diff --git a/test/test_all_urls.py b/test/test_all_urls.py index c73d0e4679..c54faa380e 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -50,6 +50,7 @@ def test_youtube_extract(self): self.assertEqual(YoutubeIE()._extract_id('http://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc') self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc') self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc'), 'BaW_jenozKc') + self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch_popup?v=BaW_jenozKc'), 'BaW_jenozKc') def test_no_duplicates(self): ies = gen_extractors() diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index ea6b9d626e..217c4a52f5 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -79,9 +79,13 @@ def calc_eta(start, now, total, current): rate = float(current) / dif eta = int((float(total) - float(current)) / rate) (eta_mins, eta_secs) = divmod(eta, 60) - if eta_mins > 99: - return '--:--' - return '%02d:%02d' % (eta_mins, eta_secs) + (eta_hours, eta_mins) = divmod(eta_mins, 60) + if eta_hours > 99: + return '--:--:--' + if eta_hours == 0: + return '%02d:%02d' % (eta_mins, eta_secs) + else: + return '%02d:%02d:%02d' % (eta_hours, eta_mins, eta_secs) @staticmethod def calc_speed(start, now, bytes): diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index b9bd3a4291..9d12608e1b 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -51,13 +51,16 @@ from .myvideo import MyVideoIE from .nba import NBAIE from .ooyala import OoyalaIE +from .pbs import PBSIE from .photobucket import PhotobucketIE from .pornotube import PornotubeIE from .rbmaradio import RBMARadioIE from .redtube import RedTubeIE from .ringtv import RingTVIE from .roxwel import RoxwelIE +from .rtlnow import RTLnowIE from .sina import SinaIE +from .slashdot import SlashdotIE from .soundcloud import SoundcloudIE, SoundcloudSetIE from .spiegel import SpiegelIE from .stanfordoc import StanfordOpenClassroomIE diff --git a/youtube_dl/extractor/collegehumor.py b/youtube_dl/extractor/collegehumor.py index 30b9c7549f..8d4c93d6da 100644 --- a/youtube_dl/extractor/collegehumor.py +++ b/youtube_dl/extractor/collegehumor.py @@ -4,6 +4,7 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_parse_urlparse, + determine_ext, ExtractorError, ) @@ -12,7 +13,7 @@ class CollegeHumorIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P[0-9]+)/?(?P.*)$' - _TEST = { + _TESTS = [{ u'url': u'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe', u'file': u'6902724.mp4', u'md5': u'1264c12ad95dca142a9f0bf7968105a0', @@ -20,7 +21,16 @@ class CollegeHumorIE(InfoExtractor): u'title': u'Comic-Con Cosplay Catastrophe', u'description': u'Fans get creative this year at San Diego. Too creative. And yes, that\'s really Joss Whedon.', }, - } + }, + { + u'url': u'http://www.collegehumor.com/video/3505939/font-conference', + u'file': u'3505939.mp4', + u'md5': u'c51ca16b82bb456a4397987791a835f5', + u'info_dict': { + u'title': u'Font Conference', + u'description': u'This video wasn\'t long enough, so we made it double-spaced.', + }, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -49,25 +59,29 @@ def _real_extract(self, url): info['description'] = videoNode.findall('./description')[0].text info['title'] = videoNode.findall('./caption')[0].text info['thumbnail'] = videoNode.findall('./thumbnail')[0].text - manifest_url = videoNode.findall('./file')[0].text + next_url = videoNode.findall('./file')[0].text except IndexError: raise ExtractorError(u'Invalid metadata XML file') - manifest_url += '?hdcore=2.10.3' - manifestXml = self._download_webpage(manifest_url, video_id, - u'Downloading XML manifest', - u'Unable to download video info XML') + if next_url.endswith(u'manifest.f4m'): + manifest_url = next_url + '?hdcore=2.10.3' + manifestXml = self._download_webpage(manifest_url, video_id, + u'Downloading XML manifest', + u'Unable to download video info XML') - adoc = xml.etree.ElementTree.fromstring(manifestXml) - try: - media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0] - node_id = media_node.attrib['url'] - video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text - except IndexError as err: - raise ExtractorError(u'Invalid manifest file') + adoc = xml.etree.ElementTree.fromstring(manifestXml) + try: + media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0] + node_id = media_node.attrib['url'] + video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text + except IndexError as err: + raise ExtractorError(u'Invalid manifest file') + url_pr = compat_urllib_parse_urlparse(info['thumbnail']) + info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','') + info['ext'] = 'mp4' + else: + # Old-style direct links + info['url'] = next_url + info['ext'] = determine_ext(info['url']) - url_pr = compat_urllib_parse_urlparse(info['thumbnail']) - - info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','') - info['ext'] = 'mp4' - return [info] + return info diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index da50abfc1c..8009c2d857 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -77,7 +77,13 @@ def __init__(self, downloader=None): @classmethod def suitable(cls, url): """Receives a URL and returns True if suitable for this IE.""" - return re.match(cls._VALID_URL, url) is not None + + # This does not use has/getattr intentionally - we want to know whether + # we have cached the regexp for *this* class, whereas getattr would also + # match the superclass + if '_VALID_URL_RE' not in cls.