03 11:20:01 +02:00
'player_url': 'https://www.rtl2.de/sites/default/modules/rtl2/jwplayer/jwplayer-7.6.0/jwplayer.flash.swf',
'page_url': url,
'flash_version': 'LNX 11,2,202,429',
'rtmp_conn': rtmp_conn,
'no_resume': True,
'quality': 1,
})
m3u8_url = video_info.get('streamurl_hls')
if m3u8_url:
2019-04-03 02:00:02 +02:00
formats.extend(self._extract_akamai_formats(m3u8_url, display_id))
2015-01-24 18:28:16 +01:00
return {
2019-04-03 02:00:02 +02:00
'id': display_id,
2015-01-24 18:28:16 +01:00
'title': title,
'thumbnail': video_info.get('image'),
'description': video_info.get('beschreibung'),
'duration': int_or_none(video_info.get('duration')),
2015-01-24 18:28:16 +01:00
'formats': formats,
}