X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/3ae74f711947d73bf6627bf312edeec41cec85c3..a497d0e55172891fd4925626374a7afdd811e00f:/youtube_dl/extractor/rtlnow.py?ds=sidebyside diff --git a/youtube_dl/extractor/rtlnow.py b/youtube_dl/extractor/rtlnow.py index 7bb236c..cd50f70 100644 --- a/youtube_dl/extractor/rtlnow.py +++ b/youtube_dl/extractor/rtlnow.py @@ -1,4 +1,7 @@ # encoding: utf-8 + +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -7,68 +10,82 @@ from ..utils import ( ExtractorError, ) + class RTLnowIE(InfoExtractor): - """Information Extractor for RTL NOW, RTL2 NOW, SUPER RTL NOW and VOX NOW""" - _VALID_URL = r'(?:http://)?(?P(?Prtl-now\.rtl\.de/|rtl2now\.rtl2\.de/|(?:www\.)?voxnow\.de/|(?:www\.)?superrtlnow\.de/)[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)' + """Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW""" + _VALID_URL = r'(?:http://)?(?P(?Prtl-now\.rtl\.de|rtl2now\.rtl2\.de|(?:www\.)?voxnow\.de|(?:www\.)?rtlnitronow\.de|(?:www\.)?superrtlnow\.de|(?:www\.)?n-tvnow\.de)/+[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)' _TESTS = [{ - u'url': u'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1', - u'file': u'90419.flv', - u'info_dict': { - u'upload_date': u'20070416', - u'title': u'Ahornallee - Folge 1 - Der Einzug', - u'description': u'Folge 1 - Der Einzug', + 'url': 'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1', + 'file': '90419.flv', + 'info_dict': { + 'upload_date': '20070416', + 'title': 'Ahornallee - Folge 1 - Der Einzug', + 'description': 'Folge 1 - Der Einzug', + }, + 'params': { + 'skip_download': True, + }, + 'skip': 'Only works from Germany', + }, + { + 'url': 'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5', + 'file': '69756.flv', + 'info_dict': { + 'upload_date': '20120519', + 'title': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit...', + 'description': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.', + 'thumbnail': 'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg', }, - u'params': { - u'skip_download': True, + 'params': { + 'skip_download': True, }, - u'skip': u'Only works from Germany', + 'skip': 'Only works from Germany', }, { - u'url': u'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5', - u'file': u'69756.flv', - u'info_dict': { - u'upload_date': u'20120519', - u'title': u'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit...', - u'description': u'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.', - u'thumbnail': u'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg', + 'url': 'http://www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17', + 'file': '13883.flv', + 'info_dict': { + 'upload_date': '20090627', + 'title': 'Voxtours - Südafrika-Reporter II', + 'description': 'Südafrika-Reporter II', }, - u'params': { - u'skip_download': True, + 'params': { + 'skip_download': True, }, - u'skip': u'Only works from Germany', }, { - u'url': u'www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17', - u'file': u'13883.flv', - u'info_dict': { - u'upload_date': u'20090627', - u'title': u'Voxtours - Südafrika-Reporter II', - u'description': u'Südafrika-Reporter II', + 'url': 'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1', + 'file': '99205.flv', + 'info_dict': { + 'upload_date': '20080928', + 'title': 'Medicopter 117 - Angst!', + 'description': 'Angst!', + 'thumbnail': 'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg' }, - u'params': { - u'skip_download': True, + 'params': { + 'skip_download': True, }, }, { - u'url': u'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1', - u'file': u'99205.flv', - u'info_dict': { - u'upload_date': u'20080928', - u'title': u'Medicopter 117 - Angst!', - u'description': u'Angst!', - u'thumbnail': u'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg' + 'url': 