diff options
Diffstat (limited to 'youtube_dl/extractor')
68 files changed, 1097 insertions, 376 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 0abf86e44..3f740baa1 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -8,6 +8,7 @@ from .arte import ( ArteTVPlus7IE, ArteTVCreativeIE, ArteTVFutureIE, + ArteTVDDCIE, ) from .auengine import AUEngineIE from .bambuser import BambuserIE, BambuserChannelIE @@ -56,7 +57,7 @@ from .flickr import FlickrIE from .francetv import ( PluzzIE, FranceTvInfoIE, - France2IE, + FranceTVIE, GenerationQuoiIE ) from .freesound import FreesoundIE @@ -102,6 +103,7 @@ from .nbc import NBCNewsIE from .newgrounds import NewgroundsIE from .nhl import NHLIE, NHLVideocenterIE from .niconico import NiconicoIE +from .ninegag import NineGagIE from .nowvideo import NowVideoIE from .ooyala import OoyalaIE from .orf import ORFIE @@ -110,6 +112,7 @@ from .photobucket import PhotobucketIE from .podomatic import PodomaticIE from .pornhub import PornHubIE from .pornotube import PornotubeIE +from .pyvideo import PyvideoIE from .rbmaradio import RBMARadioIE from .redtube import RedTubeIE from .ringtv import RingTVIE @@ -121,6 +124,12 @@ from .rutube import RutubeIE from .sina import SinaIE from .slashdot import SlashdotIE from .slideshare import SlideshareIE +from .smotri import ( + SmotriIE, + SmotriCommunityIE, + SmotriUserIE, + SmotriBroadcastIE, +) from .sohu import SohuIE from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE from .southparkstudios import ( @@ -139,6 +148,7 @@ from .teamcoco import TeamcocoIE from .techtalks import TechTalksIE from .ted import TEDIE from .tf1 import TF1IE +from .theplatform import ThePlatformIE from .thisav import ThisAVIE from .toutv import TouTvIE from .traileraddict import TrailerAddictIE @@ -159,7 +169,13 @@ from .viddler import ViddlerIE from .videodetective import VideoDetectiveIE from .videofyme import VideofyMeIE from .videopremium import VideoPremiumIE -from .vimeo import VimeoIE, VimeoChannelIE +from .vimeo import ( + VimeoIE, + VimeoChannelIE, + VimeoUserIE, + VimeoAlbumIE, + VimeoGroupsIE, +) from .vine import VineIE from .viki import VikiIE from .vk import VKIE @@ -167,6 +183,7 @@ from .wat import WatIE from .websurg import WeBSurgIE from .weibo import WeiboIE from .wimp import WimpIE +from .wistia import WistiaIE from .worldstarhiphop import WorldStarHipHopIE from .xhamster import XHamsterIE from .xnxx import XNXXIE diff --git a/youtube_dl/extractor/addanime.py b/youtube_dl/extractor/addanime.py index b99d4b966..a3a1b999d 100644 --- a/youtube_dl/extractor/addanime.py +++ b/youtube_dl/extractor/addanime.py @@ -13,7 +13,7 @@ from ..utils import ( class AddAnimeIE(InfoExtractor): - _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)' + _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', diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py index 6d6237f8a..a527f10de 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -10,7 +10,7 @@ from ..utils import ( class AppleTrailersIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?trailers.apple.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)' + _VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)' _TEST = { u"url": u"http://trailers.apple.com/trailers/wb/manofsteel/", u"playlist": [ @@ -113,7 +113,7 @@ class AppleTrailersIE(InfoExtractor): }) formats = sorted(formats, key=lambda f: (f['height'], f['width'])) - info = { + playlist.append({ '_type': 'video', 'id': video_id, 'title': title, @@ -124,12 +124,7 @@ class AppleTrailersIE(InfoExtractor): 'upload_date': upload_date, 'uploader_id': uploader_id, 'user_agent': 'QuickTime compatible (youtube-dl)', - } - # TODO: Remove when #980 has been merged - info['url'] = formats[-1]['url'] - info['ext'] = formats[-1]['ext'] - - playlist.append(info) + }) return { '_type': 'playlist', diff --git a/youtube_dl/extractor/archiveorg.py b/youtube_dl/extractor/archiveorg.py index 61ce4469a..8bb546410 100644 --- a/youtube_dl/extractor/archiveorg.py +++ b/youtube_dl/extractor/archiveorg.py @@ -11,7 +11,7 @@ from ..utils import ( class ArchiveOrgIE(InfoExtractor): IE_NAME = 'archive.org' IE_DESC = 'archive.org videos' - _VALID_URL = r'(?:https?://)?