diff options
Diffstat (limited to 'youtube_dl/extractor')
62 files changed, 2166 insertions, 930 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index b8c843515..66f71edf6 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -14,6 +14,7 @@ from .arte import ( ArteTVConcertIE, ArteTVFutureIE, ArteTVDDCIE, + ArteTVEmbedIE, ) from .auengine import AUEngineIE from .bambuser import BambuserIE, BambuserChannelIE @@ -25,6 +26,7 @@ from .bloomberg import BloombergIE from .br import BRIE from .breakcom import BreakIE from .brightcove import BrightcoveIE +from .byutv import BYUtvIE from .c56 import C56IE from .canal13cl import Canal13clIE from .canalplus import CanalplusIE @@ -38,6 +40,7 @@ from .clipfish import ClipfishIE from .cliphunter import CliphunterIE from .clipsyndicate import ClipsyndicateIE from .cmt import CMTIE +from .cnet import CNETIE from .cnn import ( CNNIE, CNNBlogsIE, @@ -81,6 +84,7 @@ from .fktv import ( ) from .flickr import FlickrIE from .fourtube import FourTubeIE +from .franceculture import FranceCultureIE from .franceinter import FranceInterIE from .francetv import ( PluzzIE, @@ -112,7 +116,7 @@ from .imdb import ( ) from .ina import InaIE from .infoq import InfoQIE -from .instagram import InstagramIE +from .instagram import InstagramIE, InstagramUserIE from .internetvideoarchive import InternetVideoArchiveIE from .iprima import IPrimaIE from .ivi import ( @@ -150,10 +154,13 @@ from .mixcloud import MixcloudIE from .mpora import MporaIE from .mofosex import MofosexIE from .mooshare import MooshareIE +from .morningstar import MorningstarIE +from .motorsport import MotorsportIE from .mtv import ( MTVIE, MTVIggyIE, ) +from .musicplayon import MusicPlayOnIE from .muzu import MuzuTVIE from .myspace import MySpaceIE from .myspass import MySpassIE @@ -175,6 +182,8 @@ from .normalboots import NormalbootsIE from .novamov import NovaMovIE from .nowness import NownessIE from .nowvideo import NowVideoIE +from .ntv import NTVIE +from .oe1 import OE1IE from .ooyala import OoyalaIE from .orf import ORFIE from .parliamentliveuk import ParliamentLiveUKIE @@ -195,6 +204,7 @@ from .ro220 import Ro220IE from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE from .rtlnow import RTLnowIE +from .rts import RTSIE from .rutube import ( RutubeIE, RutubeChannelIE, @@ -205,7 +215,6 @@ from .rutv import RUTVIE from .savefrom import SaveFromIE from .servingsys import ServingSysIE from .sina import SinaIE -from .slashdot import SlashdotIE from .slideshare import SlideshareIE from .smotri import ( SmotriIE, @@ -254,13 +263,13 @@ from .udemy import ( UdemyCourseIE ) from .unistra import UnistraIE +from .urort import UrortIE from .ustream import UstreamIE, UstreamChannelIE from .vbox7 import Vbox7IE from .veehd import VeeHDIE from .veoh import VeohIE from .vesti import VestiIE from .vevo import VevoIE -from .vice import ViceIE from .viddler import ViddlerIE from .videobam import VideoBamIE from .videodetective import VideoDetectiveIE @@ -279,16 +288,21 @@ from .vine import VineIE from .viki import VikiIE from .vk import VKIE from .vube import VubeIE +from .washingtonpost import WashingtonPostIE from .wat import WatIE -from .wdr import WDRIE +from .wdr import ( + WDRIE, + WDRMausIE, +) from .weibo import WeiboIE from .wimp import WimpIE from .wistia import WistiaIE from .worldstarhiphop import WorldStarHipHopIE +from .xbef import XBefIE from .xhamster import XHamsterIE from .xnxx import XNXXIE from .xvideos import XVideosIE -from .xtube import XTubeIE +from .xtube import XTubeUserIE, XTubeIE from .yahoo import ( YahooIE, YahooNewsIE, diff --git a/youtube_dl/extractor/addanime.py b/youtube_dl/extractor/addanime.py index a3a1b999d..fcf296057 100644 --- a/youtube_dl/extractor/addanime.py +++ b/youtube_dl/extractor/addanime.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -14,14 +16,14 @@ from ..utils import ( class AddAnimeIE(InfoExtractor): _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)' - IE_NAME = u'AddAnime' _TEST = { - u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9', - u'file': u'24MR3YO5SAS9.mp4', - u'md5': u'72954ea10bc979ab5e2eb288b21425a0', - u'info_dict': { - u"description": u"One Piece 606", - u"title": u"One Piece 606" + 'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9', + 'md5': '72954ea10bc979ab5e2eb288b21425a0', + 'info_dict': { + 'id': '24MR3YO5SAS9', + 'ext': 'mp4', + 'description': 'One Piece 606', + 'title': 'One Piece 606', } } @@ -38,10 +40,10 @@ class AddAnimeIE(InfoExtractor): redir_webpage = ee.cause.read().decode('utf-8') action = self._search_regex( r'<form id="challenge-form" action="([^"]+)"', - redir_webpage, u'Redirect form') + redir_webpage, 'Redirect form') vc = self._search_regex( r'<input type="hidden" name="jschl_vc" value="([^"]+)"/>', - redir_webpage, u'redirect vc value') + redir_webpage, 'redirect vc value') av = re.search( r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);', redir_webpage) @@ -52,19 +54,19 @@ class AddAnimeIE(InfoExtractor): parsed_url = compat_urllib_parse_urlparse(url) av_val = av_res + len(parsed_url.netloc) confirm_url = ( - parsed_url.scheme + u'://' + parsed_url.netloc + + parsed_url.scheme + '://' + parsed_url.netloc + action + '?' + compat_urllib_parse.urlencode({ 'jschl_vc': vc, 'jschl_answer': compat_str(av_val)})) self._download_webpage( confirm_url, video_id, - note=u'Confirming after redirect') + note='Confirming after redirect') webpage = self._download_webpage(url, video_id) formats = [] for format_id in ('normal', 'hq'): rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id) - video_url = self._search_regex(rex, webpage, u'video file URLx', + video_url = self._search_regex(rex, webpage, 'video file URLx', fatal=False) if not video_url: continue @@ -72,14 +74,13 @@ class AddAnimeIE(InfoExtractor): 'format_id': format_id, 'url': video_url, }) - if not formats: - raise ExtractorError(u'Cannot find any video format!') + self._sort_formats(formats) video_title = self._og_search_title(webpage) video_description = self._og_search_description(webpage) return { '_type': 'video', - 'id': video_id, + 'id': video_id, 'formats': formats, 'title': video_title, 'description': video_description diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py index 922cede05..dc8657b67 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -6,7 +6,6 @@ import json from .common import InfoExtractor from ..utils import ( compat_urlparse, - determine_ext, ) @@ -16,9 +15,10 @@ class AppleTrailersIE(InfoExtractor): "url": "http://trailers.apple.com/trailers/wb/manofsteel/", "playlist": [ { - "file": "manofsteel-trailer4.mov", "md5": "d97a8e575432dbcb81b7c3acb741f8a8", "info_dict": { + "id": "manofsteel-trailer4", + "ext": "mov", "duration": 111, "title": "Trailer 4", "upload_date": "20130523", @@ -26,9 +26,10 @@ class AppleTrailersIE(InfoExtractor): }, }, { - "file": "manofsteel-trailer3.mov", "md5": "b8017b7131b721fb4e8d6f49e1df908c", "info_dict": { + "id": "manofsteel-trailer3", + "ext": "mov", "duration": 182, "title": "Trailer 3", "upload_date": "20130417", @@ -36,9 +37,10 @@ class AppleTrailersIE(InfoExtractor): }, }, { - "file": "manofsteel-trailer.mov", "md5": "d0f1e1150989b9924679b441f3404d48", "info_dict": { + "id": "manofsteel-trailer", + "ext": "mov", "duration": 148, "title": "Trailer", "upload_date": "20121212", @@ -46,15 +48,16 @@ class AppleTrailersIE(InfoExtractor): }, }, { - "file": "manofsteel-teaser.mov", "md5": "5fe08795b943eb2e757fa95cb6def1cb", "info_dict": { + "id": "manofsteel-teaser", + "ext": "mov", "duration": 93, "title": "Teaser", "upload_date": "20120721", "uploader_id": "wb", }, - } + }, ] } @@ -65,16 +68,16 @@ class AppleTrailersIE(InfoExtractor): movie = mobj.group('movie') uploader_id = mobj.group('company') - playlist_url = compat_urlparse.urljoin(url, u'includes/playlists/itunes.inc') + playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc') def fix_html(s): - s = re.sub(r'(?s)<script[^<]*?>.*?</script>', u'', s) + s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s) s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s) # The ' in the onClick attributes are not escaped, it couldn't be parsed # like: http://trailers.apple.com/trailers/wb/gravity/ def _clean_json(m): - return u'iTunes.playURL(%s);' % m.group(1).replace('\'', ''') + return 'iTunes.playURL(%s);' % m.group(1).replace('\'', ''') s = re.sub(self._JSON_RE, _clean_json, s) - s = u'<html>' + s + u'</html>' + s = '<html>' + s + u'</html>' return s doc = self._download_xml(playlist_url, movie, transform_source=fix_html) @@ -82,7 +85,7 @@ class AppleTrailersIE(InfoExtractor): for li in doc.findall('./div/ul/li'): on_click = li.find('.//a').attrib['onClick'] trailer_info_json = self._search_regex(self._JSON_RE, - on_click, u'trailer info') + on_click, 'trailer info') trailer_info = json.loads(trailer_info_json) title = trailer_info['title'] video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower() @@ -98,8 +101,7 @@ class AppleTrailersIE(InfoExtractor): first_url = trailer_info['url'] trailer_id = first_url.split('/')[-1].rpartition('_')[0].lower() settings_json_url = compat_urlparse.urljoin(url, 'includes/settings/%s.json' % trailer_id) - settings_json = self._download_webpage(settings_json_url, trailer_id, u'Downloading settings json') - settings = json.loads(settings_json) + settings = self._download_json(settings_json_url, trailer_id, 'Downloading settings json') formats = [] for format in settings['metadata']['sizes']: @@ -107,7 +109,6 @@ class AppleTrailersIE(InfoExtractor): format_url = re.sub(r'_(\d*p.mov)', r'_h\1', format['src']) formats.append({ 'url': format_url, - 'ext': determine_ext(format_url), 'format': format['type'], 'width': format['width'], 'height': int(format['height']), diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 979481b21..646377e4b 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor from ..utils import ( @@ -19,114 +18,41 @@ from ..utils import ( # is different for each one. The videos usually expire in 7 days, so we can't # add tests. -class ArteTvIE(InfoExtractor): - _VIDEOS_URL = r'(?:http://)?videos\.arte\.tv/(?P<lang>fr|de)/.*-(?P<id>.*?)\.html' - _LIVEWEB_URL = r'(?:http://)?liveweb\.arte\.tv/(?P<lang>fr|de)/(?P<subpage>.+?)/(?P<name>.+)' - _LIVE_URL = r'index-[0-9]+\.html$' +class ArteTvIE(InfoExtractor): + _VALID_URL = r'http://videos\.arte\.tv/(?P<lang>fr|de)/.*-(?P<id>.*?)\.html' IE_NAME = 'arte.tv' - @classmethod - def suitable(cls, url): - return any(re.match(regex, url) for regex in (cls._VIDEOS_URL, cls._LIVEWEB_URL)) - - # TODO implement Live Stream - # from ..utils import compat_urllib_parse - # def extractLiveStream(self, url): - # video_lang = url.split('/')[-4] - # info = self.grep_webpage( - # url, - # r'src="(.*?/videothek_js.*?\.js)', - # 0, - # [ - # (1, 'url', 'Invalid URL: %s' % url) - # ] - # ) - # http_host = url.split('/')[2] - # next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url'))) - # info = self.grep_webpage( - # next_url, - # r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' + - # '(http://.*?\.swf).*?' + - # '(rtmp://.*?)\'', - # re.DOTALL, - # [ - # (1, 'path', 'could not extract video path: %s' % url), - # (2, 'player', 'could not extract video player: %s' % url), - # (3, 'url', 'could not extract video url: %s' % url) - # ] - # ) - # video_url = '%s/%s' % (info.get('url'), info.get('path')) - def _real_extract(self, url): - mobj = re.match(self._VIDEOS_URL, url) - if mobj is not None: - id = mobj.group('id') - lang = mobj.group('lang') - return self._extract_video(url, id, lang) - - mobj = re.match(self._LIVEWEB_URL, url) - if mobj is not None: - name = mobj.group('name') - lang = mobj.group('lang') - return self._extract_liveweb(url, name, lang) - - if re.search(self._LIVE_URL, url) is not None: - raise ExtractorError('Arte live streams are not yet supported, sorry') - # self.extractLiveStream(url) - # return - - raise ExtractorError('No video found') - - def _extract_video(self, url, video_id, lang): - """Extract from videos.arte.tv""" + mobj = re.match(self._VALID_URL, url) + lang = mobj.group('lang') + video_id = mobj.group('id') + ref_xml_url = url.replace('/videos/', '/do_delegate/videos/') ref_xml_url = ref_xml_url.replace('.html', ',view,asPlayerXml.xml') ref_xml_doc = self._download_xml( ref_xml_url, video_id, note='Downloading metadata') config_node = find_xpath_attr(ref_xml_doc, './/video', 'lang', lang) config_xml_url = config_node.attrib['ref'] - config_xml = self._download_webpage( + config = self._download_xml( config_xml_url, video_id, note='Downloading configuration') - video_urls = list(re.finditer(r'<url quality="(?P<quality>.*?)">(?P<url>.*?)</url>', config_xml)) - def _key(m): - quality = m.group('quality') - if quality == 'hd': - return 2 - else: - return 1 - # We pick the best quality - video_urls = sorted(video_urls, key=_key) - video_url = list(video_urls)[-1].group('url') - - title = self._html_search_regex(r'<name>(.*?)</name>', config_xml, 'title') - thumbnail = self._html_search_regex(r'<firstThumbnailUrl>(.*?)</firstThumbnailUrl>', - config_xml, 'thumbnail') - return {'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'url': video_url, - 'ext': 'flv', - } - - def _extract_liveweb(self, url, name, lang): - """Extract form http://liveweb.arte.tv/""" - webpage = self._download_webpage(url, name) - video_id = self._search_regex(r'eventId=(\d+?)("|&)', webpage, 'event id') - config_doc = self._download_xml('http://download.liveweb.arte.tv/o21/liveweb/events/event-%s.xml' % video_id, - video_id, 'Downloading information') - event_doc = config_doc.find('event') - url_node = event_doc.find('video').find('urlHd') - if url_node is None: - url_node = event_doc.find('urlSd') - - return {'id': video_id, - 'title': event_doc.find('name%s' % lang.capitalize()).text, - 'url': url_node.text.replace('MP4', 'mp4'), - 'ext': 'flv', - 'thumbnail': self._og_search_thumbnail(webpage), - } + formats = [{ + 'forma_id': q.attrib['quality'], + 'url': q.text, + 'ext': 'flv', + 'quality': 2 if q.attrib['quality'] == 'hd' else 1, + } for q in config.findall('./urls/url')] + self._sort_formats(formats) + + title = config.find('.//name').text + thumbnail = config.find('.//firstThumbnailUrl').text + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } class ArteTVPlus7IE(InfoExtractor): @@ -152,9 +78,7 @@ class ArteTVPlus7IE(InfoExtractor): return self._extract_from_json_url(json_url, video_id, lang) def _extract_from_json_url(self, json_url, video_id, lang): - json_info = self._download_webpage(json_url, video_id, 'Downloading info json') - self.report_extraction(video_id) - info = json.loads(json_info) + info = self._download_json(json_url, video_id) player_info = info['videoJsonPlayer'] info_dict = { @@ -176,6 +100,8 @@ class ArteTVPlus7IE(InfoExtractor): l = 'F' elif lang == 'de': l = 'A' + else: + l = lang regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l] return any(re.match(r, f['versionCode']) for r in regexes) # Some formats may not be in the same language as the url @@ -305,3 +231,22 @@ class ArteTVConcertIE(ArteTVPlus7IE): 'description': 'md5:486eb08f991552ade77439fe6d82c305', }, } + + +class ArteTVEmbedIE(ArteTVPlus7IE): + IE_NAME = 'arte.tv:embed' + _VALID_URL = r'''(?x) + http://www\.arte\.tv + /playerv2/embed\.php\?json_url= + (?P<json_url> + http://arte\.tv/papi/tvguide/videos/stream/player/ + (?P<lang>[^/]+)/(?P<id>[^/]+)[^&]* + ) + ''' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + lang = mobj.group('lang') + json_url = mobj.group('json_url') + return self._extract_from_json_url(json_url, video_id, lang) diff --git a/youtube_dl/extractor/auengine.py b/youtube_dl/extractor/auengine.py index c6f30e626..20bf12550 100644 --- a/youtube_dl/extractor/auengine.py +++ b/youtube_dl/extractor/auengine.py @@ -11,22 +11,24 @@ from ..utils import ( class AUEngineIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?auengine\.com/embed\.php\?.*?file=(?P<id>[^&]+).*?' + _TEST = { 'url': 'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370', - 'file': 'lfvlytY6.mp4', 'md5': '48972bdbcf1a3a2f5533e62425b41d4f', 'info_dict': { + 'id': 'lfvlytY6', + 'ext': 'mp4', 'title': '[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]' } } - _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed\.php\?.*?file=([^&]+).*?' def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r'<title>(?P<title>.+?)</title>', - webpage, 'title') + title = self._html_search_regex(r'<title>(?P<title>.+?)</title>', webpage, 'title') title = title.strip() links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage) links = map(compat_urllib_parse.unquote, links) @@ -39,14 +41,15 @@ class AUEngineIE(InfoExtractor): elif '/videos/' in link: video_url = link if not video_url: - raise ExtractorError(u'Could not find video URL') + raise ExtractorError('Could not find video URL') ext = '.' + determine_ext(video_url) if ext == title[-len(ext):]: title = title[:-len(ext)] return { - 'id': video_id, - 'url': video_url, - 'title': title, + 'id': video_id, + 'url': video_url, + 'title': title, 'thumbnail': thumbnail, + 'http_referer': 'http://www.auengine.com/flowplayer/flowplayer.commercial-3.2.14.swf', } diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index 2415ce403..25fb79e14 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -1,22 +1,21 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor -from .ooyala import OoyalaIE class BloombergIE(InfoExtractor): _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?)\.html' _TEST = { - u'url': u'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html', - u'file': u'12bzhqZTqQHmmlA8I-i0NpzJgcG5NNYX.mp4', - u'info_dict': { - u'title': u'Shah\'s Presentation on Foreign-Exchange Strategies', - u'description': u'md5:abc86e5236f9f0e4866c59ad36736686', - }, - u'params': { - # Requires ffmpeg (m3u8 manifest) - u'skip_download': True, + 'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html', + 'md5': '7bf08858ff7c203c870e8a6190e221e5', + 'info_dict': { + 'id': 'qurhIVlJSB6hzkVi229d8g', + 'ext': 'flv', + 'title': 'Shah\'s Presentation on Foreign-Exchange Strategies', + 'description': 'md5:0681e0d30dcdfc6abf34594961d8ea88', }, } @@ -24,7 +23,16 @@ class BloombergIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) name = mobj.group('name') webpage = self._download_webpage(url, name) - embed_code = self._search_regex( - r'<source src="https?://[^/]+/[^/]+/[^/]+/([^/]+)', webpage, - 'embed code') - return OoyalaIE._build_url_result(embed_code) + f4m_url = self._search_regex( + r'<source src="(https?://[^"]+\.f4m.