X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/3ae74f711947d73bf6627bf312edeec41cec85c3..ca4d08063804fb264eb0ae9cc57894198f66e1fb:/youtube_dl/extractor/rtlnow.py?ds=inline diff --git a/youtube_dl/extractor/rtlnow.py b/youtube_dl/extractor/rtlnow.py index 7bb236c..ccf0b15 100644 --- a/youtube_dl/extractor/rtlnow.py +++ b/youtube_dl/extractor/rtlnow.py @@ -7,14 +7,15 @@ 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'upload_date': u'20070416', u'title': u'Ahornallee - Folge 1 - Der Einzug', u'description': u'Folge 1 - Der Einzug', }, @@ -61,13 +62,27 @@ class RTLnowIE(InfoExtractor): u'params': { u'skip_download': True, }, + }, + { + u'url': u'http://www.n-tvnow.de/top-gear/episode-1-2013-01-01-00-00-00.php?film_id=124903&player=1&season=10', + u'file': u'124903.flv', + u'info_dict': { + u'upload_date': u'20130101', + u'title': u'Top Gear vom 01.01.2013', + u'description': u'Episode 1', + }, + u'params': { + u'skip_download': True, + }, + u'skip': u'Only works from Germany', }] + 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_page_url = u'http://' + mobj.group('domain') + u'/' video_id = mobj.group(u'video_id') webpage = self._download_webpage(webpage_url, video_id) @@ -79,20 +94,23 @@ class RTLnowIE(InfoExtractor): msg = clean_html(note_m.group(1)) raise ExtractorError(msg) - video_title = self._html_search_regex(r'(?P<title>[^<]+)', + 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') 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') if mobj.group('upload_date_Y'): video_upload_date = mobj.group('upload_date_Y') - else: + elif mobj.group('upload_date_y'): video_upload_date = u'20' + mobj.group('upload_date_y') - video_upload_date += mobj.group('upload_date_m')+mobj.group('upload_date_d') + else: + 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