diff options
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/mit.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/rtlnow.py | 251 | ||||
| -rw-r--r-- | youtube_dl/extractor/xhamster.py | 1 |
3 files changed, 135 insertions, 118 deletions
diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py index 270fdf04b..807b1dc89 100644 --- a/youtube_dl/extractor/mit.py +++ b/youtube_dl/extractor/mit.py @@ -73,7 +73,6 @@ class MITIE(TechTVMITIE): _TEST = { 'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/', - 'file': '.mp4', 'md5': '7db01d5ccc1895fc5010e9c9e13648da', 'info_dict': { 'id': '21783', diff --git a/youtube_dl/extractor/rtlnow.py b/youtube_dl/extractor/rtlnow.py index cd50f708d..4835ec5ec 100644 --- a/youtube_dl/extractor/rtlnow.py +++ b/youtube_dl/extractor/rtlnow.py @@ -1,148 +1,165 @@ # encoding: utf-8 - from __future__ import unicode_literals import re from .common import InfoExtractor from ..utils import ( - clean_html, ExtractorError, + clean_html, + unified_strdate, + int_or_none, ) class RTLnowIE(InfoExtractor): """Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW""" - _VALID_URL = r'(?:http://)?(?P<url>(?P<domain>rtl-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<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)' - _TESTS = [{ - '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', - }, - 'params': { - 'skip_download': True, - }, - 'skip': 'Only works from Germany', - }, - { - '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', - }, - 'params': { - 'skip_download': True, + _VALID_URL = r'''(?x) + (?:https?://)? + (?P<url> + (?P<domain> + rtl-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<video_id>[0-9]+)& + player=1(?:&season=[0-9]+)?(?:&.*)? + )''' + + _TESTS = [ + { + 'url': 'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1', + 'info_dict': { + 'id': '90419', + 'ext': 'flv', + 'title': 'Ahornallee - Folge 1 - Der Einzug', + 'description': 'md5:ce843b6b5901d9a7f7d04d1bbcdb12de', + 'upload_date': '20070416', + 'duration': 1685, + }, + 'params': { + 'skip_download': True, + }, + 'skip': 'Only works from Germany', }, - }, - { - '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' + { + 'url': 'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5', + 'info_dict': { + 'id': '69756', + 'ext': 'flv', + 'title': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.', + 'description': 'md5:3fb247005ed21a935ffc82b7dfa70cf0', + 'thumbnail': 'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg', + 'upload_date': '20120519', + 'duration': 1245, + }, + 'params': { + 'skip_download': True, + }, + 'skip': 'Only works from Germany', }, - 'params': { - 'skip_download': True, + { + 'url': 'http://www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17', + 'info_dict': { + 'id': '13883', + 'ext': 'flv', + 'title': 'Voxtours - Südafrika-Reporter II', + 'description': 'md5:de7f8d56be6fd4fed10f10f57786db00', + 'upload_date': '20090627', + 'duration': 1800, + }, + 'params': { + 'skip_download': True, + }, }, - }, - { - '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', + { + 'url': 'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1', + 'info_dict': { + 'id': '99205', + 'ext': 'flv', + 'title': 'Medicopter 117 - Angst!', + 'description': 'md5:895b1df01639b5f61a04fc305a5cb94d', + 'thumbnail': 'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg', + 'upload_date': '20080928', + 'duration': 2691, + }, + 'params': { + 'skip_download': True, + }, }, - 'params': { - 'skip_download': True, + { + 'url': 'http://www.n-tvnow.de/deluxe-alles-was-spass-macht/thema-ua-luxushotel-fuer-vierbeiner.php?container_id=153819&player=1&season=0', + 'info_dict': { + 'id': '153819', + 'ext': 'flv', + 'title': 'Deluxe - Alles was Spaß macht - Thema u.a.: Luxushotel für Vierbeiner', + 'description': 'md5:c3705e1bb32e1a5b2bcd634fc065c631', + 'thumbnail': 