*?)"', webpage, + 'f4m url') + title = re.sub(': Video$', '', self._og_search_title(webpage)) + + return { + 'id': name.split('-')[-1], + 'title': title, + 'url': f4m_url, + 'ext': 'flv', + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + } diff --git a/youtube_dl/extractor/breakcom.py b/youtube_dl/extractor/breakcom.py index 85635d1cc..1bfc9f35b 100644 --- a/youtube_dl/extractor/breakcom.py +++ b/youtube_dl/extractor/breakcom.py @@ -27,9 +27,10 @@ class BreakIE(InfoExtractor): webpage, 'info json', flags=re.DOTALL) info = json.loads(info_json) video_url = info['videoUri'] - m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', video_url) - if m_youtube is not None: - return self.url_result(m_youtube.group(1), 'Youtube') + youtube_id = info.get('youtubeId') + if youtube_id: + return self.url_result(youtube_id, 'Youtube') + final_url = video_url + '?' + info['AuthToken'] return { 'id': video_id, diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 83eec84d3..339d60ff0 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -87,7 +87,7 @@ class BrightcoveIE(InfoExtractor): object_str = object_str.replace('<--', '<!--') object_str = fix_xml_ampersands(object_str) - object_doc = xml.etree.ElementTree.fromstring(object_str) + object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8')) fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars') if fv_el is not None: diff --git a/youtube_dl/extractor/byutv.py b/youtube_dl/extractor/byutv.py new file mode 100644 index 000000000..91c6398f5 --- /dev/null +++ b/youtube_dl/extractor/byutv.py @@ -0,0 +1,50 @@ +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, +) + + +class BYUtvIE(InfoExtractor): + _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<video_id>[^/?#]+)' + _TEST = { + 'url': 'http://www.byutv.org/watch/44e80f7b-e3ba-43ba-8c51-b1fd96c94a79/granite-flats-talking', + 'info_dict': { + 'id': 'granite-flats-talking', + 'ext': 'mp4', + 'description': 'md5:1a7ae3e153359b7cc355ef3963441e5f', + 'title': 'Talking', + 'thumbnail': 're:^https?://.*promo.*' + }, + 'params': { + 'skip_download': True, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('video_id') + + webpage = self._download_webpage(url, video_id) + episode_code = self._search_regex( + r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information') + episode_json = re.sub( + r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', episode_code) + ep = json.loads(episode_json) + + if ep['providerType'] == 'Ooyala': + return { + '_type': 'url_transparent', + 'ie_key': 'Ooyala', + 'url': 'ooyala:%s' % ep['providerId'], + 'id': video_id, + 'title': ep['title'], + 'description': ep.get('description'), + 'thumbnail': ep.get('imageThumbnail'), + } + else: + raise ExtractorError('Unsupported provider %s' % ep['provider']) diff --git a/youtube_dl/extractor/c56.py b/youtube_dl/extractor/c56.py index 690bc7c25..cb96c3876 100644 --- a/youtube_dl/extractor/c56.py +++ b/youtube_dl/extractor/c56.py @@ -2,39 +2,46 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor class C56IE(InfoExtractor): - _VALID_URL = r'https?://((www|player)\.)?56\.com/(.+?/)?(v_|(play_album.+-))(?P<textid>.+?)\.(html|swf)' + _VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)' IE_NAME = '56.com' _TEST = { 'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html', - 'file': '93440716.flv', 'md5': 'e59995ac63d0457783ea05f93f12a866', 'info_dict': { + 'id': '93440716', + 'ext': 'flv', 'title': '网事知多少 第32期：车怒', + 'duration': 283.813, }, } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE) text_id = mobj.group('textid') - info_page = self._download_webpage('http://vxml.56.com/json/%s/' % text_id, - text_id, 'Downloading video info') - info = json.loads(info_page)['info'] - formats = [{ - 'format_id': f['type'], - 'filesize': int(f['filesize']), - 'url': f['url'] - } for f in info['rfiles']] + + page = self._download_json( + 'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info') + + info = page['info'] + + formats = [ + { + 'format_id': f['type'], + 'filesize': int(f['filesize']), + 'url': f['url'] + } for f in info['rfiles'] + ] self._sort_formats(formats) return { 'id': info['vid'], 'title': info['Subject'], + 'duration': int(info['duration']) / 1000.0, 'formats': formats, 'thumbnail': info.get('bimg') or info.get('img'), } diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py index 7cdcd8399..49dfd881e 100644 --- a/youtube_dl/extractor/canalplus.py +++ b/youtube_dl/extractor/canalplus.py @@ -28,7 +28,7 @@ class CanalplusIE(InfoExtractor): video_id = mobj.groupdict().get('id') if video_id is None: webpage = self._download_webpage(url, mobj.group('path')) - video_id = self._search_regex(r'videoId = "(\d+)";', webpage, u'video id') + video_id = self._search_regex(r'<canal:player videoId="(\d+)"', webpage, u'video id') info_url = self._VIDEO_INFO_TEMPLATE % video_id doc = self._download_xml(info_url,video_id, u'Downloading video info') diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index bfbffefdc..2301f61b6 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -9,12 +9,12 @@ from ..utils import ( class CinemassacreIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/.+?' + _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)' _TESTS = [ { 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', 'file': '19911.mp4', - 'md5': 'fde81fbafaee331785f58cd6c0d46190', + 'md5': '782f8504ca95a0eba8fc9177c373eec7', 'info_dict': { 'upload_date': '20121110', 'title': '“Angry Video Game Nerd: The Movie” – Trailer', @@ -24,7 +24,7 @@ class CinemassacreIE(InfoExtractor): { 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', 'file': '521be8ef82b16.mp4', - 'md5': 'd72f10cd39eac4215048f62ab477a511', + 'md5': 'dec39ee5118f8d9cc067f45f9cbe3a35', 'info_dict': { 'upload_date': '20131002', 'title': 'The Mummy’s Hand (1940)', @@ -34,8 +34,9 @@ class CinemassacreIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') - webpage = self._download_webpage(url, None) # Don't know video id yet + webpage = self._download_webpage(url, display_id) video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d') mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage) if not mobj: @@ -43,33 +44,36 @@ class CinemassacreIE(InfoExtractor): playerdata_url = mobj.group('embed_url') video_id = mobj.group('video_id') - video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|', - webpage, 'title') - video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>', + video_title = self._html_search_regex( + r'<title>(?P<title>.+?)\|', webpage, 'title') + video_description = self._html_search_regex( + r'<div class="entry-content">(?P<description>.+?)</div>', webpage, 'description', flags=re.DOTALL, fatal=False) - if len(video_description) == 0: - video_description = None playerdata = self._download_webpage(playerdata_url, video_id) - sd_url = self._html_search_regex(r'file: \'(?P<sd_file>[^\']+)\', label: \'SD\'', playerdata, 'sd_file') - hd_url = self._html_search_regex(r'file: \'(?P<hd_file>[^\']+)\', label: \'HD\'', playerdata, 'hd_file') + sd_url = self._html_search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file') + hd_url = self._html_search_regex( + r'file: \'([^\']+)\', label: \'HD\'', playerdata, 'hd_file', + default=None) video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False) - formats = [ - { - 'url': sd_url, - 'ext': 'mp4', - 'format': 'sd', - 'format_id': 'sd', - }, - { + formats = [{ + 'url': sd_url, + 'ext': 'mp4', + 'format': 'sd', + 'format_id': 'sd', + 'quality': 1, + }] + if hd_url: + formats.append({ 'url': hd_url, 'ext': 'mp4', 'format': 'hd', 'format_id': 'hd', - }, - ] + 'quality': 2, + }) + self._sort_formats(formats) return { 'id': video_id, diff --git a/youtube_dl/extractor/clipfish.py b/youtube_dl/extractor/clipfish.py index 43efb08bf..669919a2c 100644 --- a/youtube_dl/extractor/clipfish.py +++ b/youtube_dl/extractor/clipfish.py @@ -1,22 +1,28 @@ +from __future__ import unicode_literals + import re import time import xml.etree.ElementTree from .common import InfoExtractor -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + parse_duration, +) class ClipfishIE(InfoExtractor): - IE_NAME = u'clipfish' + IE_NAME = 'clipfish' _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/' _TEST = { - u'url': u'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/', - u'file': u'3966754.mp4', - u'md5': u'2521cd644e862936cf2e698206e47385', - u'info_dict': { - u'title': u'FIFA 14 - E3 2013 Trailer', - u'duration': 82, + 'url': 'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/', + 'md5': '2521cd644e862936cf2e698206e47385', + 'info_dict': { + 'id': '3966754', + 'ext': 'mp4', + 'title': 'FIFA 14 - E3 2013 Trailer', + 'duration': 82, }, u'skip': 'Blocked in the US' } @@ -33,21 +39,10 @@ class ClipfishIE(InfoExtractor): video_url = doc.find('filename').text if video_url is None: xml_bytes = xml.etree.ElementTree.tostring(doc) - raise ExtractorError(u'Cannot find video URL in document %r' % + raise ExtractorError('Cannot find video URL in document %r' % xml_bytes) thumbnail = doc.find('imageurl').text - duration_str = doc.find('duration').text - m = re.match( - r'^(?P<hours>[0-9]+):(?P<minutes>[0-9]{2}):(?P<seconds>[0-9]{2}):(?P<ms>[0-9]*)$', - duration_str) - if m: - duration = ( - (int(m.group('hours')) * 60 * 60) + - (int(m.group('minutes')) * 60) + - (int(m.group('seconds'))) - ) - else: - duration = None + duration = parse_duration(doc.find('duration').text) return { 'id': video_id, diff --git a/youtube_dl/extractor/clipsyndicate.py b/youtube_dl/extractor/clipsyndicate.py index 9ab6a4ab6..02a1667fa 100644 --- a/youtube_dl/extractor/clipsyndicate.py +++ b/youtube_dl/extractor/clipsyndicate.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -11,13 +13,14 @@ class ClipsyndicateIE(InfoExtractor): _VALID_URL = r'http://www\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)' _TEST = { - u'url': u'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe', - u'md5': u'4d7d549451bad625e0ff3d7bd56d776c', - u'info_dict': { - u'id': u'4629301', - u'ext': u'mp4', - u'title': u'Brick Briscoe', - u'duration': 612, + 'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe', + 'md5': '4d7d549451bad625e0ff3d7bd56d776c', + 'info_dict': { + 'id': '4629301', + 'ext': 'mp4', + 'title': 'Brick Briscoe', + 'duration': 612, + 'thumbnail': 're:^https?://.+\.jpg', }, } @@ -26,13 +29,13 @@ class ClipsyndicateIE(InfoExtractor): video_id = mobj.group('id') js_player = self._download_webpage( 'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id, - video_id, u'Downlaoding player') + video_id, 'Downlaoding player') # it includes a required token - flvars = self._search_regex(r'flvars: "(.*?)"', js_player, u'flvars') + flvars = self._search_regex(r'flvars: "(.*?)"', js_player, 'flvars') pdoc = self._download_xml( 'http://eplayer.clipsyndicate.com/osmf/playlist?%s' % flvars, - video_id, u'Downloading video info', + video_id, 'Downloading video info', transform_source=fix_xml_ampersands) track_doc = pdoc.find('trackList/track') diff --git a/youtube_dl/extractor/cnet.py b/youtube_dl/extractor/cnet.py new file mode 100644 index 000000000..f5ab443d2 --- /dev/null +++ b/youtube_dl/extractor/cnet.py @@ -0,0 +1,75 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + int_or_none, +) + + +class CNETIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/' + _TEST = { + 'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/', + 'md5': '041233212a0d06b179c87cbcca1577b8', + 'info_dict': { + 'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60', + 'ext': 'mp4', + 'title': 'Hands-on with Microsoft Windows 8.1 Update', + 'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.', + 'thumbnail': 're:^http://.*/flmswindows8.jpg$', + 'uploader_id': 'sarah.mitroff@cbsinteractive.com', + 'uploader': 'Sarah Mitroff', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') + + webpage = self._download_webpage(url, display_id) + data_json = self._html_search_regex( + r"<div class=\"cnetVideoPlayer\" data-cnet-video-options='([^']+)'", + webpage, 'data json') + data = json.loads(data_json) + vdata = data['video'] + if not vdata: + vdata = data['videos'][0] + if not vdata: + raise ExtractorError('Cannot find video data') + + video_id = vdata['id'] + title = vdata['headline'] + description = vdata.get('dek') + thumbnail = vdata.get('image', {}).get('path') + author = vdata.get('author') + if author: + uploader = '%s %s' % (author['firstName'], author['lastName']) + uploader_id = author.get('email') + else: + uploader = None + uploader_id = None + + formats = [{ + 'format_id': '%s-%s-%s' % ( + f['type'], f['format'], + int_or_none(f.get('bitrate'), 1000, default='')), + 'url': f['uri'], + 'tbr': int_or_none(f.get('bitrate'), 1000), + } for f in vdata['files']['data']] + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'formats': formats, + 'description': description, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index d50fcdbdb..0c99887a2 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -7,8 +7,8 @@ from .mtv import MTVServicesInfoExtractor from ..utils import ( compat_str, compat_urllib_parse, - ExtractorError, + float_or_none, unified_strdate, ) @@ -32,31 +32,34 @@ class ComedyCentralIE(MTVServicesInfoExtractor): class ComedyCentralShowsIE(InfoExtractor): - IE_DESC = 'The Daily Show / Colbert Report' + IE_DESC = 'The Daily Show / The Colbert Report' # urls can be abbreviations like :thedailyshow or :colbert # urls for episodes like: # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day # or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524 - _VALID_URL = r"""^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport) - |(https?://)?(www\.)? - (?P<showname>thedailyshow|colbertnation)\.com/ - (full-episodes/(?P<episode>.*)| + _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport) + |https?://(:www\.)? + (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/ + (full-episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)| (?P<clip> - (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?)) - |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))| + (?:(?:guests/[^/]+|videos)/[^/]+/(?P<videotitle>[^/?#]+)) + |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?)) + |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)) + )| (?P<interview> - extended-interviews/(?P<interID>[0-9]+)/playlist_tds_extended_(?P<interview_title>.*?)/.*?))) - $""" + extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?))) + (?:[?#].*|$)''' _TEST = { - 'url': 'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart', - 'file': '422212.mp4', + 'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart', 'md5': '4e2f5cb088a83cd8cdb7756132f9739d', 'info_dict': { - "upload_date": "20121214", - "description": "Kristen Stewart", - "uploader": "thedailyshow", - "title": "thedailyshow-kristen-stewart part 1" + 'id': 'ab9ab3e7-5a98-4dbe-8b21-551dc0523d55', + 'ext': 'mp4', + 'upload_date': '20121213', + 'description': 'Kristen Stewart learns to let loose in "On the Road."', + 'uploader': 'thedailyshow', + 'title': 'thedailyshow kristen-stewart part 1', } } @@ -79,11 +82,6 @@ class ComedyCentralShowsIE(InfoExtractor): '400': (384, 216), } - @classmethod - def suitable(cls, url): - """Receives a URL and returns True if suitable for this IE.""" - return re.match(cls._VALID_URL, url, re.VERBOSE) is not None - @staticmethod def _transform_rtmp_url(rtmp_video_url): m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\.comedystor/.*)$', rtmp_video_url) @@ -99,14 +97,16 @@ class ComedyCentralShowsIE(InfoExtractor): if mobj.group('shortname'): if mobj.group('shortname') in ('tds', 'thedailyshow'): - url = 'http://www.thedailyshow.com/full-episodes/' + url = 'http://thedailyshow.cc.com/full-episodes/' else: - url = 'http://www.colbertnation.com/full-episodes/' + url = 'http://thecolbertreport.cc.com/full-episodes/' mobj = re.match(self._VALID_URL, url, re.VERBOSE) assert mobj is not None if mobj.group('clip'): - if mobj.group('showname') == 'thedailyshow': + if mobj.group('videotitle'): + epTitle = mobj.group('videotitle') + elif mobj.group('showname') == 'thedailyshow': epTitle = mobj.group('tdstitle') else: epTitle = mobj.group('cntitle') @@ -120,9 +120,9 @@ class ComedyCentralShowsIE(InfoExtractor): epTitle = mobj.group('showname') else: epTitle = mobj.group('episode') + show_name = mobj.group('showname') - self.report_extraction(epTitle) - webpage,htmlHandle = self._download_webpage_handle(url, epTitle) + webpage, htmlHandle = self._download_webpage_handle(url, epTitle) if dlNewest: url = htmlHandle.geturl() mobj = re.match(self._VALID_URL, url, re.VERBOSE) @@ -130,71 +130,86 @@ class ComedyCentralShowsIE(InfoExtractor): raise ExtractorError('Invalid redirected URL: ' + url) if mobj.group('episode') == '': raise ExtractorError('Redirected URL is still not specific: ' + url) - epTitle = mobj.group('episode') + epTitle = mobj.group('episode').rpartition('/')[-1] mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage) - if len(mMovieParams) == 0: # The Colbert Report embeds the information in a without # a URL prefix; so extract the alternate reference # and then add the URL prefix manually. - altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage) + altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video|playlist).*?:.*?)"', webpage) if len(altMovieParams) == 0: raise ExtractorError('unable to find Flash URL in webpage ' + url) else: mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])] uri = mMovieParams[0][1] - indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri}) - idoc = self._download_xml(indexUrl, epTitle, - 'Downloading show index', - 'unable to download episode index') - - results = [] - - itemEls = idoc.findall('.