ytdl/youtube_dl/extractor/rtl2.py
2015-01-25 18:09:48 +01:00

73 lines
2.6 KiB
Python

# encoding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class RTL2IE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?rtl2\.de/[^?#]*?/(?P<id>[^?#/]*?)(?:$|/(?:$|[?#]))'
_TESTS = [{
'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0',
'md5': 'bfcc179030535b08dc2b36b469b5adc7',
'info_dict': {
'id': 'folge-203-0',
'ext': 'f4v',
'title': 'GRIP sucht den Sommerkönig',
'description': 'Matthias, Det und Helge treten gegeneinander an.'
},
}, {
'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/',
'md5': 'ffcd517d2805b57ce11a58a2980c2b02',
'info_dict': {
'id': '21040-anna-erwischt-alex',
'ext': 'mp4',
'title': 'Anna erwischt Alex!',
'description': 'Anna ist Alex\' Tochter bei Köln 50667.'
},
}]
def _real_extract(self, url):
# Some rtl2 urls have no slash at the end, so append it.
if not url.endswith('/'):
url += '/'
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
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')
info_url = 'http://www.rtl2.de/video/php/get_video.php?vico_id=' + vico_id + '&vivi_id=' + vivi_id
webpage = self._download_webpage(info_url, '')
info = self._download_json(info_url, video_id)
video_info = info['video']
title = video_info['titel']
description = video_info.get('beschreibung')
thumbnail = video_info.get('image')
download_url = video_info['streamurl']
download_url = download_url.replace('\\', '')
stream_url = 'mp4:' + self._html_search_regex(r'ondemand/(.*)', download_url, 'stream URL')
rtmp_conn = ["S:connect", "O:1", "NS:pageUrl:" + url, "NB:fpad:0", "NN:videoFunction:1", "O:0"]
formats = [{
'url': download_url,
'play_path': stream_url,
'player_url': 'http://www.rtl2.de/flashplayer/vipo_player.swf',
'page_url': url,
'flash_version': 'LNX 11,2,202,429',
'rtmp_conn': rtmp_conn,
'no_resume': True,
}]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'description': description,
'formats': formats,
}