__dict__: + cls._VALID_URL_RE = re.compile(cls._VALID_URL) + return cls._VALID_URL_RE.match(url) is not None @classmethod def working(cls): diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py index 67a7e5f76f..4508f0dfac 100644 --- a/youtube_dl/extractor/funnyordie.py +++ b/youtube_dl/extractor/funnyordie.py @@ -21,17 +21,14 @@ def _real_extract(self, url): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - video_url = self._html_search_regex(r']*>\s*]*>\s*(?P.*?)</h1>", - r'<title>(?P<title>[^<]+?)'), webpage, 'title', flags=re.DOTALL) - info = { 'id': video_id, 'url': video_url, 'ext': 'mp4', - 'title': title, + 'title': self._og_search_title(webpage), 'description': self._og_search_description(webpage), } return [info] diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index b633e896c6..da016f7ee8 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -107,8 +107,13 @@ def http_error_405(self, req, fp, code, msg, headers): return new_url def _real_extract(self, url): - new_url = self._test_redirect(url) - if new_url: return [self.url_result(new_url)] + try: + new_url = self._test_redirect(url) + if new_url: + return [self.url_result(new_url)] + except compat_urllib_error.HTTPError: + # This may be a stupid server that doesn't like HEAD, our UA, or so + pass video_id = url.split('/')[-1] try: @@ -144,6 +149,9 @@ def _real_extract(self, url): # We only look in og:video if the MIME type is a video, don't try if it's a Flash player: if m_video_type is not None: mobj = re.search(r'.*?(.*?)', xml_config, re.MULTILINE|re.DOTALL).group(1) info = json.loads(info)['versions'][0] video_url = 'http://video720.jeuxvideo.com/' + info['file'] - track_info = {'id':id, - 'title' : title, - 'ext' : 'mp4', - 'url' : video_url - } - - return [track_info] + return {'id': id, + 'title' : config.find('titre_video').text, + 'ext' : 'mp4', + 'url' : video_url, + 'description': self._og_search_description(webpage), + 'thumbnail': config.find('image').text, + } diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py new file mode 100644 index 0000000000..65462d8670 --- /dev/null +++ b/youtube_dl/extractor/pbs.py @@ -0,0 +1,34 @@ +import re +import json + +from .common import InfoExtractor + + +class PBSIE(InfoExtractor): + _VALID_URL = r'https?://video.pbs.org/video/(?P\d+)/?' + + _TEST = { + u'url': u'http://video.pbs.org/video/2365006249/', + u'file': u'2365006249.mp4', + u'md5': 'ce1888486f0908d555a8093cac9a7362', + u'info_dict': { + u'title': u'A More Perfect Union', + u'description': u'md5:ba0c207295339c8d6eced00b7c363c6a', + u'duration': 3190, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id + info_page = self._download_webpage(info_url, video_id) + info =json.loads(info_page) + return {'id': video_id, + 'title': info['title'], + 'url': info['alternate_encoding']['url'], + 'ext': 'mp4', + 'description': info['program'].get('description'), + 'thumbnail': info.get('image_url'), + 'duration': info.get('duration'), + } diff --git a/youtube_dl/extractor/rtlnow.py b/youtube_dl/extractor/rtlnow.py new file mode 100644 index 0000000000..2f134e6a7b --- /dev/null +++ b/youtube_dl/extractor/rtlnow.py @@ -0,0 +1,113 @@ +# encoding: utf-8 +import re + +from .common import InfoExtractor +from ..utils import ( + clean_html, + ExtractorError, +) + +class RTLnowIE(InfoExtractor): + """Information Extractor for RTLnow, RTL2now and VOXnow""" + _VALID_URL = r'(?:http://)?(?P(?Prtl(?:(?P2)|-)now\.rtl(?(is_rtl2)2|)\.de/|(?:www\.)?voxnow\.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', + }, + u'params': { + u'skip_download': True, + }, + u'skip': u'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', + }, + u'params': { + u'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', + }, + u'params': { + u'skip_download': True, + }, + }] + + 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 = self._download_webpage(webpage_url, video_id) + + note_m = re.search(r'''(?sx) + (.*?) + ''', webpage) + if note_m: + 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') + + 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) + if mobj: + video_description = mobj.group(u'description') + if mobj.group('upload_date_Y'): + video_upload_date = 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') + else: + video_description = None + video_upload_date = None + self._downloader.report_warning(u'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') + 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' + + 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, + }] diff --git a/youtube_dl/extractor/slashdot.py b/youtube_dl/extractor/slashdot.py new file mode 100644 index 0000000000..2cba530766 --- /dev/null +++ b/youtube_dl/extractor/slashdot.py @@ -0,0 +1,23 @@ +import re + +from .common import InfoExtractor + + +class SlashdotIE(InfoExtractor): + _VALID_URL = r'https?://tv.slashdot.org/video/\?embed=(?P.*?)(&|$)' + + _TEST = { + u'url': u'http://tv.slashdot.org/video/?embed=JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz', + u'file': u'JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz.mp4', + u'md5': u'd2222e7a4a4c1541b3e0cf732fb26735', + u'info_dict': { + u'title': u' Meet the Stampede Supercomputing Cluster\'s Administrator', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + ooyala_url = self._search_regex(r'