//item') - for partNum,itemEl in enumerate(itemEls): - mediaId = itemEl.findall('./guid')[0].text - shortMediaId = mediaId.split(':')[-1] - showId = mediaId.split(':')[-2].replace('.com', '') - officialTitle = itemEl.findall('./title')[0].text - officialDate = unified_strdate(itemEl.findall('./pubDate')[0].text) - - configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' + - compat_urllib_parse.urlencode({'uri': mediaId})) - cdoc = self._download_xml(configUrl, epTitle, - 'Downloading configuration for %s' % shortMediaId) + # Correct cc.com in uri + uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.cc.com', uri) + + index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse.urlencode({'uri': uri})) + idoc = self._download_xml( + index_url, epTitle, + 'Downloading show index', 'Unable to download episode index') + + title = idoc.find('./channel/title').text + description = idoc.find('./channel/description').text + + entries = [] + item_els = idoc.findall('.//item') + for part_num, itemEl in enumerate(item_els): + upload_date = unified_strdate(itemEl.findall('./pubDate')[0].text) + thumbnail = itemEl.find('.//{http://search.yahoo.com/mrss/}thumbnail').attrib.get('url') + + content = itemEl.find('.//{http://search.yahoo.com/mrss/}content') + duration = float_or_none(content.attrib.get('duration')) + mediagen_url = content.attrib['url'] + guid = itemEl.find('./guid').text.rpartition(':')[-1] + + cdoc = self._download_xml( + mediagen_url, epTitle, + 'Downloading configuration for segment %d / %d' % (part_num + 1, len(item_els))) turls = [] for rendition in cdoc.findall('.//rendition'): finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text) turls.append(finfo) - if len(turls) == 0: - self._downloader.report_error('unable to download ' + mediaId + ': No videos found') - continue - formats = [] for format, rtmp_video_url in turls: w, h = self._video_dimensions.get(format, (None, None)) formats.append({ + 'format_id': 'vhttp-%s' % format, 'url': self._transform_rtmp_url(rtmp_video_url), 'ext': self._video_extensions.get(format, 'mp4'), - 'format_id': format, 'height': h, 'width': w, }) + formats.append({ + 'format_id': 'rtmp-%s' % format, + 'url': rtmp_video_url, + 'ext': self._video_extensions.get(format, 'mp4'), + 'height': h, + 'width': w, + }) + self._sort_formats(formats) - effTitle = showId + '-' + epTitle + ' part ' + compat_str(partNum+1) - results.append({ - 'id': shortMediaId, + virtual_id = show_name + ' ' + epTitle + ' part ' + compat_str(part_num + 1) + entries.append({ + 'id': guid, + 'title': virtual_id, 'formats': formats, - 'uploader': showId, - 'upload_date': officialDate, - 'title': effTitle, - 'thumbnail': None, - 'description': compat_str(officialTitle), + 'uploader': show_name, + 'upload_date': upload_date, + 'duration': duration, + 'thumbnail': thumbnail, + 'description': description, }) - return results + return { + '_type': 'playlist', + 'entries': entries, + 'title': show_name + ' ' + title, + 'description': description, + } diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 647720c8a..da4193734 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -74,7 +74,7 @@ class InfoExtractor(object): "http", "https", "rtsp", "rtmp", "m3u8" or so. * preference Order number of this format. If this field is present and not None, the formats get sorted - by this field. + by this field, regardless of all other values. -1 for default (order by other properties), -2 or smaller for less than default. * quality Order number of the video quality of this @@ -252,6 +252,17 @@ class InfoExtractor(object): outf.write(webpage_bytes) content = webpage_bytes.decode(encoding, 'replace') + + if (u'<title>Access to this site is blocked</title>' in content and + u'Websense' in content[:512]): + msg = u'Access to this webpage has been blocked by Websense filtering software in your network.' + blocked_iframe = self._html_search_regex( + r'<iframe src="([^"]+)"', content, + u'Websense information URL', default=None) + if blocked_iframe: + msg += u' Visit %s for more details' % blocked_iframe + raise ExtractorError(msg, expected=True) + return (content, urlh) def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index 2a8eda9ef..b6552c542 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -4,6 +4,7 @@ import re from .common import InfoExtractor from ..utils import ( + int_or_none, unescapeHTML, find_xpath_attr, ) @@ -54,18 +55,29 @@ class CSpanIE(InfoExtractor): info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id data = self._download_json(info_url, video_id) - url = unescapeHTML(data['video']['files'][0]['path']['#text']) - - doc = self._download_xml('http://www.c-span.org/common/services/flashXml.php?programid=' + video_id, + doc = self._download_xml( + 'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id, video_id) - def find_string(s): - return find_xpath_attr(doc, './/string', 'name', s).text + title = find_xpath_attr(doc, './/string', 'name', 'title').text + thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text + + files = data['video']['files'] + + entries = [{ + 'id': '%s_%d' % (video_id, partnum + 1), + 'title': ( + title if len(files) == 1 else + '%s part %d' % (title, partnum + 1)), + 'url': unescapeHTML(f['path']['#text']), + 'description': description, + 'thumbnail': thumbnail, + 'duration': int_or_none(f.get('length', {}).get('#text')), + } for partnum, f in enumerate(files)] return { + '_type': 'playlist', + 'entries': entries, + 'title': title, 'id': video_id, - 'title': find_string('title'), - 'url': url, - 'description': description, - 'thumbnail': find_string('poster'), } diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 10b97d8ca..5504d93eb 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -8,7 +8,6 @@ from .subtitles import SubtitlesInfoExtractor from ..utils import ( compat_urllib_request, compat_str, - get_element_by_attribute, get_element_by_id, orderedSet, str_to_int, @@ -180,7 +179,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): IE_NAME = u'dailymotion:playlist' _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/' - _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>' + _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"' _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s' def _extract_entries(self, id): @@ -190,10 +189,9 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): webpage = self._download_webpage(request, id, u'Downloading page %s' % pagenum) - playlist_el = get_element_by_attribute(u'class', u'row video_list', webpage) - video_ids.extend(re.findall(r'data-id="(.+?)"', playlist_el)) + video_ids.extend(re.findall(r'data-id="(.+?)"', webpage)) - if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: + if re.search(self._MORE_PAGES_INDICATOR, webpage) is None: break return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion') for video_id in orderedSet(video_ids)] @@ -212,8 +210,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): class DailymotionUserIE(DailymotionPlaylistIE): IE_NAME = u'dailymotion:user' - _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)' - _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/user/.+?".*?>.*?</a>.*?</div>' + _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)' _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s' def _real_extract(self, url): diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 885944c5e..2ae6ecc12 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -10,9 +10,10 @@ class DiscoveryIE(InfoExtractor): _VALID_URL = r'http://dsc\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?' _TEST = { 'url': 'http://dsc.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm', - 'file': '614784.mp4', 'md5': 'e12614f9ee303a6ccef415cb0793eba2', 'info_dict': { + 'id': '614784', + 'ext': 'mp4', 'title': 'MythBusters: Mission Impossible Outtakes', 'description': ('Watch Jamie Hyneman and Adam Savage practice being' ' each other -- to the point of confusing Jamie\'s dog -- and ' @@ -34,7 +35,7 @@ class DiscoveryIE(InfoExtractor): formats = [] for f in info['mp4']: formats.append( - {'url': f['src'], r'ext': r'mp4', 'tbr': int(f['bitrate'][:-1])}) + {'url': f['src'], 'ext': 'mp4', 'tbr': int(f['bitrate'][:-1])}) return { 'id': info['contentId'], diff --git a/youtube_dl/extractor/ehow.py b/youtube_dl/extractor/ehow.py index 2bb77aec6..f8f49a013 100644 --- a/youtube_dl/extractor/ehow.py +++ b/youtube_dl/extractor/ehow.py @@ -1,23 +1,25 @@ +from __future__ import unicode_literals + import re from ..utils import ( compat_urllib_parse, - determine_ext ) from .common import InfoExtractor class EHowIE(InfoExtractor): - IE_NAME = u'eHow' - _VALID_URL = r'(?:https?://)?(?:www\.)?ehow\.com/[^/_?]*_(?P<id>[0-9]+)' + IE_NAME = 'eHow' + _VALID_URL = r'https?://(?:www\.)?ehow\.com/[^/_?]*_(?P<id>[0-9]+)' _TEST = { - u'url': u'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html', - u'file': u'12245069.flv', - u'md5': u'9809b4e3f115ae2088440bcb4efbf371', - u'info_dict': { - u"title": u"Hardwood Flooring Basics", - u"description": u"Hardwood flooring may be time consuming, but its ultimately a pretty straightforward concept. Learn about hardwood flooring basics with help from a hardware flooring business owner in this free video...", - u"uploader": u"Erick Nathan" + 'url': 'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html', + 'md5': '9809b4e3f115ae2088440bcb4efbf371', + 'info_dict': { + 'id': '12245069', + 'ext': 'flv', + 'title': 'Hardwood Flooring Basics', + 'description': 'Hardwood flooring may be time consuming, but its ultimately a pretty straightforward concept. Learn about hardwood flooring basics with help from a hardware flooring business owner in this free video...', + 'uploader': 'Erick Nathan', } } @@ -26,21 +28,16 @@ class EHowIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)', - webpage, u'video URL') - final_url = compat_urllib_parse.unquote(video_url) - uploader = self._search_regex(r'<meta name="uploader" content="(.+?)" />', - webpage, u'uploader') + webpage, 'video URL') + final_url = compat_urllib_parse.unquote(video_url) + uploader = self._html_search_meta('uploader', webpage) title = self._og_search_title(webpage).replace(' | eHow', '') - ext = determine_ext(final_url) return { - '_type': 'video', - 'id': video_id, - 'url': final_url, - 'ext': ext, - 'title': title, - 'thumbnail': self._og_search_thumbnail(webpage), + 'id': video_id, + 'url': final_url, + 'title': title, + 'thumbnail': self._og_search_thumbnail(webpage), 'description': self._og_search_description(webpage), - 'uploader': uploader, + 'uploader': uploader, } - diff --git a/youtube_dl/extractor/franceculture.py b/youtube_dl/extractor/franceculture.py new file mode 100644 index 000000000..898e0dda7 --- /dev/null +++ b/youtube_dl/extractor/franceculture.py @@ -0,0 +1,77 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + compat_parse_qs, + compat_urlparse, +) + + +class FranceCultureIE(InfoExtractor): + _VALID_URL = r'(?P<baseurl>http://(?:www\.)?franceculture\.fr/)player/reecouter\?play=(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.franceculture.fr/player/reecouter?play=4795174', + 'info_dict': { + 'id': '4795174', + 'ext': 'mp3', + 'title': 'Rendez-vous au pays des geeks', + 'vcodec': 'none', + 'uploader': 'Colette Fellous', + 'upload_date': '20140301', + 'duration': 3601, + 'thumbnail': r're:^http://www\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$', + 'description': 'Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats-Unis dans la S ...', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + baseurl = mobj.group('baseurl') + + webpage = self._download_webpage(url, video_id) + params_code = self._search_regex( + r"<param name='movie' value='/sites/all/modules/rf/rf_player/swf/loader.swf\?([^']+)' />", + webpage, 'parameter code') + params = compat_parse_qs(params_code) + video_url = compat_urlparse.urljoin(baseurl, params['urlAOD'][0]) + + title = self._html_search_regex( + r'<h1 class="title[^"]+">(.+?)</h1>', webpage, 'title') + uploader = self._html_search_regex( + r'(?s)<div id="emission".*?<span class="author">(.*?)</span>', + webpage, 'uploader', fatal=False) + thumbnail_part = self._html_search_regex( + r'(?s)<div id="emission".*?<img src="([^"]+)"', webpage, + 'thumbnail', fatal=False) + if thumbnail_part is None: + thumbnail = None + else: + thumbnail = compat_urlparse.urljoin(baseurl, thumbnail_part) + description = self._html_search_regex( + r'(?s)<p class="desc">(.*?)</p>', webpage, 'description') + + info = json.loads(params['infoData'][0])[0] + duration = info.get('media_length') + upload_date_candidate = info.get('media_section5') + upload_date = ( + upload_date_candidate + if (upload_date_candidate is not None and + re.match(r'[0-9]{8}$', upload_date_candidate)) + else None) + + return { + 'id': video_id, + 'url': video_url, + 'vcodec': 'none' if video_url.lower().endswith('.mp3') else None, + 'duration': duration, + 'uploader': uploader, + 'upload_date': upload_date, + 'title': title, + 'thumbnail': thumbnail, + 'description': description, + } diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 4d649fe71..6a2ce0d6d 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -25,6 +25,7 @@ from ..utils import ( from .brightcove import BrightcoveIE from .ooyala import OoyalaIE from .rutv import RUTVIE +from .smotri import SmotriIE class GenericIE(InfoExtractor): @@ -81,6 +82,17 @@ class GenericIE(InfoExtractor): }, 'add_ie': ['Brightcove'], }, + { + 'url': 'http://www.championat.com/video/football/v/87/87499.html', + 'md5': 'fb973ecf6e4a78a67453647444222983', + 'info_dict': { + 'id': '3414141473001', + 'ext': 'mp4', + 'title': 'Видео. Удаление Дзагоева (ЦСКА)', + 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"', + 'uploader': 'Championat', + }, + }, # Direct link to a video { 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4', @@ -102,20 +114,6 @@ class GenericIE(InfoExtractor): 'title': '2cc213299525360.mov', # that's what we get }, }, - # second style of embedded ooyala videos - { - 'url': 'http://www.smh.com.au/tv/business/show/financial-review-sunday/behind-the-scenes-financial-review-sunday--4350201.html', - 'info_dict': { - 'id': '13djJjYjptA1XpPx8r9kuzPyj3UZH0Uk', - 'ext': 'mp4', - 'title': 'Behind-the-scenes: Financial Review Sunday ', - 'description': 'Step inside Channel Nine studios for an exclusive tour of its upcoming financial business show.', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }, # google redirect { 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE', @@ -197,6 +195,36 @@ class GenericIE(InfoExtractor): 'description': 'No description', }, }, + # arte embed + { + 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html', + 'md5': '7653032cbb25bf6c80d80f217055fa43', + 'info_dict': { + 'id': '048195-004_PLUS7-F', + 'ext': 'flv', + 'title': 'X:enius', + 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168', + 'upload_date': '20140320', + }, + 'params': { + 'skip_download': 'Requires rtmpdump' + } + }, + # smotri embed + { + 'url': 'http://rbctv.rbc.ru/archive/news/562949990879132.shtml', + 'md5': 'ec40048448e9284c9a1de77bb188108b', + 'info_dict': { + 'id': 'v27008541fad', + 'ext': 'mp4', + 'title': 'Крым и Севастополь вошли в состав России', + 'description': 'md5:fae01b61f68984c7bd2fa741e11c3175', + 'duration': 900, + 'upload_date': '20140318', + 'uploader': 'rbctv_2012_4', + 'uploader_id': 'rbctv_2012_4', + }, + }, ] def report_download_webpage(self, video_id): @@ -285,13 +313,16 @@ class GenericIE(InfoExtractor): if not parsed_url.scheme: default_search = self._downloader.params.get('default_search') if default_search is None: - default_search = 'auto' + default_search = 'auto_warning' - if default_search == 'auto': + if default_search in ('auto', 'auto_warning'): if '/' in url: self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http') return self.url_result('http://' + url) else: + if default_search == 'auto_warning': + self._downloader.report_warning( + 'Falling back to youtube search for %s . Set --default-search to "auto" to suppress this warning.' % url) return self.url_result('ytsearch:' + url) else: assert ':' in default_search @@ -525,6 +556,18 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result(mobj.group('url'), 'TED') + # Look for embedded arte.tv player + mobj = re.search( + r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'ArteTVEmbed') + + # Look for embedded smotri.com player + smotri_url = SmotriIE._extract_url(webpage) + if smotri_url: + return self.url_result(smotri_url, 'Smotri') + # Start with something easy: JW Player in SWFObject mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) if mobj is None: diff --git a/youtube_dl/extractor/huffpost.py b/youtube_dl/extractor/huffpost.py index 0d1ea6802..94e7cf790 100644 --- a/youtube_dl/extractor/huffpost.py +++ b/youtube_dl/extractor/huffpost.py @@ -21,9 +21,10 @@ class HuffPostIE(InfoExtractor): _TEST = { 'url': 'http://live.huffingtonpost.com/r/segment/legalese-it/52dd3e4b02a7602131000677', - 'file': '52dd3e4b02a7602131000677.mp4', 'md5': '55f5e8981c1c80a64706a44b74833de8', 'info_dict': { + 'id': '52dd3e4b02a7602131000677', + 'ext': 'mp4', 'title': 'Legalese It! with @MikeSacksHP', 'description': 'This week on Legalese It, Mike talks to David Bosco about his new book on the ICC, "Rough Justice," he also discusses the Virginia AG\'s historic stance on gay marriage, the execution of Edgar Tamayo, the ICC\'s delay of Kenya\'s President and more. ', 'duration': 1549, diff --git a/youtube_dl/extractor/ign.py b/youtube_dl/extractor/ign.py index 381af91e4..cfeaa4146 100644 --- a/youtube_dl/extractor/ign.py +++ b/youtube_dl/extractor/ign.py @@ -1,10 +1,8 @@ +from __future__ import unicode_literals + import re -import json from .common import InfoExtractor -from ..utils import ( - determine_ext, -) class IGNIE(InfoExtractor): @@ -14,52 +12,57 @@ class IGNIE(InfoExtractor): """ _VALID_URL = r'https?://.+?\.ign\.com/(?P<type>videos|show_videos|articles|(?:[^/]*/feature))(/.+)?/(?P<name_or_id>.