diff options
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/common.py | 7 | ||||
| -rw-r--r-- | youtube_dl/extractor/rtl2.py | 116 |
2 files changed, 49 insertions, 74 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 7b7a832dc..388c55e99 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -114,8 +114,11 @@ class InfoExtractor(object): * http_post_data Additional data to send with a POST request. * stretched_ratio If given and not 1, indicates that the - video's pixels are not square. - width : height ratio as float. + video's pixels are not square. + width : height ratio as float. + * no_resume The server does not support resuming the + (HTTP or RTMP) download. Boolean. + url: Final video URL. ext: Video filename extension. format: The video format, defaults to ext (used for --get-format) diff --git a/youtube_dl/extractor/rtl2.py b/youtube_dl/extractor/rtl2.py index 7086d698f..72cd80498 100644 --- a/youtube_dl/extractor/rtl2.py +++ b/youtube_dl/extractor/rtl2.py @@ -1,100 +1,72 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( - ExtractorError, - clean_html, - unified_strdate, - int_or_none, -) class RTL2IE(InfoExtractor): - """Information Extractor for RTL2""" - _VALID_URL = r'http?://(?P<url>(?P<domain>(www\.)?rtl2\.de)/.*/(?P<video_id>.*))/' + _VALID_URL = r'http?://(?:www\.)?rtl2\.de/[^?#]*?/(?P<id>[^?#/]*?)(?:$|/(?:$|[?#]))' _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' : 'Matthias, Det und Helge treten gegeneinander an.' - }, - 'params': { - # rtmp download - 'skip_download': True, - }, + '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/', - 'info_dict': { - 'id': '21040-anna-erwischt-alex', - 'ext': 'mp4', - 'title': 'Anna erwischt Alex!', - 'description' : 'Anna ist Alex\' Tochter bei Köln 50667.' - }, - 'params': { - # rtmp download - 'skip_download': True, - }, + }, { + '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("/"): + # 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_id = mobj.group('video_id') + 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 not found'); - vivi_id = self._html_search_regex(r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id not found'); - + 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, '') - video_info = self._download_json(info_url, video_id) - - download_url = video_info["video"]["streamurl"] - title = video_info["video"]["titel"] - description = video_info["video"]["beschreibung"] - - thumbnail = video_info["video"]["image"] + 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 = download_url.replace("\\", "") + 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"] - stream_url = 'mp4:' + self._html_search_regex(r'ondemand/(.*)', download_url, '%s') - - #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' : True, - }] + '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, + 'thumbnail': thumbnail, + 'description': description, 'formats': formats, } |