From fe41ddbb285abccc3c4d7a3ebc1238c13ec72577 Mon Sep 17 00:00:00 2001 From: David Development Date: Sun, 25 Jan 2015 11:53:53 +0100 Subject: [PATCH] refactoring - bug fixes --- youtube_dl/extractor/rtl2.py | 66 ++++++++++++++++++------------------ 1 file changed, 33 insertions(+), 33 deletions(-) diff --git a/youtube_dl/extractor/rtl2.py b/youtube_dl/extractor/rtl2.py index 14b45e86e..7086d698f 100644 --- a/youtube_dl/extractor/rtl2.py +++ b/youtube_dl/extractor/rtl2.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor from ..utils import ( @@ -14,82 +13,83 @@ from ..utils import ( class RTL2IE(InfoExtractor): - """Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW""" - _VALID_URL = r'http?://(?P(?P(www\.)?rtl2\.de)/.*/(?P.*))' + """Information Extractor for RTL2""" + _VALID_URL = r'http?://(?P(?P(www\.)?rtl2\.de)/.*/(?P.*))/' _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 Sommerk\xf6nig', + 'title': 'GRIP sucht den Sommerkönig', 'description' : 'Matthias, Det und Helge treten gegeneinander an.' }, 'params': { # rtmp download - #'skip_download': True, + 'skip_download': True, }, }, { 'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/', 'info_dict': { 'id': '21040-anna-erwischt-alex', - 'ext': 'f4v', - 'title': 'GRIP sucht den Sommerk\xf6nig', - 'description' : 'Matthias, Det und Helge treten gegeneinander an.' + 'ext': 'mp4', + 'title': 'Anna erwischt Alex!', + 'description' : 'Anna ist Alex\' Tochter bei Köln 50667.' }, 'params': { # rtmp download - #'skip_download': True, + 'skip_download': True, }, }, ] def _real_extract(self, url): + + #Some rtl2 urls have no slash at the end, so append it. + if not url.endswith("/"): + url += '/' + mobj = re.match(self._VALID_URL, url) - video_page_url = 'http://%s/' % mobj.group('domain') video_id = mobj.group('video_id') - - webpage = self._download_webpage('http://' + mobj.group('url'), video_id) - vico_id = self._html_search_regex(r'vico_id\s*:\s*([0-9]+)', webpage, '%s'); - vivi_id = self._html_search_regex(r'vivi_id\s*:\s*([0-9]+)', webpage, '%s'); + webpage = self._download_webpage(url, video_id) + + vico_id = self._html_search_regex(r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id not found'); + vivi_id = self._html_search_regex(r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id not found'); 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, '') - video_info = json.loads(webpage) + video_info = self._download_json(info_url, video_id) - download_url = video_info["video"]["streamurl"] # self._html_search_regex(r'streamurl\":\"(.*?)\"', webpage, '%s'); - title = video_info["video"]["titel"] # self._html_search_regex(r'titel\":\"(.*?)\"', webpage, '%s'); - description = video_info["video"]["beschreibung"] # self._html_search_regex(r'beschreibung\":\"(.*?)\"', webpage, '%s'); - #ext = self._html_search_regex(r'streamurl\":\".*?(\..{2,4})\"', webpage, '%s'); + download_url = video_info["video"]["streamurl"] + title = video_info["video"]["titel"] + description = video_info["video"]["beschreibung"] thumbnail = video_info["video"]["image"] download_url = download_url.replace("\\", "") stream_url = 'mp4:' + self._html_search_regex(r'ondemand/(.*)', download_url, '%s') - - #print(download_url) - #print(stream_url) - #print(title) - #print(description) - #print(video_id) - formats = [] - - fmt = { - 'url' : download_url, + #Debug output + #print('URL: ' + url) + #print('DL URL: ' + download_url) + #print('Stream URL: ' + stream_url) + #print('Title: ' + title) + #print('Description: '+ description) + #print('Video ID: ' + video_id) + + formats = [{ + 'url' : download_url, #'app': 'ondemand?_fcs_vhost=cp108781.edgefcs.net', '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' : ["S:connect", "O:1", "NS:pageUrl:" + url, "NB:fpad:0", "NN:videoFunction:1", "O:0"], - 'no_resume' : 1, - } - - formats.append(fmt) + 'no_resume' : True, + }] return { 'id': video_id,