+)' - IE_NAME = u'ign.com' + IE_NAME = 'ign.com' _CONFIG_URL_TEMPLATE = 'http://www.ign.com/videos/configs/id/%s.config' - _DESCRIPTION_RE = [r'<span class="page-object-description">(.+?)</span>', - r'id="my_show_video">.*?<p>(.*?)</p>', - ] + _DESCRIPTION_RE = [ + r'<span class="page-object-description">(.+?)</span>', + r'id="my_show_video">.*?<p>(.*?)</p>', + ] _TESTS = [ { - u'url': u'http://www.ign.com/videos/2013/06/05/the-last-of-us-review', - u'file': u'8f862beef863986b2785559b9e1aa599.mp4', - u'md5': u'eac8bdc1890980122c3b66f14bdd02e9', - u'info_dict': { - u'title': u'The Last of Us Review', - u'description': u'md5:c8946d4260a4d43a00d5ae8ed998870c', + 'url': 'http://www.ign.com/videos/2013/06/05/the-last-of-us-review', + 'md5': 'eac8bdc1890980122c3b66f14bdd02e9', + 'info_dict': { + 'id': '8f862beef863986b2785559b9e1aa599', + 'ext': 'mp4', + 'title': 'The Last of Us Review', + 'description': 'md5:c8946d4260a4d43a00d5ae8ed998870c', } }, { - u'url': u'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind', - u'playlist': [ + 'url': 'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind', + 'playlist': [ { - u'file': u'5ebbd138523268b93c9141af17bec937.mp4', - u'info_dict': { - u'title': u'GTA 5 Video Review', - u'description': u'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.', + 'info_dict': { + 'id': '5ebbd138523268b93c9141af17bec937', + 'ext': 'mp4', + 'title': 'GTA 5 Video Review', + 'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.', }, }, { - u'file': u'638672ee848ae4ff108df2a296418ee2.mp4', - u'info_dict': { - u'title': u'26 Twisted Moments from GTA 5 in Slow Motion', - u'description': u'The twisted beauty of GTA 5 in stunning slow motion.', + 'info_dict': { + 'id': '638672ee848ae4ff108df2a296418ee2', + 'ext': 'mp4', + 'title': '26 Twisted Moments from GTA 5 in Slow Motion', + 'description': 'The twisted beauty of GTA 5 in stunning slow motion.', }, }, ], - u'params': { - u'skip_download': True, + 'params': { + 'skip_download': True, }, }, ] def _find_video_id(self, webpage): - res_id = [r'data-video-id="(.+?)"', - r'<object id="vid_(.+?)"', - r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"', - ] + res_id = [ + r'data-video-id="(.+?)"', + r'<object id="vid_(.+?)"', + r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"', + ] return self._search_regex(res_id, webpage, 'video id') def _real_extract(self, url): @@ -68,7 +71,7 @@ class IGNIE(InfoExtractor): page_type = mobj.group('type') webpage = self._download_webpage(url, name_or_id) if page_type == 'articles': - video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, u'video url') + video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, 'video url') return self.url_result(video_url, ie='IGN') elif page_type != 'video': multiple_urls = re.findall( @@ -80,41 +83,37 @@ class IGNIE(InfoExtractor): video_id = self._find_video_id(webpage) result = self._get_video_info(video_id) description = self._html_search_regex(self._DESCRIPTION_RE, - webpage, 'video description', - flags=re.DOTALL) + webpage, 'video description', flags=re.DOTALL) result['description'] = description return result def _get_video_info(self, video_id): config_url = self._CONFIG_URL_TEMPLATE % video_id - config = json.loads(self._download_webpage(config_url, video_id, - u'Downloading video info')) + config = self._download_json(config_url, video_id) media = config['playlist']['media'] - video_url = media['url'] - return {'id': media['metadata']['videoId'], - 'url': video_url, - 'ext': determine_ext(video_url), - 'title': media['metadata']['title'], - 'thumbnail': media['poster'][0]['url'].replace('{size}', 'grande'), - } + return { + 'id': media['metadata']['videoId'], + 'url': media['url'], + 'title': media['metadata']['title'], + 'thumbnail': media['poster'][0]['url'].replace('{size}', 'grande'), + } class OneUPIE(IGNIE): - """Extractor for 1up.com, it uses the ign videos system.""" - _VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)' IE_NAME = '1up.com' _DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>' _TEST = { - u'url': u'http://gamevideos.1up.com/video/id/34976', - u'file': u'34976.mp4', - u'md5': u'68a54ce4ebc772e4b71e3123d413163d', - u'info_dict': { - u'title': u'Sniper Elite V2 - Trailer', - u'description': u'md5:5d289b722f5a6d940ca3136e9dae89cf', + 'url': 'http://gamevideos.1up.com/video/id/34976', + 'md5': '68a54ce4ebc772e4b71e3123d413163d', + 'info_dict': { + 'id': '34976', + 'ext': 'mp4', + 'title': 'Sniper Elite V2 - Trailer', + 'description': 'md5:5d289b722f5a6d940ca3136e9dae89cf', } } @@ -123,7 +122,6 @@ class OneUPIE(IGNIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - id = mobj.group('name_or_id') result = super(OneUPIE, self)._real_extract(url) - result['id'] = id + result['id'] = mobj.group('name_or_id') return result diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index 63141af27..b5372bf7a 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -3,6 +3,9 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import ( + int_or_none, +) class InstagramIE(InfoExtractor): @@ -37,3 +40,68 @@ class InstagramIE(InfoExtractor): 'uploader_id': uploader_id, 'description': desc, } + + +class InstagramUserIE(InfoExtractor): + _VALID_URL = r'http://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])' + IE_DESC = 'Instagram user profile' + IE_NAME = 'instagram:user' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + uploader_id = mobj.group('username') + + entries = [] + page_count = 0 + media_url = 'http://instagram.com/%s/media' % uploader_id + while True: + page = self._download_json( + media_url, uploader_id, + note='Downloading page %d ' % (page_count + 1), + ) + page_count += 1 + + for it in page['items']: + if it.get('type') != 'video': + continue + like_count = int_or_none(it.get('likes', {}).get('count')) + user = it.get('user', {}) + + formats = [{ + 'format_id': k, + 'height': v.get('height'), + 'width': v.get('width'), + 'url': v['url'], + } for k, v in it['videos'].items()] + self._sort_formats(formats) + + thumbnails_el = it.get('images', {}) + thumbnail = thumbnails_el.get('thumbnail', {}).get('url') + + title = it.get('caption', {}).get('text', it['id']) + + entries.append({ + 'id': it['id'], + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + 'webpage_url': it.get('link'), + 'uploader': user.get('full_name'), + 'uploader_id': user.get('username'), + 'like_count': like_count, + 'timestamp': int_or_none(it.get('created_time')), + }) + + if not page['items']: + break + max_id = page['items'][-1]['id'] + media_url = ( + 'http://instagram.com/%s/media?max_id=%s' % ( + uploader_id, max_id)) + + return { + '_type': 'playlist', + 'entries': entries, + 'id': uploader_id, + 'title': uploader_id, + } diff --git a/youtube_dl/extractor/keezmovies.py b/youtube_dl/extractor/keezmovies.py index 29658a7d6..75b63cffb 100644 --- a/youtube_dl/extractor/keezmovies.py +++ b/youtube_dl/extractor/keezmovies.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import os import re @@ -11,22 +13,22 @@ from ..aes import ( aes_decrypt_text ) + class KeezMoviesIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>keezmovies\.com/video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)' + _VALID_URL = r'^https?://(?:www\.)?keezmovies\.com/video/.+?(?P<videoid>[0-9]+)(?:[/?&]|$)' _TEST = { - u'url': u'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711', - u'file': u'1214711.mp4', - u'md5': u'6e297b7e789329923fcf83abb67c9289', - u'info_dict': { - u"title": u"Petite Asian Lady Mai Playing In Bathtub", - u"age_limit": 18, + 'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711', + 'file': '1214711.mp4', + 'md5': '6e297b7e789329923fcf83abb67c9289', + 'info_dict': { + 'title': 'Petite Asian Lady Mai Playing In Bathtub', + 'age_limit': 18, } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('videoid') - url = 'http://www.' + mobj.group('url') req = compat_urllib_request.Request(url) req.add_header('Cookie', 'age_verified=1') @@ -38,10 +40,10 @@ class KeezMoviesIE(InfoExtractor): embedded_url = mobj.group(1) return self.url_result(embedded_url) - video_title = self._html_search_regex(r'<h1 [^>]*>([^<]+)', webpage, u'title') - video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&', webpage, u'video_url')) - if webpage.find('encrypted=true')!=-1: - password = self._html_search_regex(r'video_title=(.+?)&', webpage, u'password') + video_title = self._html_search_regex(r'<h1 [^>]*>([^<]+)', webpage, 'title') + video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&', webpage, 'video_url')) + if 'encrypted=true' in webpage: + password = self._html_search_regex(r'video_title=(.+?)&', webpage, 'password') video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8') path = compat_urllib_parse_urlparse(video_url).path extension = os.path.splitext(path)[1][1:] diff --git a/youtube_dl/extractor/kickstarter.py b/youtube_dl/extractor/kickstarter.py index 50bc883ef..961dd1aa6 100644 --- a/youtube_dl/extractor/kickstarter.py +++ b/youtube_dl/extractor/kickstarter.py @@ -1,37 +1,39 @@ +# encoding: utf-8 +from __future__ import unicode_literals + import re from .common import InfoExtractor class KickStarterIE(InfoExtractor): - _VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>\d*)/.*' + _VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>[^/]*)/.*' _TEST = { - u"url": u"https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant?ref=home_location", - u"file": u"1404461844.mp4", - u"md5": u"c81addca81327ffa66c642b5d8b08cab", - u"info_dict": { - u"title": u"Intersection: The Story of Josh Grant by Kyle Cowling", + 'url': 'https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant?ref=home_location', + 'md5': 'c81addca81327ffa66c642b5d8b08cab', + 'info_dict': { + 'id': '1404461844', + 'ext': 'mp4', + 'title': 'Intersection: The Story of Josh Grant by Kyle Cowling', + 'description': 'A unique motocross documentary that examines the ' + 'life and mind of one of sports most elite athletes: Josh Grant.', }, } def _real_extract(self, url): m = re.match(self._VALID_URL, url) video_id = m.group('id') - webpage_src = self._download_webpage(url, video_id) + webpage = self._download_webpage(url, video_id) - video_url = self._search_regex(r'data-video="(.*?)">', - webpage_src, u'video URL') - if 'mp4' in video_url: - ext = 'mp4' - else: - ext = 'flv' - video_title = self._html_search_regex(r"<title>(.*?)</title>", - webpage_src, u'title').rpartition(u'\u2014 Kickstarter')[0].strip() + video_url = self._search_regex(r'data-video-url="(.*?)"', + webpage, 'video URL') + video_title = self._html_search_regex(r'<title>(.*?)</title>', + webpage, 'title').rpartition('— Kickstarter')[0].strip() - results = [{ - 'id': video_id, - 'url': video_url, - 'title': video_title, - 'ext': ext, - }] - return results + return { + 'id': video_id, + 'url': video_url, + 'title': video_title, + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + } diff --git a/youtube_dl/extractor/metacritic.py b/youtube_dl/extractor/metacritic.py index 465ac4916..07f072924 100644 --- a/youtube_dl/extractor/metacritic.py +++ b/youtube_dl/extractor/metacritic.py @@ -13,8 +13,9 @@ class MetacriticIE(InfoExtractor): _TEST = { 'url': 'http://www.metacritic.com/game/playstation-4/infamous-second-son/trailers/3698222', - 'file': '3698222.mp4', 'info_dict': { + 'id': '3698222', + 'ext': 'mp4', 'title': 'inFamous: Second Son - inSide Sucker Punch: Smoke & Mirrors', 'description': 'Take a peak behind-the-scenes to see how Sucker Punch brings smoke into the universe of inFAMOUS Second Son on the PS4.', 'duration': 221, diff --git a/youtube_dl/extractor/mooshare.py b/youtube_dl/extractor/mooshare.py index f1875add5..7d21ea18f 100644 --- a/youtube_dl/extractor/mooshare.py +++ b/youtube_dl/extractor/mooshare.py @@ -14,7 +14,7 @@ from ..utils import ( class MooshareIE(InfoExtractor): IE_NAME = 'mooshare' IE_DESC = 'Mooshare.biz' - _VALID_URL = r'http://mooshare\.biz/(?P<id>[\da-z]{12})' + _VALID_URL = r'http://(?:www\.)?mooshare\.biz/(?P<id>[\da-z]{12})' _TESTS = [ { diff --git a/youtube_dl/extractor/morningstar.py b/youtube_dl/extractor/morningstar.py new file mode 100644 index 000000000..4f7a5d2e4 --- /dev/null +++ b/youtube_dl/extractor/morningstar.py @@ -0,0 +1,47 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class MorningstarIE(InfoExtractor): + IE_DESC = 'morningstar.com' + _VALID_URL = r'https?://(?:www\.)?morningstar\.com/cover/videocenter\.aspx\?id=(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://www.morningstar.com/cover/videocenter.aspx?id=615869', + 'md5': '6c0acface7a787aadc8391e4bbf7b0f5', + 'info_dict': { + 'id': '615869', + 'ext': 'mp4', + 'title': 'Get Ahead of the Curve on 2013 Taxes', + 'description': "Vanguard's Joel Dickson on managing higher tax rates for high-income earners and fund capital-gain distributions in 2013.", + 'thumbnail': r're:^https?://.*m(?:orning)?star\.com/.+thumb\.jpg$' + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex( + r'<h1 id="titleLink">(.*?)</h1>', webpage, 'title') + video_url = self._html_search_regex( + r'<input type="hidden" id="hidVideoUrl" value="([^"]+)"', + webpage, 'video URL') + thumbnail = self._html_search_regex( + r'<input type="hidden" id="hidSnapshot" value="([^"]+)"', + webpage, 'thumbnail', fatal=False) + description = self._html_search_regex( + r'<div id="mstarDeck".*?>(.*?)</div>', + webpage, 'description', fatal=False) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'thumbnail': thumbnail, + 'description': description, + } diff --git a/youtube_dl/extractor/motorsport.py b/youtube_dl/extractor/motorsport.py new file mode 100644 index 000000000..dc727be10 --- /dev/null +++ b/youtube_dl/extractor/motorsport.py @@ -0,0 +1,63 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import hashlib +import json +import re +import time + +from .common import InfoExtractor +from ..utils import ( + compat_parse_qs, + compat_str, + int_or_none, +) + + +class MotorsportIE(InfoExtractor): + IE_DESC = 'motorsport.com' + _VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/(?:$|[?#])' + _TEST = { + 'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/', + 'md5': '5592cb7c5005d9b2c163df5ac3dc04e4', + 'info_dict': { + 'id': '7063', + 'ext': 'mp4', + 'title': 'Red Bull Racing: 2014 Rules Explained', + 'duration': 207, + 'description': 'A new clip from Red Bull sees Daniel Ricciardo and Sebastian Vettel explain the 2014 Formula One regulations – which are arguably the most complex the sport has ever seen.', + 'uploader': 'rainiere', + 'thumbnail': r're:^http://.*motorsport\.com/.+\.jpg$' + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') + + webpage = self._download_webpage(url, display_id) + flashvars_code = self._html_search_regex( + r'<embed id="player".*?flashvars="([^"]+)"', webpage, 'flashvars') + flashvars = compat_parse_qs(flashvars_code) + params = json.loads(flashvars['parameters'][0]) + + e = compat_str(int(time.time()) + 24 * 60 * 60) + base_video_url = params['location'] + '?e=' + e + s = 'h3hg713fh32' + h = hashlib.md5(s + base_video_url).hexdigest() + video_url = base_video_url + '&h=' + h + + uploader = self._html_search_regex( + r'(?s)<span class="label">Video by: </span>(.*?)</a>', webpage, + 'uploader', fatal=False) + + return { + 'id': params['video_id'], + 'display_id': display_id, + 'title': params['title'], + 'url': video_url, + 'description': params.get('description'), + 'thumbnail': params.get('main_thumb'), + 'duration': int_or_none(params.get('duration')), + 'uploader': uploader, + } diff --git a/youtube_dl/extractor/musicplayon.py b/youtube_dl/extractor/musicplayon.py new file mode 100644 index 000000000..42d7a82a5 --- /dev/null +++ b/youtube_dl/extractor/musicplayon.py @@ -0,0 +1,75 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +class MusicPlayOnIE(InfoExtractor): + _VALID_URL = r'https?://(?:.+?\.)?musicplayon\.com/play(?:-touch)?\?(?:v|pl=100&play)=(?P<id>\d+)' + + _TEST = { + 'url': 'http://en.musicplayon.com/play?v=433377', + 'info_dict': { + 'id': '433377', + 'ext': 'mp4', + 'title': 'Rick Ross - Interview On Chelsea Lately (2014)', + 'description': 'Rick Ross Interview On Chelsea Lately', + 'duration': 342, + 'uploader': 'ultrafish', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + page = self._download_webpage(url, video_id) + + title = self._og_search_title(page) + description = self._og_search_description(page) + thumbnail = self._og_search_thumbnail(page) + duration = self._html_search_meta('video:duration', page, 'duration', fatal=False) + view_count = self._og_search_property('count', page, fatal=False) + uploader = self._html_search_regex( + r'<div>by <a href="[^"]+" class="purple">([^<]+)</a></div>', page, 'uploader', fatal=False) + + formats = [ + { + 'url': 'http://media0-eu-nl.musicplayon.com/stream-mobile?id=%s&type=.mp4' % video_id, + 'ext': 'mp4', + } + ] + + manifest = self._download_webpage( + 'http://en.musicplayon.com/manifest.m3u8?v=%s' % video_id, video_id, 'Downloading manifest') + + for entry in manifest.split('#')[1:]: + if entry.startswith('EXT-X-STREAM-INF:'): + meta, url, _ = entry.split('\n') + params = dict(param.split('=') for param in meta.split(',')[1:]) + formats.append({ + 'url': url, + 'ext': 'mp4', + 'tbr': int(params['BANDWIDTH']), + 'width': int(params['RESOLUTION'].split('x')[1]), + 'height': int(params['RESOLUTION'].split('x')[-1]), + 'format_note': params['NAME'].replace('"', '').strip(), + }) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'duration': int_or_none(duration), + 'view_count': int_or_none(view_count), + 'formats': formats, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/nba.py b/youtube_dl/extractor/nba.py index 7e421610e..633b42f72 100644 --- a/youtube_dl/extractor/nba.py +++ b/youtube_dl/extractor/nba.py @@ -6,12 +6,13 @@ from .common import InfoExtractor class NBAIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$' + _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)(?:/index\.html)?(?:\?.*)?