'http://www.n-tvnow.de/top-gear/episode-1-2013-01-01-00-00-00.php?film_id=124903&player=1&season=10', + 'file': '124903.flv', + 'info_dict': { + 'upload_date': '20130101', + 'title': 'Top Gear vom 01.01.2013', + 'description': 'Episode 1', }, - u'params': { - u'skip_download': True, + 'params': { + 'skip_download': True, }, + 'skip': 'Only works from Germany', }] - def _real_extract(self,url): + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - webpage_url = u'http://' + mobj.group('url') - video_page_url = u'http://' + mobj.group('base_url') - video_id = mobj.group(u'video_id') + webpage_url = 'http://' + mobj.group('url') + video_page_url = 'http://' + mobj.group('domain') + '/' + video_id = mobj.group('video_id') webpage = self._download_webpage(webpage_url, video_id) @@ -79,48 +96,53 @@ class RTLnowIE(InfoExtractor): msg = clean_html(note_m.group(1)) raise ExtractorError(msg) - video_title = self._html_search_regex(r'(?P<title>[^<]+)', - webpage, u'title') - playerdata_url = self._html_search_regex(r'\'playerdata\': \'(?P[^\']+)\'', - webpage, u'playerdata_url') + video_title = self._html_search_regex( + r'(?P<title>[^<]+?)( \| [^<]*)?', + webpage, 'title') + playerdata_url = self._html_search_regex( + r'\'playerdata\': \'(?P[^\']+)\'', + webpage, 'playerdata_url') playerdata = self._download_webpage(playerdata_url, video_id) - mobj = re.search(r'<!\[CDATA\[(?P<description>.+?)\s+- (?:Sendung )?vom (?P<upload_date_d>[0-9]{2})\.(?P<upload_date_m>[0-9]{2})\.(?:(?P<upload_date_Y>[0-9]{4})|(?P<upload_date_y>[0-9]{2})) [0-9]{2}:[0-9]{2} Uhr\]\]>', playerdata) + mobj = re.search(r'<!\[CDATA\[(?P<description>.+?)(?:\s+- (?:Sendung )?vom (?P<upload_date_d>[0-9]{2})\.(?P<upload_date_m>[0-9]{2})\.(?:(?P<upload_date_Y>[0-9]{4})|(?P<upload_date_y>[0-9]{2})) [0-9]{2}:[0-9]{2} Uhr)?\]\]>', playerdata) if mobj: - video_description = mobj.group(u'description') + video_description = mobj.group('description') if mobj.group('upload_date_Y'): video_upload_date = mobj.group('upload_date_Y') + elif mobj.group('upload_date_y'): + video_upload_date = '20' + mobj.group('upload_date_y') else: - video_upload_date = u'20' + mobj.group('upload_date_y') - video_upload_date += mobj.group('upload_date_m')+mobj.group('upload_date_d') + video_upload_date = None + if video_upload_date: + video_upload_date += mobj.group('upload_date_m') + mobj.group('upload_date_d') else: video_description = None video_upload_date = None - self._downloader.report_warning(u'Unable to extract description and upload date') + self._downloader.report_warning('Unable to extract description and upload date') # Thumbnail: not every video has an thumbnail mobj = re.search(r'', webpage) if mobj: - video_thumbnail = mobj.group(u'thumbnail') + video_thumbnail = mobj.group('thumbnail') else: video_thumbnail = None mobj = re.search(r']+>rtmpe://(?:[^/]+/){2})(?P[^\]]+)\]\]>', playerdata) if mobj is None: - raise ExtractorError(u'Unable to extract media URL') - video_url = mobj.group(u'url') - video_play_path = u'mp4:' + mobj.group(u'play_path') - video_player_url = video_page_url + u'includes/vodplayer.swf' + raise ExtractorError('Unable to extract media URL') + video_url = mobj.group('url') + video_play_path = 'mp4:' + mobj.group('play_path') + video_player_url = video_page_url + 'includes/vodplayer.swf' - return [{ - 'id': video_id, - 'url': video_url, - 'play_path': video_play_path, - 'page_url': video_page_url, - 'player_url': video_player_url, - 'ext': 'flv', - 'title': video_title, + return { + 'id': video_id, + 'url': video_url, + 'play_path': video_play_path, + 'page_url': video_page_url, + 'player_url': video_player_url, + 'ext': 'flv', + 'title': video_title, 'description': video_description, 'upload_date': video_upload_date, - 'thumbnail': video_thumbnail, - }] + 'thumbnail': video_thumbnail, + }