'http://autoimg.static-fra.de/ntvnow/383157/1500x1500/image2.jpg', + 'upload_date': '20140221', + 'duration': 2429, + }, + 'skip': 'Only works from Germany', }, - 'skip': 'Only works from Germany', - }] + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - - webpage_url = 'http://' + mobj.group('url') - video_page_url = 'http://' + mobj.group('domain') + '/' + video_page_url = 'http://%s/' % mobj.group('domain') video_id = mobj.group('video_id') - webpage = self._download_webpage(webpage_url, video_id) + webpage = self._download_webpage('http://' + mobj.group('url'), video_id) - note_m = re.search(r'''(?sx) - <div[ ]style="margin-left:[ ]20px;[ ]font-size:[ ]13px;">(.*?) - <div[ ]id="playerteaser">''', webpage) - if note_m: - msg = clean_html(note_m.group(1)) - raise ExtractorError(msg) + mobj = re.search(r'(?s)<div style="margin-left: 20px; font-size: 13px;">(.*?)<div id="playerteaser">', webpage) + if mobj: + raise ExtractorError(clean_html(mobj.group(1)), expected=True) - video_title = self._html_search_regex( - r'<title>(?P<title>[^<]+?)( \| [^<]*)?</title>', - webpage, 'title') - playerdata_url = self._html_search_regex( - r'\'playerdata\': \'(?P<playerdata_url>[^\']+)\'', - webpage, 'playerdata_url') + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage, default=None) - playerdata = self._download_webpage(playerdata_url, video_id) - mobj = re.search(r'<title><!\[CDATA\[(?P<description>.+?)(?:\s+- (?:Sendung )?vom (?P<upload_date_d>[0-9]{2})\.(?P<upload_date_m>[0-9]{2})\.(?:(?P<upload_date_Y>[0-9]{4})|(?P<upload_date_y>[0-9]{2})) [0-9]{2}:[0-9]{2} Uhr)?\]\]></title>', playerdata) - if mobj: - 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 = 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('Unable to extract description and upload date') + upload_date = unified_strdate(self._html_search_meta('uploadDate', webpage, 'upload date')) - # Thumbnail: not every video has an thumbnail - mobj = re.search(r'<meta property="og:image" content="(?P<thumbnail>[^"]+)">', webpage) - if mobj: - video_thumbnail = mobj.group('thumbnail') - else: - video_thumbnail = None + mobj = re.search(r'<meta itemprop="duration" content="PT(?P<seconds>\d+)S" />', webpage) + duration = int(mobj.group('seconds')) if mobj else None - mobj = re.search(r'<filename [^>]+><!\[CDATA\[(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>[^\]]+)\]\]></filename>', playerdata) - if mobj is None: - 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' + playerdata_url = self._html_search_regex( + r"'playerdata': '(?P<playerdata_url>[^']+)'", webpage, 'playerdata_url') + + playerdata = self._download_xml(playerdata_url, video_id, 'Downloading player data XML') + + videoinfo = playerdata.find('./playlist/videoinfo') + + formats = [] + for filename in videoinfo.findall('filename'): + mobj = re.search(r'(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>.+)', filename.text) + if mobj: + fmt = { + 'url': mobj.group('url'), + 'play_path': 'mp4:' + mobj.group('play_path'), + 'page_url': video_page_url, + 'player_url': video_page_url + 'includes/vodplayer.swf', + } + else: + fmt = { + 'url': filename.text, + } + fmt.update({ + 'width': int_or_none(filename.get('width')), + 'height': int_or_none(filename.get('height')), + 'vbr': int_or_none(filename.get('bitrate')), + 'ext': 'flv', + }) + formats.append(fmt) 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, - } + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'duration': duration, + 'formats': formats, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index a75e1380d..5374495f9 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -103,6 +103,7 @@ class XHamsterIE(InfoExtractor): }] if not hd: + mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url') webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage') if is_hd(webpage): video_url = extract_video_url(webpage) |