$' _TEST = { 'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html', - 'file': u'0021200253-okc-bkn-recap.nba.mp4', 'md5': u'c0edcfc37607344e2ff8f13c378c88a4', 'info_dict': { + 'id': '0021200253-okc-bkn-recap.nba', + 'ext': 'mp4', 'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.', 'title': 'Thunder vs. Nets', }, @@ -19,7 +20,7 @@ class NBAIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) @@ -33,7 +34,6 @@ class NBAIE(InfoExtractor): return { 'id': shortened_video_id, 'url': video_url, - 'ext': 'mp4', 'title': title, 'description': description, } diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py index 46774317c..517a72561 100644 --- a/youtube_dl/extractor/niconico.py +++ b/youtube_dl/extractor/niconico.py @@ -1,12 +1,10 @@ # encoding: utf-8 +from __future__ import unicode_literals import re -import socket from .common import InfoExtractor from ..utils import ( - compat_http_client, - compat_urllib_error, compat_urllib_parse, compat_urllib_request, compat_urlparse, @@ -18,57 +16,54 @@ from ..utils import ( class NiconicoIE(InfoExtractor): - IE_NAME = u'niconico' - IE_DESC = u'ニコニコ動画' + IE_NAME = 'niconico' + IE_DESC = 'ニコニコ動画' _TEST = { - u'url': u'http://www.nicovideo.jp/watch/sm22312215', - u'file': u'sm22312215.mp4', - u'md5': u'd1a75c0823e2f629128c43e1212760f9', - u'info_dict': { - u'title': u'Big Buck Bunny', - u'uploader': u'takuya0301', - u'uploader_id': u'2698420', - u'upload_date': u'20131123', - u'description': u'(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org', + 'url': 'http://www.nicovideo.jp/watch/sm22312215', + 'md5': 'd1a75c0823e2f629128c43e1212760f9', + 'info_dict': { + 'id': 'sm22312215', + 'ext': 'mp4', + 'title': 'Big Buck Bunny', + 'uploader': 'takuya0301', + 'uploader_id': '2698420', + 'upload_date': '20131123', + 'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org', }, - u'params': { - u'username': u'ydl.niconico@gmail.com', - u'password': u'youtube-dl', + 'params': { + 'username': 'ydl.niconico@gmail.com', + 'password': 'youtube-dl', }, } _VALID_URL = r'^https?://(?:www\.|secure\.)?nicovideo\.jp/watch/([a-z][a-z][0-9]+)(?:.*)$' _NETRC_MACHINE = 'niconico' - # If True it will raise an error if no login info is provided - _LOGIN_REQUIRED = True def _real_initialize(self): self._login() def _login(self): (username, password) = self._get_login_info() - # No authentication to be performed if username is None: - if self._LOGIN_REQUIRED: - raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True) - return False + # Login is required + raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) # Log in login_form_strs = { - u'mail': username, - u'password': password, + 'mail': username, + 'password': password, } # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode # chokes on unicode - login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items()) + login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items()) login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8') request = compat_urllib_request.Request( - u'https://secure.nicovideo.jp/secure/login', login_data) + 'https://secure.nicovideo.jp/secure/login', login_data) login_results = self._download_webpage( - request, u'', note=u'Logging in', errnote=u'Unable to log in') + request, None, note='Logging in', errnote='Unable to log in') if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None: - self._downloader.report_warning(u'unable to log in: bad username or password') + self._downloader.report_warning('unable to log in: bad username or password') return False return True @@ -82,12 +77,12 @@ class NiconicoIE(InfoExtractor): video_info = self._download_xml( 'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id, - note=u'Downloading video info page') + note='Downloading video info page') # Get flv info flv_info_webpage = self._download_webpage( - u'http://flapi.nicovideo.jp/api/getflv?v=' + video_id, - video_id, u'Downloading flv info') + 'http://flapi.nicovideo.jp/api/getflv?v=' + video_id, + video_id, 'Downloading flv info') video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0] # Start extracting information @@ -106,22 +101,22 @@ class NiconicoIE(InfoExtractor): url = 'http://seiga.nicovideo.jp/api/user/info?id=' + video_uploader_id try: user_info = self._download_xml( - url, video_id, note=u'Downloading user information') + url, video_id, note='Downloading user information') video_uploader = user_info.find('.//nickname').text - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.report_warning(u'Unable to download user info webpage: %s' % compat_str(err)) + except ExtractorError as err: + self._downloader.report_warning('Unable to download user info webpage: %s' % compat_str(err)) return { - 'id': video_id, - 'url': video_real_url, - 'title': video_title, - 'ext': video_extension, - 'format': video_format, - 'thumbnail': video_thumbnail, + 'id': video_id, + 'url': video_real_url, + 'title': video_title, + 'ext': video_extension, + 'format': video_format, + 'thumbnail': video_thumbnail, 'description': video_description, - 'uploader': video_uploader, + 'uploader': video_uploader, 'upload_date': video_upload_date, 'uploader_id': video_uploader_id, - 'view_count': video_view_count, + 'view_count': video_view_count, 'webpage_url': video_webpage_url, } diff --git a/youtube_dl/extractor/ntv.py b/youtube_dl/extractor/ntv.py new file mode 100644 index 000000000..8447a9b86 --- /dev/null +++ b/youtube_dl/extractor/ntv.py @@ -0,0 +1,157 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + unescapeHTML +) + + +class NTVIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?ntv\.ru/(?P<id>.+)' + + _TESTS = [ + { + 'url': 'http://www.ntv.ru/novosti/863142/', + 'info_dict': { + 'id': '746000', + 'ext': 'flv', + 'title': 'Командующий Черноморским флотом провел переговоры в штабе ВМС Украины', + 'description': 'Командующий Черноморским флотом провел переговоры в штабе ВМС Украины', + 'duration': 136, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.ntv.ru/video/novosti/750370/', + 'info_dict': { + 'id': '750370', + 'ext': 'flv', + 'title': 'Родные пассажиров пропавшего Boeing не верят в трагический исход', + 'description': 'Родные пассажиров пропавшего Boeing не верят в трагический исход', + 'duration': 172, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.ntv.ru/peredacha/segodnya/m23700/o232416', + 'info_dict': { + 'id': '747480', + 'ext': 'flv', + 'title': '«Сегодня». 21 марта 2014 года. 16:00 ', + 'description': '«Сегодня». 21 марта 2014 года. 16:00 ', + 'duration': 1496, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.ntv.ru/kino/Koma_film', + 'info_dict': { + 'id': '750783', + 'ext': 'flv', + 'title': 'Остросюжетный фильм «Кома» 4 апреля вечером на НТВ', + 'description': 'Остросюжетный фильм «Кома» 4 апреля вечером на НТВ', + 'duration': 28, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + { + 'url': 'http://www.ntv.ru/serial/Delo_vrachey/m31760/o233916/', + 'info_dict': { + 'id': '751482', + 'ext': 'flv', + 'title': '«Дело врачей»: «Деревце жизни»', + 'description': '«Дело врачей»: «Деревце жизни»', + 'duration': 2590, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, + ] + + _VIDEO_ID_REGEXES = [ + r'<meta property="og:url" content="http://www\.ntv\.ru/video/(\d+)', + r'<video embed=[^>]+><id>(\d+)</id>', + r'<video restriction[^>]+><key>(\d+)</key>' + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + page = self._download_webpage(url, video_id, 'Downloading page') + + for pattern in self._VIDEO_ID_REGEXES: + mobj = re.search(pattern, page) + if mobj: + break + + if not mobj: + raise ExtractorError('No media links available for %s' % video_id) + + video_id = mobj.group(1) + + player = self._download_xml('http://www.ntv.ru/vi%s/' % video_id, video_id, 'Downloading video XML') + title = unescapeHTML(player.find('./data/title').text) + description = unescapeHTML(player.find('./data/description').text) + + video = player.find('./data/video') + video_id = video.find('./id').text + thumbnail = video.find('./splash').text + duration = int(video.find('./totaltime').text) + view_count = int(video.find('./views').text) + puid22 = video.find('./puid22').text + + apps = { + '4': 'video1', + '7': 'video2', + } + + app = apps[puid22] if puid22 in apps else apps['4'] + + formats = [] + for format_id in ['', 'hi', 'webm']: + file = video.find('./%sfile' % format_id) + if file is None: + continue + size = video.find('./%ssize' % format_id) + formats.append({ + 'url': 'rtmp://media.ntv.ru/%s' % app, + 'app': app, + 'play_path': file.text, + 'rtmp_conn': 'B:1', + 'player_url': 'http://www.ntv.ru/swf/vps1.swf?update=20131128', + 'page_url': 'http://www.ntv.ru', + 'flash_ver': 'LNX 11,2,202,341', + 'rtmp_live': True, + 'ext': 'flv', + 'filesize': int(size.text), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'view_count': view_count, + 'formats': formats, + }
\ No newline at end of file diff --git a/youtube_dl/extractor/oe1.py b/youtube_dl/extractor/oe1.py new file mode 100644 index 000000000..38971ab4d --- /dev/null +++ b/youtube_dl/extractor/oe1.py @@ -0,0 +1,40 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import calendar +import datetime +import re + +from .common import InfoExtractor + +# audios on oe1.orf.at are only available for 7 days, so we can't +# add tests. + + +class OE1IE(InfoExtractor): + IE_DESC = 'oe1.orf.at' + _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + show_id = mobj.group('id') + + data = self._download_json( + 'http://oe1.orf.at/programm/%s/konsole' % show_id, + show_id + ) + + timestamp = datetime.datetime.strptime('%s %s' % ( + data['item']['day_label'], + data['item']['time'] + ), '%d.%m.%Y %H:%M') + unix_timestamp = calendar.timegm(timestamp.utctimetuple()) + + return { + 'id': show_id, + 'title': data['item']['title'], + 'url': data['item']['url_stream'], + 'ext': 'mp3', + 'description': data['item'].get('info'), + 'timestamp': unix_timestamp + } diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py index e20327791..13f12824c 100644 --- a/youtube_dl/extractor/ooyala.py +++ b/youtube_dl/extractor/ooyala.py @@ -7,7 +7,7 @@ from ..utils import unescapeHTML class OoyalaIE(InfoExtractor): - _VALID_URL = r'https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=(?P<id>.+?)(&|$)' + _VALID_URL = r'(?:ooyala:|https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=)(?P<id>.+?)(&|$)' _TEST = { # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index 58f9c690e..718fe9aba 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -1,44 +1,81 @@ from __future__ import unicode_literals import re +import json from .common import InfoExtractor -from ..utils import compat_urllib_parse +from ..utils import int_or_none class PornHdIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)' + _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)' _TEST = { 'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video', - 'file': '1962.flv', - 'md5': '35272469887dca97abd30abecc6cdf75', + 'md5': '956b8ca569f7f4d8ec563e2c41598441', 'info_dict': { - "title": "sierra-day-gets-his-cum-all-over-herself-hd-porn-video", - "age_limit": 18, + 'id': '1962', + 'ext': 'mp4', + 'title': 'Sierra loves doing laundry', + 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294', + 'age_limit': 18, } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('video_id') - video_title = mobj.group('video_title') + video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - next_url = self._html_search_regex( - r'&hd=(http.+?)&', webpage, 'video URL') - next_url = compat_urllib_parse.unquote(next_url) + title = self._og_search_title(webpage) + TITLE_SUFFIX = ' porn HD Video | PornHD.com ' + if title.endswith(TITLE_SUFFIX): + title = title[:-len(TITLE_SUFFIX)] + + description = self._html_search_regex( + r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False) + view_count = int_or_none(self._html_search_regex( + r'(\d+) views </span>', webpage, 'view count', fatal=False)) + + formats = [ + { + 'url': format_url, + 'ext': format.lower(), + 'format_id': '%s-%s' % (format.lower(), quality.lower()), + 'quality': 1 if quality.lower() == 'high' else 0, + } for format, quality, format_url in re.findall( + r'var __video([\da-zA-Z]+?)(Low|High)StreamUrl = \'(http://.+?)\?noProxy=1\'', webpage) + ] + + mobj = re.search(r'flashVars = (?P<flashvars>{.+?});', webpage) + if mobj: + flashvars = json.loads(mobj.group('flashvars')) + formats.extend([ + { + 'url': flashvars['hashlink'].replace('?noProxy=1', ''), + 'ext': 'flv', + 'format_id': 'flv-low', + 'quality': 0, + }, + { + 'url': flashvars['hd'].replace('?noProxy=1', ''), + 'ext': 'flv', + 'format_id': 'flv-high', + 'quality': 1, + } + ]) + thumbnail = flashvars['urlWallpaper'] + else: + thumbnail = self._og_search_thumbnail(webpage) - video_url = self._download_webpage( - next_url, video_id, note='Retrieving video URL', - errnote='Could not retrieve video URL') - age_limit = 18 + self._sort_formats(formats) return { 'id': video_id, - 'url': video_url, - 'ext': 'flv', - 'title': video_title, - 'age_limit': age_limit, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'view_count': view_count, + 'formats': formats, + 'age_limit': 18, } diff --git a/youtube_dl/extractor/pyvideo.py b/youtube_dl/extractor/pyvideo.py index 33054591b..d2d909136 100644 --- a/youtube_dl/extractor/pyvideo.py +++ b/youtube_dl/extractor/pyvideo.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re import os @@ -5,45 +7,50 @@ from .common import InfoExtractor class PyvideoIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)' - _TESTS = [{ - u'url': u'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes', - u'file': u'24_4WWkSmNo.mp4', - u'md5': u'de317418c8bc76b1fd8633e4f32acbc6', - u'info_dict': { - u"title": u"Become a logging expert in 30 minutes", - u"description": u"md5:9665350d466c67fb5b1598de379021f7", - u"upload_date": u"20130320", - u"uploader": u"NextDayVideo", - u"uploader_id": u"NextDayVideo", + _VALID_URL = r'http://(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)' + + _TESTS = [ + { + 'url': 'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes', + 'md5': 'de317418c8bc76b1fd8633e4f32acbc6', + 'info_dict': { + 'id': '24_4WWkSmNo', + 'ext': 'mp4', + 'title': 'Become a logging expert in 30 minutes', + 'description': 'md5:9665350d466c67fb5b1598de379021f7', + 'upload_date': '20130320', + 'uploader': 'NextDayVideo', + 'uploader_id': 'NextDayVideo', + }, + 'add_ie': ['Youtube'], }, - u'add_ie': ['Youtube'], - }, - { - u'url': u'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v', - u'md5': u'5fe1c7e0a8aa5570330784c847ff6d12', - u'info_dict': { - u'id': u'2542', - u'ext': u'm4v', - u'title': u'Gloriajw-SpotifyWithErikBernhardsson182', + { + 'url': 'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v', + 'md5': '5fe1c7e0a8aa5570330784c847ff6d12', + 'info_dict': { + 'id': '2542', + 'ext': 'm4v', + 'title': 'Gloriajw-SpotifyWithErikBernhardsson182', + }, }, - }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) - m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage) + m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage) if m_youtube is not None: return self.url_result(m_youtube.group(1), 'Youtube') - title = self._html_search_regex(r'<div class="section">.*?<h3>([^>]+?)</h3>', - webpage, u'title', flags=re.DOTALL) - video_url = self._search_regex([r'<source src="(.*?)"', - r'<dt>Download</dt>.*?<a href="(.+?)"'], - webpage, u'video url', flags=re.DOTALL) + title = self._html_search_regex( + r'<div class="section">.*?<h3>([^>]+?)</h3>', webpage, 'title', flags=re.DOTALL) + video_url = self._search_regex( + [r'<source src="(.*?)"', r'<dt>Download</dt>.*?<a href="(.+?)"'], + webpage, 'video url', flags=re.DOTALL) + return { 'id': video_id, 'title': os.path.splitext(title)[0], diff --git a/youtube_dl/extractor/radiofrance.py b/youtube_dl/extractor/radiofrance.py index 34652f6c1..09352ed82 100644 --- a/youtube_dl/extractor/radiofrance.py +++ b/youtube_dl/extractor/radiofrance.py @@ -1,4 +1,6 @@ # coding: utf-8 +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -6,16 +8,17 @@ from .common import InfoExtractor class RadioFranceIE(InfoExtractor): _VALID_URL = r'^https?://maison\.radiofrance\.fr/radiovisions/(?P<id>[^?#]+)' - IE_NAME = u'radiofrance' + IE_NAME = 'radiofrance' _TEST = { - u'url': u'http://maison.radiofrance.fr/radiovisions/one-one', - u'file': u'one-one.ogg', - u'md5': u'bdbb28ace95ed0e04faab32ba3160daf', - u'info_dict': { - u"title": u"One to one", - u"description": u"Plutôt que d'imaginer la radio de demain comme technologie ou comme création de contenu, je veux montrer que quelles que soient ses évolutions, j'ai l'intime conviction que la radio continuera d'être un grand média de proximité pour les auditeurs.", - u"uploader": u"Thomas Hercouët", + 'url': 'http://maison.radiofrance.fr/radiovisions/one-one', + 'md5': 'bdbb28ace95ed0e04faab32ba3160daf', + 'info_dict': { + 'id': 'one-one', + 'ext': 'ogg', + "title": "One to one", + "description": "Plutôt que d'imaginer la radio de demain comme technologie ou comme création de contenu, je veux montrer que quelles que soient ses évolutions, j'ai l'intime conviction que la radio continuera d'être un grand média de proximité pour les auditeurs.", + "uploader": "Thomas Hercouët", }, } @@ -24,27 +27,28 @@ class RadioFranceIE(InfoExtractor): video_id = m.group('id') webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, u'title') + title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title') description = self._html_search_regex( r'<div class="bloc_page_wrapper"><div class="text">(.*?)</div>', - webpage, u'description', fatal=False) + webpage, 'description', fatal=False) uploader = self._html_search_regex( r'<div class="credit"> © (.*?)</div>', - webpage, u'uploader', fatal=False) + webpage, 'uploader', fatal=False) formats_str = self._html_search_regex( r'class="jp-jplayer[^"]*" data-source="([^"]+)">', - webpage, u'audio URLs') + webpage, 'audio URLs') formats = [ { 'format_id': fm[0], 'url': fm[1], 'vcodec': 'none', + 'preference': i, } - for fm in - re.findall(r"([a-z0-9]+)\s*:\s*'([^']+)'", formats_str) + for i, fm in + enumerate(re.findall(r"([a-z0-9]+)\s*:\s*'([^']+)'", formats_str)) ] - # No sorting, we don't know any more about these formats + self._sort_formats(formats) return { 'id': video_id, diff --git a/youtube_dl/extractor/roxwel.py b/youtube_dl/extractor/roxwel.py index d339e6cb5..41638c1d0 100644 --- a/youtube_dl/extractor/roxwel.py +++ b/youtube_dl/extractor/roxwel.py @@ -1,5 +1,6 @@ +from __future__ import unicode_literals + import re -import json from .common import InfoExtractor from ..utils import unified_strdate, determine_ext @@ -9,41 +10,44 @@ class RoxwelIE(InfoExtractor): _VALID_URL = r'https?://www\.roxwel\.com/player/(?P<filename>.+?)(\.|\?|$)' _TEST = { - u'url': u'http://www.roxwel.com/player/passionpittakeawalklive.html', - u'file': u'passionpittakeawalklive.flv', - u'md5': u'd9dea8360a1e7d485d2206db7fe13035', - u'info_dict': { - u'title': u'Take A Walk (live)', - u'uploader': u'Passion Pit', - u'description': u'Passion Pit performs "Take A Walk\" live at The Backyard in Austin, Texas. ', + 'url': 'http://www.roxwel.com/player/passionpittakeawalklive.html', + 'info_dict': { + 'id': 'passionpittakeawalklive', + 'ext': 'flv', + 'title': 'Take A Walk (live)', + 'uploader': 'Passion Pit', + 'uploader_id': 'passionpit', + 'upload_date': '20120928', + 'description': 'Passion Pit performs "Take A Walk\" live at The Backyard in Austin, Texas. ', }, - u'skip': u'Requires rtmpdump', + 'params': { + # rtmp download + 'skip_download': True, + } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) filename = mobj.group('filename') info_url = 'http://www.roxwel.com/api/videos/%s' % filename - info_page = self._download_webpage(info_url, filename, - u'Downloading video info') + info = self._download_json(info_url, filename) - self.report_extraction(filename) - info = json.loads(info_page) rtmp_rates = sorted([int(r.replace('flv_', '')) for r in info['media_rates'] if r.startswith('flv_')]) best_rate = rtmp_rates[-1] url_page_url = 'http://roxwel.com/pl_one_time.php?filename=%s&quality=%s' % (filename, best_rate) - rtmp_url = self._download_webpage(url_page_url, filename, u'Downloading video url') + rtmp_url = self._download_webpage(url_page_url, filename, 'Downloading video url') ext = determine_ext(rtmp_url) if ext == 'f4v': rtmp_url = rtmp_url.replace(filename, 'mp4:%s' % filename) - return {'id': filename, - 'title': info['title'], - 'url': rtmp_url, - 'ext': 'flv', - 'description': info['description'], - 'thumbnail': info.get('player_image_url') or info.get('image_url_large'), - 'uploader': info['artist'], - 'uploader_id': info['artistname'], - 'upload_date': unified_strdate(info['dbdate']), - } + return { + 'id': filename, + 'title': info['title'], + 'url': rtmp_url, + 'ext': 'flv', + 'description': info['description'], + 'thumbnail': info.get('player_image_url') or info.get('image_url_large'), + 'uploader': info['artist'], + 'uploader_id': info['artistname'], + 'upload_date': unified_strdate(info['dbdate']), + } diff --git a/youtube_dl/extractor/rts.py b/youtube_dl/extractor/rts.py new file mode 100644 index 000000000..40224d761 --- /dev/null +++ b/youtube_dl/extractor/rts.py @@ -0,0 +1,151 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_duration, + parse_iso8601, + unescapeHTML, + compat_str, +) + + +class RTSIE(InfoExtractor): + IE_DESC = 'RTS.ch' + _VALID_URL = r'^https?://(?:www\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-.*?\.html' + + _TESTS = [ + { + 'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html', + 'md5': '753b877968ad8afaeddccc374d4256a5', + 'info_dict': { + 'id': '3449373', + 'ext': 'mp4', + 'duration': 1488, + 'title': 'Les Enfants Terribles', + 'description': 'France Pommier et sa soeur Luce Feral, les deux filles de ce groupe de 5.', + 'uploader': 'Divers', + 'upload_date': '19680921', + 'timestamp': -40280400, + 'thumbnail': 're:^https?://.*\.image' + }, + }, + { + 'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html', + 'md5': 'c197f0b2421995c63a64cc73d800f42e', + 'info_dict': { + 'id': '5738317', + 'ext': 'mp4', + 'duration': 55, + 'title': 'Bande de lancement de Passe-moi les jumelles', + 'description': '', + 'uploader': 'Passe-moi les jumelles', + 'upload_date': '20140404', + 'timestamp': 1396635300, + 'thumbnail': 're:^https?://.*\.image' + }, + }, + { + 'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html', + 'md5': 'b4326fecd3eb64a458ba73c73e91299d', + 'info_dict': { + 'id': '5745975', + 'ext': 'mp4', + 'duration': 48, + 'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski', + 'description': 'Hockey - Playoff', + 'uploader': 'Hockey', + 'upload_date': '20140403', + 'timestamp': 1396556882, + 'thumbnail': 're:^https?://.*\.image' + }, + 'skip': 'Blocked outside Switzerland', + }, + { + 'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html', + 'md5': '9bb06503773c07ce83d3cbd793cebb91', + 'info_dict': { + 'id': '5745356', + 'ext': 'mp4', + 'duration': 33, + 'title': 'Londres cachée par un épais smog', + 'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.', + 'uploader': 'Le Journal en continu', + 'upload_date': '20140403', + 'timestamp': 1396537322, + 'thumbnail': 're:^https?://.*\.image' + }, + }, + { + 'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html', + 'md5': 'dd8ef6a22dff163d063e2a52bc8adcae', + 'info_dict': { + 'id': '5706148', + 'ext': 'mp3', + 'duration': 123, + 'title': '"Urban Hippie", de Damien Krisl', + 'description': 'Des Hippies super glam.', + 'upload_date': '20140403', + 'timestamp': 1396551600, + }, + }, + ] + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('id') + + def download_json(video_id): + return self._download_json( + 'http://www.rts.ch/a/%s.html?f=json/article' % video_id, video_id) + + all_info = download_json(video_id) + + # video_id extracted out of URL is not always a real id + if 'video' not in all_info and 'audio' not in all_info: + page = self._download_webpage(url, video_id) + video_id = self._html_search_regex(r'<(?:video|audio) data-id="(\d+)"', page, 'video id') + all_info = download_json(video_id) + + info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio'] + + upload_timestamp = parse_iso8601(info.get('broadcast_date')) + duration = info.get('duration') or info.get('cutout') or info.get('cutduration') + if isinstance(duration, compat_str): + duration = parse_duration(duration) + view_count = info.get('plays') + thumbnail = unescapeHTML(info.get('preview_image_url')) + + def extract_bitrate(url): + return int_or_none(self._search_regex( + r'-([0-9]+)k\.', url, 'bitrate', default=None)) + + formats = [{ + 'format_id': fid, + 'url': furl, + 'tbr': extract_bitrate(furl), + } for fid, furl in info['streams'].items()] + + if 'media' in info: + formats.extend([{ + 'format_id': '%s-%sk' % (media['ext'], media['rate']), + 'url': 'http://download-video.rts.ch/%s' % media['url'], + 'tbr': media['rate'] or extract_bitrate(media['url']), + } for media in info['media'] if media.get('rate')]) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'formats': formats, + 'title': info['title'], + 'description': info.get('intro'), + 'duration': duration, + 'view_count': view_count, + 'uploader': info.get('programName'), + 'timestamp': upload_timestamp, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 4922dd764..f1ce66433 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import re -import json import itertools from .common import InfoExtractor @@ -20,8 +19,9 @@ class RutubeIE(InfoExtractor): _TEST = { 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/', - 'file': '3eac3b4561676c17df9132a9a1e62e3e.mp4', 'info_dict': { + 'id': '3eac3b4561676c17df9132a9a1e62e3e', + 'ext': 'mp4', 'title': 'Раненный кенгуру забежал в аптеку', 'description': 'http://www.ntdtv.ru ', 'duration': 80, @@ -38,15 +38,15 @@ class RutubeIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - - api_response = self._download_webpage('http://rutube.ru/api/video/%s/?format=json' % video_id, - video_id, 'Downloading video JSON') - video = json.loads(api_response) - - api_response = self._download_webpage('http://rutube.ru/api/play/trackinfo/%s/?format=json' % video_id, - video_id, 'Downloading trackinfo JSON') - trackinfo = json.loads(api_response) - + + video = self._download_json( + 'http://rutube.ru/api/video/%s/?format=json' % video_id, + video_id, 'Downloading video JSON') + + trackinfo = self._download_json( + 'http://rutube.ru/api/play/trackinfo/%s/?format=json' % video_id, + video_id, 'Downloading trackinfo JSON') + # Some videos don't have the author field author = trackinfo.get('author') or {} m3u8_url = trackinfo['video_balancer'].get('m3u8') @@ -79,10 +79,9 @@ class RutubeChannelIE(InfoExtractor): def _extract_videos(self, channel_id, channel_title=None): entries = [] for pagenum in itertools.count(1): - api_response = self._download_webpage( + page = self._download_json( self._PAGE_TEMPLATE % (channel_id, pagenum), channel_id, 'Downloading page %s' % pagenum) - page = json.loads(api_response) results = page['results'] if not results: break @@ -108,10 +107,9 @@ class RutubeMovieIE(RutubeChannelIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) movie_id = mobj.group('id') - api_response = self._download_webpage( + movie = self._download_json( self._MOVIE_TEMPLATE % movie_id, movie_id, 'Downloading movie JSON') - movie = json.loads(api_response) movie_name = movie['name'] return self._extract_videos(movie_id, movie_name) diff --git a/youtube_dl/extractor/slashdot.py b/youtube_dl/extractor/slashdot.py deleted file mode 100644 index d68646d24..000000000 --- a/youtube_dl/extractor/slashdot.py +++ /dev/null @@ -1,24 +0,0 @@ -import re - -from .common import InfoExtractor - - -class SlashdotIE(InfoExtractor): - _VALID_URL = r'https?://tv\.slashdot\.org/video/\?embed=(?P<id>.*?)(&|$)' - - _TEST = { - u'add_ie': ['Ooyala'], - 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'<script src="(.*?)"', webpage, 'ooyala url') - return self.url_result(ooyala_url, 'Ooyala') diff --git a/youtube_dl/extractor/smotri.py b/youtube_dl/extractor/smotri.py index 540c55703..13e7e71cb 100644 --- a/youtube_dl/extractor/smotri.py +++ b/youtube_dl/extractor/smotri.py @@ -13,22 +13,24 @@ from ..utils import ( compat_urllib_request, ExtractorError, url_basename, + int_or_none, ) class SmotriIE(InfoExtractor): IE_DESC = 'Smotri.com' IE_NAME = 'smotri' - _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/video/view/\?id=(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4}))' + _VALID_URL = r'^https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})' _NETRC_MACHINE = 'smotri' _TESTS = [ # real video id 2610366 { 'url': 'http://smotri.com/video/view/?id=v261036632ab', - 'file': 'v261036632ab.mp4', 'md5': '2a7b08249e6f5636557579c368040eb9', 'info_dict': { + 'id': 'v261036632ab', + 'ext': 'mp4', 'title': 'катастрофа с камер видеонаблюдения', 'uploader': 'rbc2008', 'uploader_id': 'rbc08', @@ -40,9 +42,10 @@ class SmotriIE(InfoExtractor): # real video id 57591 { 'url': 'http://smotri.com/video/view/?id=v57591cb20', - 'file': 'v57591cb20.flv', 'md5': '830266dfc21f077eac5afd1883091bcd', 'info_dict': { + 'id': 'v57591cb20', + 'ext': 'flv', 'title': 'test', 'uploader': 'Support Photofile@photofile', 'uploader_id': 'support-photofile', @@ -54,9 +57,10 @@ class SmotriIE(InfoExtractor): # video-password { 'url': 'http://smotri.com/video/view/?id=v1390466a13c', - 'file': 'v1390466a13c.mp4', 'md5': 'f6331cef33cad65a0815ee482a54440b', 'info_dict': { + 'id': 'v1390466a13c', + 'ext': 'mp4', 'title': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1', 'uploader': 'timoxa40', 'uploader_id': 'timoxa40', @@ -71,9 +75,10 @@ class SmotriIE(InfoExtractor): # age limit + video-password { 'url': 'http://smotri.com/video/view/?id=v15408898bcf', - 'file': 'v15408898bcf.flv', 'md5': '91e909c9f0521adf5ee86fbe073aad70', 'info_dict': { + 'id': 'v15408898bcf', + 'ext': 'flv', 'title': 'этот ролик не покажут по ТВ', 'uploader': 'zzxxx', 'uploader_id': 'ueggb', @@ -85,7 +90,22 @@ class SmotriIE(InfoExtractor): 'params': { 'videopassword': '333' } - } + }, + # swf player + { + 'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500', + 'md5': '4d47034979d9390d14acdf59c4935bc2', + 'info_dict': { + 'id': 'v9188090500', + 'ext': 'mp4', + 'title': 'Shakira - Don\'t Bother', + 'uploader': 'HannahL', + 'uploader_id': 'lisaha95', + 'upload_date': '20090331', + 'description': 'Shakira - Don\'t Bother, видео Shakira - Don\'t Bother', + 'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg', + }, + }, ] _SUCCESS = 0 @@ -93,6 +113,21 @@ class SmotriIE(InfoExtractor): _PASSWORD_DETECTED = 2 _VIDEO_NOT_FOUND = 3 + @classmethod + def _extract_url(cls, webpage): + mobj = re.search( + r'<embed[^>]src=(["\'])(?P<url>http://pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=v.+?\1)', + webpage) + if mobj is not None: + return mobj.group('url') + + mobj = re.search( + r'''(?x)<div\s+class="video_file">http://smotri\.com/video/download/file/[^<]+</div>\s* + <div\s+class="video_image">[^<]+</div>\s* + <div\s+class="video_id">(?P<id>[^<]+)</div>''', webpage) + if mobj is not None: + return 'http://smotri.com/video/view/?id=%s' % mobj.group('id') + def _search_meta(self, name, html, display_name=None): if display_name is None: display_name = name @@ -134,7 +169,7 @@ class SmotriIE(InfoExtractor): # Video JSON does not provide enough meta data # We will extract some from the video web page instead - video_page_url = 'http://' + mobj.group('url') + video_page_url = 'http://smotri.com/video/view/?id=%s' % video_id video_page = self._download_webpage(video_page_url, video_id, 'Downloading video page') # Warning if video is unavailable @@ -222,7 +257,7 @@ class SmotriIE(InfoExtractor): 'upload_date': video_upload_date, 'uploader_id': video_uploader_id, 'duration': video_duration, - 'view_count': video_view_count, + 'view_count': int_or_none(video_view_count), 'age_limit': 18 if adult_content else 0, 'video_page_url': video_page_url } diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 2f254f023..8893699aa 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -100,7 +100,7 @@ class SoundcloudIE(InfoExtractor): def report_resolve(self, video_id): """Report information extraction.""" - self.to_screen(u'%s: Resolving id' % video_id) + self.to_screen('%s: Resolving id' % video_id) @classmethod def _resolv_url(cls, url): @@ -124,45 +124,46 @@ class SoundcloudIE(InfoExtractor): 'description': info['description'], 'thumbnail': thumbnail, } + formats = [] if info.get('downloadable', False): # We can build a direct link to the song format_url = ( 'https://api.soundcloud.com/tracks/{0}/download?client_id={1}'.format( track_id, self._CLIENT_ID)) - result['formats'] = [{ + formats.append({ 'format_id': 'download', 'ext': info.get('original_format', 'mp3'), 'url': format_url, 'vcodec': 'none', - }] - else: - # We have to retrieve the url - streams_url = ('http://api.soundcloud.com/i1/tracks/{0}/streams?' - 'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token)) - stream_json = self._download_webpage( - streams_url, - track_id, 'Downloading track url') - - formats = [] - format_dict = json.loads(stream_json) - for key, stream_url in format_dict.items(): - if key.startswith(u'http'): - formats.append({ - 'format_id': key, - 'ext': ext, - 'url': stream_url, - 'vcodec': 'none', - }) - elif key.startswith(u'rtmp'): - # The url doesn't have an rtmp app, we have to extract the playpath - url, path = stream_url.split('mp3:', 1) - formats.append({ - 'format_id': key, - 'url': url, - 'play_path': 'mp3:' + path, - 'ext': ext, - 'vcodec': 'none', - }) + 'preference': 10, + }) + + # We have to retrieve the url + streams_url = ('http://api.soundcloud.com/i1/tracks/{0}/streams?' + 'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token)) + stream_json = self._download_webpage( + streams_url, + track_id, 'Downloading track url') + + format_dict = json.loads(stream_json) + for key, stream_url in format_dict.items(): + if key.startswith('http'): + formats.append({ + 'format_id': key, + 'ext': ext, + 'url': stream_url, + 'vcodec': 'none', + }) + elif key.startswith('rtmp'): + # The url doesn't have an rtmp app, we have to extract the playpath + url, path = stream_url.split('mp3:', 1) + formats.append({ + 'format_id': key, + 'url': url, + 'play_path': 'mp3:' + path, + 'ext': ext, + 'vcodec': 'none', + }) if not formats: # We fallback to the stream_url in the original info, this @@ -188,7 +189,7 @@ class SoundcloudIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE) if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) + raise ExtractorError('Invalid URL: %s' % url) track_id = mobj.group('track_id') token = None @@ -226,7 +227,7 @@ class SoundcloudSetIE(SoundcloudIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) + raise ExtractorError('Invalid URL: %s' % url) # extract uploader (which is in the url) uploader = mobj.group(1) @@ -243,7 +244,7 @@ class SoundcloudSetIE(SoundcloudIE): info = json.loads(info_json) if 'errors' in info: for err in info['errors']: - self._downloader.report_error(u'unable to download video webpage: %s' % compat_str(err['error_message'])) + self._downloader.report_error('unable to download video webpage: %s' % compat_str(err['error_message'])) return self.report_extraction(full_title) diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index ad1a46c33..a8d8e8b29 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -18,12 +18,14 @@ class TEDIE(SubtitlesInfoExtractor): (?P<type_playlist>playlists(?:/\d+)?) # We have a playlist | ((?P<type_talk>talks)) # We have a simple talk + | + (?P<type_watch>watch)/[^/]+/[^/]+ ) (/lang/(.*?))? # The url may contain the language - /(?P<name>\w+) # Here goes the name and then ".html" + /(?P<name>[\w-]+) # Here goes the name and then ".html" .*)$ ''' - _TEST = { + _TESTS = [{ 'url': 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html', 'md5': '4ea1dada91e4174b53dac2bb8ace429d', 'info_dict': { @@ -36,7 +38,17 @@ class TEDIE(SubtitlesInfoExtractor): 'actively fooling us.'), 'uploader': 'Dan Dennett', } - } + }, { + 'url': 'http://www.ted.com/watch/ted-institute/ted-bcg/vishal-sikka-the-beauty-and-power-of-algorithms', + 'md5': '226f4fb9c62380d11b7995efa4c87994', + 'info_dict': { + 'id': 'vishal-sikka-the-beauty-and-power-of-algorithms', + 'ext': 'mp4', + 'title': 'Vishal Sikka: The beauty and power of algorithms', + 'thumbnail': 're:^https?://.+\.jpg', + 'description': 'Adaptive, intelligent, and consistent, algorithms are emerging as the ultimate app for everything from matching consumers to products to assessing medical diagnoses. Vishal Sikka shares his appreciation for the algorithm, charting both its inherent beauty and its growing power.', + } + }] _FORMATS_PREFERENCE = { 'low': 1, @@ -57,6 +69,8 @@ class TEDIE(SubtitlesInfoExtractor): name = m.group('name') if m.group('type_talk'): return self._talk_info(url, name) + elif m.group('type_watch'): + return self._watch_info(url, name) else: return self._playlist_videos_info(url, name) @@ -123,3 +137,26 @@ class TEDIE(SubtitlesInfoExtractor): else: self._downloader.report_warning(u'video doesn\'t have subtitles') return {} + + def _watch_info(self, url, name): + webpage = self._download_webpage(url, name) + + config_json = self._html_search_regex( + r"data-config='([^']+)", webpage, 'config') + config = json.loads(config_json) + video_url = config['video']['url'] + thumbnail = config.get('image', {}).get('url') + + title = self._html_search_regex( + r"(?s)<h1(?:\s+class='[^']+')?>(.+?)</h1>", webpage, 'title') + description = self._html_search_regex( + r'(?s)<h4 class="[^"]+" id="h3--about-this-talk">.*?</h4>(.*?)</div>', + webpage, 'description', fatal=False) + + return { + 'id': name, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'description': description, + } diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py index 2c5c88be8..fdae17b1b 100644 --- a/youtube_dl/extractor/tf1.py +++ b/youtube_dl/extractor/tf1.py @@ -1,33 +1,37 @@ # coding: utf-8 +from __future__ import unicode_literals -import json import re from .common import InfoExtractor + class TF1IE(InfoExtractor): """TF1 uses the wat.tv player.""" - _VALID_URL = r'http://videos\.tf1\.fr/.*-(.*?)\.html' + _VALID_URL = r'http://videos\.tf1\.fr/.*-(?P<id>.*?)\.html' _TEST = { - u'url': u'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html', - u'file': u'10635995.mp4', - u'md5': u'2e378cc28b9957607d5e88f274e637d8', - u'info_dict': { - u'title': u'Citroën Grand C4 Picasso 2013 : présentation officielle', - u'description': u'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.', + 'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html', + 'info_dict': { + 'id': '10635995', + 'ext': 'mp4', + 'title': 'Citroën Grand C4 Picasso 2013 : présentation officielle', + 'description': 'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.', + }, + 'params': { + # Sometimes wat serves the whole file with the --test option + 'skip_download': True, }, - u'skip': u'Sometimes wat serves the whole file with the --test option', } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - id = mobj.group(1) - webpage = self._download_webpage(url, id) - embed_url = self._html_search_regex(r'"(https://www.wat.tv/embedframe/.*?)"', - webpage, 'embed url') - embed_page = self._download_webpage(embed_url, id, u'Downloading embed player page') + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + embed_url = self._html_search_regex( + r'"(https://www.wat.tv/embedframe/.*?)"', webpage, 'embed url') + embed_page = self._download_webpage(embed_url, video_id, + 'Downloading embed player page') wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id') - wat_info = self._download_webpage('http://www.wat.tv/interface/contentv3/%s' % wat_id, id, u'Downloading Wat info') - wat_info = json.loads(wat_info)['media'] - wat_url = wat_info['url'] - return self.url_result(wat_url, 'Wat') + wat_info = self._download_json( + 'http://www.wat.tv/interface/contentv3/%s' % wat_id, video_id) + return self.url_result(wat_info['media']['url'], 'Wat') diff --git a/youtube_dl/extractor/urort.py b/youtube_dl/extractor/urort.py new file mode 100644 index 000000000..5d06fcc9e --- /dev/null +++ b/youtube_dl/extractor/urort.py @@ -0,0 +1,61 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + unified_strdate, +) + + +class UrortIE(InfoExtractor): + IE_DESC = 'NRK P3 Urørt' + _VALID_URL = r'https?://(?:www\.)?urort\.p3\.no/#!/Band/(?P<id>[^/]+)$' + + _TEST = { + 'url': 'https://urort.p3.no/#!/Band/Gerilja', + 'md5': '5ed31a924be8a05e47812678a86e127b', + 'info_dict': { + 'id': '33124-4', + 'ext': 'mp3', + 'title': 'The Bomb', + 'thumbnail': 're:^https?://.+\.jpg', + 'like_count': int, + 'uploader': 'Gerilja', + 'uploader_id': 'Gerilja', + 'upload_date': '20100323', + }, + 'params': { + 'matchtitle': '^The Bomb$', # To test, we want just one video + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + playlist_id = mobj.group('id') + + fstr = compat_urllib_parse.quote("InternalBandUrl eq '%s'" % playlist_id) + json_url = 'http://urort.p3.no/breeze/urort/TrackDtos?$filter=' + fstr + songs = self._download_json(json_url, playlist_id) + print(songs[0]) + + entries = [{ + 'id': '%d-%s' % (s['BandId'], s['$id']), + 'title': s['Title'], + 'url': s['TrackUrl'], + 'ext': 'mp3', + 'uploader_id': playlist_id, + 'uploader': s.get('BandName', playlist_id), + 'like_count': s.get('LikeCount'), + 'thumbnail': 'http://urort.p3.no/cloud/images/%s' % s['Image'], + 'upload_date': unified_strdate(s.get('Released')), + } for s in songs] + + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': playlist_id, + 'entries': entries, + } diff --git a/youtube_dl/extractor/veoh.py b/youtube_dl/extractor/veoh.py index c90feefd2..d16993daf 100644 --- a/youtube_dl/extractor/veoh.py +++ b/youtube_dl/extractor/veoh.py @@ -4,26 +4,99 @@ import re import json from .common import InfoExtractor -from ..utils import compat_urllib_request +from ..utils import ( + compat_urllib_request, + int_or_none, +) class VeohIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?veoh\.com/(?:watch|iphone/#_Watch)/v(?P<id>\d*)' - - _TEST = { - 'url': 'http://www.veoh.com/watch/v56314296nk7Zdmz3', - 'file': '56314296.mp4', - 'md5': '620e68e6a3cff80086df3348426c9ca3', - 'info_dict': { - 'title': 'Straight Backs Are Stronger', - 'uploader': 'LUMOback', - 'description': 'At LUMOback, we believe straight backs are stronger. The LUMOback Posture & Movement Sensor: It gently vibrates when you slouch, inspiring improved posture and mobility. Use the app to track your data and improve your posture over time. ', + _VALID_URL = r'http://(?:www\.)?veoh\.com/(?:watch|iphone/#_Watch)/(?P<id>(?:v|yapi-)[\da-zA-Z]+)' + + _TESTS = [ + { + 'url': 'http://www.veoh.com/watch/v56314296nk7Zdmz3', + 'md5': '620e68e6a3cff80086df3348426c9ca3', + 'info_dict': { + 'id': '56314296', + 'ext': 'mp4', + 'title': 'Straight Backs Are Stronger', + 'uploader': 'LUMOback', + 'description': 'At LUMOback, we believe straight backs are stronger. The LUMOback Posture & Movement Sensor: It gently vibrates when you slouch, inspiring improved posture and mobility. Use the app to track your data and improve your posture over time. ', + }, + }, + { + 'url': 'http://www.veoh.com/watch/v27701988pbTc4wzN?h1=Chile+workers+cover+up+to+avoid+skin+damage', + 'md5': '4a6ff84b87d536a6a71e6aa6c0ad07fa', + 'info_dict': { + 'id': '27701988', + 'ext': 'mp4', + 'title': 'Chile workers cover up to avoid skin damage', + 'description': 'md5:2bd151625a60a32822873efc246ba20d', + 'uploader': 'afp-news', + 'duration': 123, + }, + }, + { + 'url': 'http://www.veoh.com/watch/v69525809F6Nc4frX', + 'md5': '4fde7b9e33577bab2f2f8f260e30e979', + 'note': 'Embedded ooyala video', + 'info_dict': { + 'id': '69525809', + 'ext': 'mp4', + 'title': 'Doctors Alter Plan For Preteen\'s Weight Loss Surgery', + 'description': 'md5:f5a11c51f8fb51d2315bca0937526891', + 'uploader': 'newsy-videos', + }, + }, + ] + + def _extract_formats(self, source): + formats = [] + link = source.get('aowPermalink') + if link: + formats.append({ + 'url': link, + 'ext': 'mp4', + 'format_id': 'aow', + }) + link = source.get('fullPreviewHashLowPath') + if link: + formats.append({ + 'url': link, + 'format_id': 'low', + }) + link = source.get('fullPreviewHashHighPath') + if link: + formats.append({ + 'url': link, + 'format_id': 'high', + }) + return formats + + def _extract_video(self, source): + return { + 'id': source.get('videoId'), + 'title': source.get('title'), + 'description': source.get('description'), + 'thumbnail': source.get('highResImage') or source.get('medResImage'), + 'uploader': source.get('username'), + 'duration': int_or_none(source.get('length')), + 'view_count': int_or_none(source.get('views')), + 'age_limit': 18 if source.get('isMature') == 'true' or source.get('isSexy') == 'true' else 0, + 'formats': self._extract_formats(source), } - } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + + if video_id.startswith('v'): + rsp = self._download_xml( + r'http://www.veoh.com/api/findByPermalink?permalink=%s' % video_id, video_id, 'Downloading video XML') + if rsp.get('stat') == 'ok': + return self._extract_video(rsp.find('./videoList/video')) + webpage = self._download_webpage(url, video_id) age_limit = 0 if 'class="adultwarning-container"' in webpage: @@ -33,24 +106,16 @@ class VeohIE(InfoExtractor): request.add_header('Cookie', 'confirmedAdult=true') webpage = self._download_webpage(request, video_id) - m_youtube = re.search(r'http://www\.youtube\.com/v/(.*?)(\&|")', webpage) + m_youtube = re.search(r'http://www\.youtube\.com/v/(.*?)(\&|"|\?)', webpage) if m_youtube is not None: youtube_id = m_youtube.group(1) self.to_screen('%s: detected Youtube video.' % video_id) return self.url_result(youtube_id, 'Youtube') - self.report_extraction(video_id) - info = self._search_regex(r'videoDetailsJSON = \'({.*?})\';', webpage, 'info') - info = json.loads(info) - video_url = info.get('fullPreviewHashHighPath') or info.get('fullPreviewHashLowPath') + info = json.loads( + self._search_regex(r'videoDetailsJSON = \'({.*?})\';', webpage, 'info').replace('\\\'', '\'')) - return { - 'id': info['videoId'], - 'title': info['title'], - 'url': video_url, - 'uploader': info['username'], - 'thumbnail': info.get('highResImage') or info.get('medResImage'), - 'description': info['description'], - 'view_count': info['views'], - 'age_limit': age_limit, - } + video = self._extract_video(info) + video['age_limit'] = age_limit + + return video diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py deleted file mode 100644 index 87812d6af..000000000 --- a/youtube_dl/extractor/vice.py +++ /dev/null @@ -1,38 +0,0 @@ -import re - -from .common import InfoExtractor -from .ooyala import OoyalaIE -from ..utils import ExtractorError - - -class ViceIE(InfoExtractor): - _VALID_URL = r'http://www\.vice\.com/.*?/(?P<name>.+)' - - _TEST = { - u'url': u'http://www.vice.com/Fringes/cowboy-capitalists-part-1', - u'file': u'43cW1mYzpia9IlestBjVpd23Yu3afAfp.mp4', - u'info_dict': { - u'title': u'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov', - }, - u'params': { - # Requires ffmpeg (m3u8 manifest) - u'skip_download': True, - }, - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - name = mobj.group('name') - webpage = self._download_webpage(url, name) - try: - ooyala_url = self._og_search_video_url(webpage) - except ExtractorError: - try: - embed_code = self._search_regex( - r'OO.Player.create\(\'ooyalaplayer\', \'(.+?)\'', webpage, - u'ooyala embed code') - ooyala_url = OoyalaIE._url_for_embed_code(embed_code) - except ExtractorError: - raise ExtractorError(u'The page doesn\'t contain a video', expected=True) - return self.url_result(ooyala_url, ie='Ooyala') - diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 3b3bec92f..8b1432fec 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -16,7 +16,7 @@ from ..utils import ( class VKIE(InfoExtractor): IE_NAME = 'vk.com' - _VALID_URL = r'https?://vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>\d+).*?\bid=(?P<id>\d+)|(?:videos.*?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))' + _VALID_URL = r'https?://vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:videos.*?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))' _NETRC_MACHINE = 'vk' _TESTS = [ diff --git a/youtube_dl/extractor/washingtonpost.py b/youtube_dl/extractor/washingtonpost.py new file mode 100644 index 000000000..cb8f0887d --- /dev/null +++ b/youtube_dl/extractor/washingtonpost.py @@ -0,0 +1,103 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + strip_jsonp, +) + + +class WashingtonPostIE(InfoExtractor): + _VALID_URL = r'^https?://(?:www\.)?washingtonpost\.com/.*?/(?P<id>[^/]+)/(?:$|[?#])' + _TEST = { + 'url': 'http://www.washingtonpost.com/sf/national/2014/03/22/sinkhole-of-bureaucracy/', + 'playlist': [{ + 'md5': 'c3f4b4922ffa259243f68e928db2db8c', + 'info_dict': { + 'id': 'fc433c38-b146-11e3-b8b3-44b1d1cd4c1f', + 'ext': 'mp4', + 'title': 'Breaking Points: The Paper Mine', + 'duration': 1287, + 'description': 'Overly complicated paper pushing is nothing new to government bureaucracy. But the way federal retirement applications are filed may be the most outdated. David Fahrenthold explains.', + 'uploader': 'The Washington Post', + 'timestamp': 1395527908, + 'upload_date': '20140322', + }, + }, { + 'md5': 'f645a07652c2950cd9134bb852c5f5eb', + 'info_dict': { + 'id': '41255e28-b14a-11e3-b8b3-44b1d1cd4c1f', + 'ext': 'mp4', + 'title': 'The town bureaucracy sustains', + 'description': 'Underneath the friendly town of Boyers is a sea of government paperwork. In a disused limestone mine, hundreds of locals now track, file and process retirement applications for the federal government. We set out to find out what it\'s like to do paperwork 230 feet underground.', + 'duration': 2217, + 'timestamp': 1395528005, + 'upload_date': '20140322', + 'uploader': 'The Washington Post', + }, + }] + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + page_id = mobj.group('id') + + webpage = self._download_webpage(url, page_id) + title = self._og_search_title(webpage) + uuids = re.findall(r'data-video-uuid="([^"]+)"', webpage) + entries = [] + for i, uuid in enumerate(uuids, start=1): + vinfo_all = self._download_json( + 'http://www.washingtonpost.com/posttv/c/videojson/%s?resType=jsonp' % uuid, + page_id, + transform_source=strip_jsonp, + note='Downloading information of video %d/%d' % (i, len(uuids)) + ) + vinfo = vinfo_all[0]['contentConfig'] + uploader = vinfo.get('credits', {}).get('source') + timestamp = int_or_none( + vinfo.get('dateConfig', {}).get('dateFirstPublished'), 1000) + + formats = [{ + 'format_id': ( + '%s-%s-%s' % (s.get('type'), s.get('width'), s.get('bitrate')) + if s.get('width') + else s.get('type')), + 'vbr': s.get('bitrate') if s.get('width') != 0 else None, + 'width': s.get('width'), + 'height': s.get('height'), + 'acodec': s.get('audioCodec'), + 'vcodec': s.get('videoCodec') if s.get('width') != 0 else 'none', + 'filesize': s.get('fileSize'), + 'url': s.get('url'), + 'ext': 'mp4', + 'protocol': { + 'MP4': 'http', + 'F4F': 'f4m', + }.get(s.get('type')) + } for s in vinfo.get('streams', [])] + source_media_url = vinfo.get('sourceMediaURL') + if source_media_url: + formats.append({ + 'format_id': 'source_media', + 'url': source_media_url, + }) + self._sort_formats(formats) + entries.append({ + 'id': uuid, + 'title': vinfo['title'], + 'description': vinfo.get('blurb'), + 'uploader': uploader, + 'formats': formats, + 'duration': int_or_none(vinfo.get('videoDuration'), 100), + 'timestamp': timestamp, + }) + + return { + '_type': 'playlist', + 'entries': entries, + 'id': page_id, + 'title': title, + } diff --git a/youtube_dl/extractor/wat.py b/youtube_dl/extractor/wat.py index 4fab6c6e8..a584e0896 100644 --- a/youtube_dl/extractor/wat.py +++ b/youtube_dl/extractor/wat.py @@ -1,37 +1,37 @@ # coding: utf-8 +from __future__ import unicode_literals -import json import re from .common import InfoExtractor - from ..utils import ( unified_strdate, ) class WatIE(InfoExtractor): - _VALID_URL=r'http://www\.wat\.tv/.*-(?P<shortID>.*?)_.*?\.html' + _VALID_URL = r'http://www\.wat\.tv/.*-(?P<shortID>.*?)_.*?\.html' IE_NAME = 'wat.tv' _TEST = { - u'url': u'http://www.wat.tv/video/world-war-philadelphia-vost-6bv55_2fjr7_.html', - u'file': u'10631273.mp4', - u'md5': u'd8b2231e1e333acd12aad94b80937e19', - u'info_dict': { - u'title': u'World War Z - Philadelphia VOST', - u'description': u'La menace est partout. Que se passe-t-il à Philadelphia ?\r\nWORLD WAR Z, avec Brad Pitt, au cinéma le 3 juillet.\r\nhttp://www.worldwarz.fr', + 'url': 'http://www.wat.tv/video/world-war-philadelphia-vost-6bv55_2fjr7_.html', + 'info_dict': { + 'id': '10631273', + 'ext': 'mp4', + 'title': 'World War Z - Philadelphia VOST', + 'description': 'La menace est partout. Que se passe-t-il à Philadelphia ?\r\nWORLD WAR Z, avec Brad Pitt, au cinéma le 3 juillet.\r\nhttp://www.worldwarz.fr', + }, + 'params': { + # Sometimes wat serves the whole file with the --test option + 'skip_download': True, }, - u'skip': u'Sometimes wat serves the whole file with the --test option', } - + def download_video_info(self, real_id): # 'contentv4' is used in the website, but it also returns the related # videos, we don't need them - info = self._download_webpage('http://www.wat.tv/interface/contentv3/' + real_id, real_id, 'Downloading video info') - info = json.loads(info) + info = self._download_json('http://www.wat.tv/interface/contentv3/' + real_id, real_id) return info['media'] - def _real_extract(self, url): def real_id_for_chapter(chapter): return chapter['tc_start'].split('-')[0] @@ -56,17 +56,17 @@ class WatIE(InfoExtractor): entries = [self.url_result(chapter_url) for chapter_url in chapter_urls] return self.playlist_result(entries, real_id, video_info['title']) + upload_date = None + if 'date_diffusion' in first_chapter: + upload_date = unified_strdate(first_chapter['date_diffusion']) # Otherwise we can continue and extract just one part, we have to use # the short id for getting the video url - info = {'id': real_id, - 'url': 'http://wat.tv/get/android5/%s.mp4' % real_id, - 'ext': 'mp4', - 'title': first_chapter['title'], - 'thumbnail': first_chapter['preview'], - 'description': first_chapter['description'], - 'view_count': video_info['views'], - } - if 'date_diffusion' in first_chapter: - info['upload_date'] = unified_strdate(first_chapter['date_diffusion']) - - return info + return { + 'id': real_id, + 'url': 'http://wat.tv/get/android5/%s.mp4' % real_id, + 'title': first_chapter['title'], + 'thumbnail': first_chapter['preview'], + 'description': first_chapter['description'], + 'view_count': video_info['views'], + 'upload_date': upload_date, + } diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py index 500b9146f..63691aa67 100644 --- a/youtube_dl/extractor/wdr.py +++ b/youtube_dl/extractor/wdr.py @@ -4,9 +4,10 @@ import re from .common import InfoExtractor from ..utils import ( - unified_strdate, + compat_parse_qs, compat_urlparse, determine_ext, + unified_strdate, ) @@ -111,4 +112,85 @@ class WDRIE(InfoExtractor): 'description': description, 'thumbnail': thumbnail, 'upload_date': upload_date, - }
\ No newline at end of file + } + + +class WDRMausIE(InfoExtractor): + _VALID_URL = 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))' + IE_DESC = 'Sendung mit der Maus' + _TESTS = [{ + 'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5', + 'info_dict': { + 'id': 'aktuelle-sendung', + 'ext': 'mp4', + 'thumbnail': 're:^http://.+\.jpg', + 'upload_date': 're:^[0-9]{8}$', + 'title': 're:^[0-9.]{10} - Aktuelle Sendung$', + } + }, { + 'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/40_jahre_maus.php5', + 'md5': '3b1227ca3ed28d73ec5737c65743b2a3', + 'info_dict': { + 'id': '40_jahre_maus', + 'ext': 'mp4', + 'thumbnail': 're:^http://.+\.jpg', + 'upload_date': '20131007', + 'title': '12.03.2011 - 40 Jahre Maus', + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + param_code = self._html_search_regex( + r'<a href="\?startVideo=1&([^"]+)"', webpage, 'parameters') + + title_date = self._search_regex( + r'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>', + webpage, 'air date') + title_str = self._html_search_regex( + r'<h1>(.*?)</h1>', webpage, 'title') + title = '%s - %s' % (title_date, title_str) + upload_date = unified_strdate( + self._html_search_meta('dc.date', webpage)) + + fields = compat_parse_qs(param_code) + video_url = fields['firstVideo'][0] + thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0]) + + formats = [{ + 'format_id': 'rtmp', + 'url': video_url, + }] + + jscode = self._download_webpage( + 'http://www.wdrmaus.de/codebase/js/extended-medien.min.js', + video_id, fatal=False, + note='Downloading URL translation table', + errnote='Could not download URL translation table') + if jscode: + for m in re.finditer( + r"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}", + jscode): + if video_url.startswith(m.group('stream')): + http_url = video_url.replace( + m.group('stream'), m.group('dl')) + formats.append({ + 'format_id': 'http', + 'url': http_url, + }) + break + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + } + +# TODO test _1
\ No newline at end of file diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index 79fd53e0c..c27dda944 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -3,11 +3,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from .youtube import YoutubeIE class WimpIE(InfoExtractor): _VALID_URL = r'http://(?:www\.)?wimp\.com/([^/]+)/' - _TEST = { + _TESTS = [{ 'url': 'http://www.wimp.com/maruexhausted/', 'md5': 'f1acced123ecb28d9bb79f2479f2b6a1', 'info_dict': { @@ -16,7 +17,20 @@ class WimpIE(InfoExtractor): 'title': 'Maru is exhausted.', 'description': 'md5:57e099e857c0a4ea312542b684a869b8', } - } + }, { + # youtube video + 'url': 'http://www.wimp.com/clowncar/', + 'info_dict': { + 'id': 'cG4CEr2aiSg', + 'ext': 'mp4', + 'title': 'Basset hound clown car...incredible!', + 'description': 'md5:8d228485e0719898c017203f900b3a35', + 'uploader': 'Gretchen Hoey', + 'uploader_id': 'gretchenandjeff1', + 'upload_date': '20140303', + }, + 'add_ie': ['Youtube'], + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -24,6 +38,13 @@ class WimpIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_url = self._search_regex( r's1\.addVariable\("file",\s*"([^"]+)"\);', webpage, 'video URL') + if YoutubeIE.suitable(video_url): + self.to_screen('Found YouTube video') + return { + '_type': 'url', + 'url': video_url, + 'ie_key': YoutubeIE.ie_key(), + } return { 'id': video_id, @@ -31,4 +52,4 @@ class WimpIE(InfoExtractor): 'title': self._og_search_title(webpage), 'thumbnail': self._og_search_thumbnail(webpage), 'description': self._og_search_description(webpage), - }
\ No newline at end of file + } diff --git a/youtube_dl/extractor/worldstarhiphop.py b/youtube_dl/extractor/worldstarhiphop.py index fc9237a3f..4e89acd81 100644 --- a/youtube_dl/extractor/worldstarhiphop.py +++ b/youtube_dl/extractor/worldstarhiphop.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -7,14 +9,14 @@ class WorldStarHipHopIE(InfoExtractor): _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)' _TEST = { "url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO", - "file": "wshh6a7q1ny0G34ZwuIO.mp4", "md5": "9d04de741161603bf7071bbf4e883186", "info_dict": { + "id": "wshh6a7q1ny0G34ZwuIO", + "ext": "mp4", "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!" } } - def _real_extract(self, url): m = re.match(self._VALID_URL, url) video_id = m.group('id') @@ -23,41 +25,32 @@ class WorldStarHipHopIE(InfoExtractor): m_vevo_id = re.search(r'videoId=(.*?)&?', webpage_src) - if m_vevo_id is not None: - self.to_screen(u'Vevo video detected:') return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo') - video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)', - webpage_src, u'video URL') + video_url = self._search_regex( + r'so\.addVariable\("file","(.*?)"\)', webpage_src, 'video URL') if 'youtube' in video_url: - self.to_screen(u'Youtube video detected:') return self.url_result(video_url, ie='Youtube') - if 'mp4' in video_url: - ext = 'mp4' - else: - ext = 'flv' - - video_title = self._html_search_regex(r"<title>(.*)</title>", - webpage_src, u'title') + video_title = self._html_search_regex( + r"<title>(.*)</title>", webpage_src, 'title') # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video. - thumbnail = self._html_search_regex(r'rel="image_src" href="(.*)" />', - webpage_src, u'thumbnail', fatal=False) - + thumbnail = self._html_search_regex( + r'rel="image_src" href="(.*)" />', webpage_src, 'thumbnail', + fatal=False) if not thumbnail: _title = r"""candytitles.*>(.*)</span>""" mobj = re.search(_title, webpage_src) if mobj is not None: video_title = mobj.group(1) - results = [{ - 'id': video_id, - 'url' : video_url, - 'title' : video_title, - 'thumbnail' : thumbnail, - 'ext' : ext, - }] - return results + return { + 'id': video_id, + 'url': video_url, + 'title': video_title, + 'thumbnail': thumbnail, + } + diff --git a/youtube_dl/extractor/xbef.py b/youtube_dl/extractor/xbef.py new file mode 100644 index 000000000..71bd7c463 --- /dev/null +++ b/youtube_dl/extractor/xbef.py @@ -0,0 +1,50 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, +) + + +class XBefIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?xbef\.com/video/(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://xbef.com/video/5119-glamourous-lesbians-smoking-drinking-and-fucking', + 'md5': 'a478b565baff61634a98f5e5338be995', + 'info_dict': { + 'id': '5119', + 'ext': 'mp4', + 'title': 'md5:7358a9faef8b7b57acda7c04816f170e', + 'age_limit': 18, + 'thumbnail': 're:^http://.*\.jpg', + } + } + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('id') + + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex( + r'<h1[^>]*>(.*?)</h1>', webpage, 'title') + + config_url_enc = self._download_webpage( + 'http://xbef.com/Main/GetVideoURLEncoded/%s' % video_id, video_id, + note='Retrieving config URL') + config_url = compat_urllib_parse.unquote(config_url_enc) + config = self._download_xml( + config_url, video_id, note='Retrieving config') + + video_url = config.find('./file').text + thumbnail = config.find('./image').text + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'age_limit': 18, + } + diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 033a9d893..b293e2665 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -75,4 +75,40 @@ class XTubeIE(InfoExtractor): 'comment_count': comment_count, 'formats': formats, 'age_limit': 18, - }
\ No newline at end of file + } + +class XTubeUserIE(InfoExtractor): + IE_DESC = 'XTube user profile' + _VALID_URL = r'https?://(?:www\.)?xtube\.com/community/profile\.php\?(.*?)user=(?P<username>[^&#]+)(?:$|[&#])' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + username = mobj.group('username') + + profile_page = self._download_webpage( + url, username, note='Retrieving profile page') + + video_count = int(self._search_regex( + r'<strong>%s\'s Videos \(([0-9]+)\)</strong>'%username, profile_page, + 'video count')) + + PAGE_SIZE = 25 + urls = [] + page_count = (video_count + PAGE_SIZE + 1) // PAGE_SIZE + for n in range(1, page_count + 1): + lpage_url = 'http://www.xtube.com/user_videos.php?page=%d&u=%s' % (n, username) + lpage = self._download_webpage( + lpage_url, username, + note='Downloading page %d/%d' % (n, page_count)) + urls.extend( + re.findall(r'addthis:url="([^"]+)"', lpage)) + + return { + '_type': 'playlist', + 'id': username, + 'entries': [{ + '_type': 'url', + 'url': eurl, + 'ie_key': 'XTube', + } for eurl in urls] + } diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index d92d14f71..e2cf1ae56 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -15,22 +15,24 @@ from ..utils import ( class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen' - _VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P<id>\d*?)\.html' + _VALID_URL = r'https?://screen\.yahoo\.com/.*?-(?P<id>[0-9]+)(?:-[a-z]+)?\.html' _TESTS = [ { 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', - 'file': '214727115.mp4', 'md5': '4962b075c08be8690a922ee026d05e69', 'info_dict': { + 'id': '214727115', + 'ext': 'mp4', 'title': 'Julian Smith & Travis Legg Watch Julian Smith', 'description': 'Julian and Travis watch Julian Smith', }, }, { 'url': 'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html', - 'file': '103000935.mp4', 'md5': 'd6e6fc6e1313c608f316ddad7b82b306', 'info_dict': { + 'id': '103000935', + 'ext': 'mp4', 'title': 'Codefellas - The Cougar Lies with Spanish Moss', 'description': 'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?', }, @@ -60,10 +62,9 @@ class YahooIE(InfoExtractor): 'env': 'prod', 'format': 'json', }) - query_result_json = self._download_webpage( + query_result = self._download_json( 'http://video.query.yahoo.com/v1/public/yql?' + data, video_id, 'Downloading video info') - query_result = json.loads(query_result_json) info = query_result['query']['results']['mediaObj'][0] meta = info['meta'] @@ -86,7 +87,6 @@ class YahooIE(InfoExtractor): else: format_url = compat_urlparse.urljoin(host, path) format_info['url'] = format_url - formats.append(format_info) self._sort_formats(formats) @@ -134,27 +134,25 @@ class YahooSearchIE(SearchInfoExtractor): def _get_n_results(self, query, n): """Get a specified number of results for a query""" - - res = { - '_type': 'playlist', - 'id': query, - 'entries': [] - } - for pagenum in itertools.count(0): + entries = [] + for pagenum in itertools.count(0): result_url = 'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30) - webpage = self._download_webpage(result_url, query, - note='Downloading results page '+str(pagenum+1)) - info = json.loads(webpage) + info = self._download_json(result_url, query, + note='Downloading results page '+str(pagenum+1)) m = info['m'] results = info['results'] for (i, r) in enumerate(results): - if (pagenum * 30) +i >= n: + if (pagenum * 30) + i >= n: break mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r) e = self.url_result('http://' + mobj.group('url'), 'Yahoo') - res['entries'].append(e) - if (pagenum * 30 +i >= n) or (m['last'] >= (m['total'] -1)): + entries.append(e) + if (pagenum * 30 + i >= n) or (m['last'] >= (m['total'] - 1)): break - return res + return { + '_type': 'playlist', + 'id': query, + 'entries': entries, + } diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 3a3a5a39e..334a61833 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -7,13 +7,13 @@ import itertools import json import os.path import re -import string import struct import traceback import zlib from .common import InfoExtractor, SearchInfoExtractor from .subtitles import SubtitlesInfoExtractor +from ..jsinterp import JSInterpreter from ..utils import ( compat_chr, compat_parse_qs, @@ -438,113 +438,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): def _parse_sig_js(self, jscode): funcname = self._search_regex( r'signature=([a-zA-Z]+)', jscode, - u'Initial JS player signature function name') - - functions = {} - - def argidx(varname): - return string.lowercase.index(varname) - - def interpret_statement(stmt, local_vars, allow_recursion=20): - if allow_recursion < 0: - raise ExtractorError(u'Recursion limit reached') - - if stmt.startswith(u'var '): - stmt = stmt[len(u'var '):] - ass_m = re.match(r'^(?P<out>[a-z]+)(?:\[(?P<index>[^\]]+)\])?' + - r'=(?P<expr>.*)$', stmt) - if ass_m: - if ass_m.groupdict().get('index'): - def assign(val): - lvar = local_vars[ass_m.group('out')] - idx = interpret_expression(ass_m.group('index'), - local_vars, allow_recursion) - assert isinstance(idx, int) - lvar[idx] = val - return val - expr = ass_m.group('expr') - else: - def assign(val): - local_vars[ass_m.group('out')] = val - return val - expr = ass_m.group('expr') - elif stmt.startswith(u'return '): - assign = lambda v: v - expr = stmt[len(u'return '):] - else: - raise ExtractorError( - u'Cannot determine left side of statement in %r' % stmt) - - v = interpret_expression(expr, local_vars, allow_recursion) - return assign(v) - - def interpret_expression(expr, local_vars, allow_recursion): - if expr.isdigit(): - return int(expr) - - if expr.isalpha(): - return local_vars[expr] - - m = re.match(r'^(?P<in>[a-z]+)\.(?P<member>.*)$', expr) - if m: - member = m.group('member') - val = local_vars[m.group('in')] - if member == 'split("")': - return list(val) - if member == 'join("")': - return u''.join(val) - if member == 'length': - return len(val) - if member == 'reverse()': - return val[::-1] - slice_m = re.match(r'slice\((?P<idx>.*)\)', member) - if slice_m: - idx = interpret_expression( - slice_m.group('idx'), local_vars, allow_recursion-1) - return val[idx:] - - m = re.match( - r'^(?P<in>[a-z]+)\[(?P<idx>.+)\]$', expr) - if m: - val = local_vars[m.group('in')] - idx = interpret_expression(m.group('idx'), local_vars, - allow_recursion-1) - return val[idx] - - m = re.match(r'^(?P<a>.+?)(?P<op>[%])(?P<b>.+?)$', expr) - if m: - a = interpret_expression(m.group('a'), - local_vars, allow_recursion) - b = interpret_expression(m.group('b'), - local_vars, allow_recursion) - return a % b - - m = re.match( - r'^(?P<func>[a-zA-Z$]+)\((?P<args>[a-z0-9,]+)\)$', expr) - if m: - fname = m.group('func') - if fname not in functions: - functions[fname] = extract_function(fname) - argvals = [int(v) if v.isdigit() else local_vars[v] - for v in m.group('args').split(',')] - return functions[fname](argvals) - raise ExtractorError(u'Unsupported JS expression %r' % expr) - - def extract_function(funcname): - func_m = re.search( - r'function ' + re.escape(funcname) + - r'\((?P<args>[a-z,]+)\){(?P<code>[^}]+)}', - jscode) - argnames = func_m.group('args').split(',') - - def resf(args): - local_vars = dict(zip(argnames, args)) - for stmt in func_m.group('code').split(';'): - res = interpret_statement(stmt, local_vars) - return res - return resf - - initial_function = extract_function(funcname) + u'Initial JS player signature function name') + + jsi = JSInterpreter(jscode) + initial_function = jsi.extract_function(funcname) return lambda s: initial_function([s]) def _parse_sig_swf(self, file_contents): @@ -1549,12 +1446,15 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): break more = self._download_json( - 'https://youtube.com/%s' % mobj.group('more'), playlist_id, 'Downloading page #%s' % page_num) + 'https://youtube.com/%s' % mobj.group('more'), playlist_id, + 'Downloading page #%s' % page_num, + transform_source=uppercase_escape) content_html = more['content_html'] more_widget_html = more['load_more_widget_html'] playlist_title = self._html_search_regex( - r'<h1 class="pl-header-title">\s*(.*?)\s*</h1>', page, u'title') + r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>', + page, u'title') url_results = self._ids_to_results(ids) return self.playlist_result(url_results, playlist_id, playlist_title) @@ -1712,7 +1612,7 @@ class YoutubeUserIE(InfoExtractor): class YoutubeSearchIE(SearchInfoExtractor): IE_DESC = u'YouTube.com searches' - _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc' + _API_URL = u'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc' _MAX_RESULTS = 1000 IE_NAME = u'youtube:search' _SEARCH_KEY = 'ytsearch' @@ -1723,9 +1623,12 @@ class YoutubeSearchIE(SearchInfoExtractor): video_ids = [] pagenum = 0 limit = n + PAGE_SIZE = 50 - while (50 * pagenum) < limit: - result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1) + while (PAGE_SIZE * pagenum) < limit: + result_url = self._API_URL % ( + compat_urllib_parse.quote_plus(query.encode('utf-8')), + (PAGE_SIZE * pagenum) + 1) data_json = self._download_webpage( result_url, video_id=u'query "%s"' % query, note=u'Downloading page %s' % (pagenum + 1), @@ -1836,11 +1739,10 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): feed_entries = [] paging = 0 for i in itertools.count(1): - info = self._download_webpage(self._FEED_TEMPLATE % paging, + info = self._download_json(self._FEED_TEMPLATE % paging, u'%s feed' % self._FEED_NAME, u'Downloading page %s' % i) - info = json.loads(info) - feed_html = info['feed_html'] + feed_html = info.get('feed_html') or info.get('content_html') m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html) ids = orderedSet(m.group(1) for m in m_ids) feed_entries.extend( @@ -1852,7 +1754,7 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE) class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): - IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword(requires authentication)' + IE_DESC = u'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' _FEED_NAME = 'subscriptions' _PLAYLIST_TITLE = u'Youtube Subscriptions' |