(?:www\.)?archive.org/details/(?P<id>[^?/]+)(?:[?].*)?$' + _VALID_URL = r'(?:https?://)?(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$' _TEST = { u"url": u"http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect", u'file': u'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv', @@ -49,7 +49,7 @@ class ArchiveOrgIE(InfoExtractor): for f in formats: f['ext'] = determine_ext(f['url']) - info = { + return { '_type': 'video', 'id': video_id, 'title': title, @@ -57,12 +57,5 @@ class ArchiveOrgIE(InfoExtractor): 'description': description, 'uploader': uploader, 'upload_date': upload_date, + 'thumbnail': data.get('misc', {}).get('image'), } - thumbnail = data.get('misc', {}).get('image') - if thumbnail: - info['thumbnail'] = thumbnail - - # TODO: Remove when #980 has been merged - info.update(formats[-1]) - - return info diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 8b62ee774..4b7bef775 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -10,6 +10,7 @@ from ..utils import ( determine_ext, get_element_by_id, compat_str, + get_element_by_attribute, ) # There are different sources of video in arte.tv, the extraction process @@ -17,8 +18,8 @@ from ..utils import ( # 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>.+)' + _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$' IE_NAME = u'arte.tv' @@ -142,7 +143,9 @@ class ArteTVPlus7IE(InfoExtractor): def _extract_from_webpage(self, webpage, video_id, lang): json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url') + 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) @@ -257,3 +260,35 @@ class ArteTVFutureIE(ArteTVPlus7IE): webpage = self._download_webpage(url, anchor_id) row = get_element_by_id(anchor_id, webpage) return self._extract_from_webpage(row, anchor_id, lang) + + +class ArteTVDDCIE(ArteTVPlus7IE): + IE_NAME = u'arte.tv:ddc' + _VALID_URL = r'http?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>.+)' + + _TEST = { + u'url': u'http://ddc.arte.tv/folge/neues-aus-mauretanien', + u'file': u'049881-009_PLUS7-D.flv', + u'info_dict': { + u'title': u'Mit offenen Karten', + u'description': u'md5:57929b0eaeddeb8a0c983f58e9ebd3b6', + u'upload_date': u'20131207', + }, + u'params': { + # rtmp download + u'skip_download': True, + }, + } + + def _real_extract(self, url): + video_id, lang = self._extract_url_info(url) + if lang == 'folge': + lang = 'de' + elif lang == 'emission': + lang = 'fr' + webpage = self._download_webpage(url, video_id) + scriptElement = get_element_by_attribute('class', 'visu_video_block', webpage) + script_url = self._html_search_regex(r'src="(.*?)"', scriptElement, 'script url') + javascriptPlayerGenerator = self._download_webpage(script_url, video_id, 'Download javascript player generator') + json_url = self._search_regex(r"json_url=(.*)&rendering_place.*", javascriptPlayerGenerator, '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 95c038003..bcccc0b7a 100644 --- a/youtube_dl/extractor/auengine.py +++ b/youtube_dl/extractor/auengine.py @@ -16,7 +16,7 @@ class AUEngineIE(InfoExtractor): u"title": u"[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]" } } - _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed.php\?.*?file=([^&]+).*?' + _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed\.php\?.*?file=([^&]+).*?' def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/bambuser.py b/youtube_dl/extractor/bambuser.py index b80508efe..d48c0c38d 100644 --- a/youtube_dl/extractor/bambuser.py +++ b/youtube_dl/extractor/bambuser.py @@ -54,7 +54,7 @@ class BambuserIE(InfoExtractor): class BambuserChannelIE(InfoExtractor): IE_NAME = u'bambuser:channel' - _VALID_URL = r'http://bambuser.com/channel/(?P<user>.*?)(?:/|#|\?|$)' + _VALID_URL = r'https?://bambuser\.com/channel/(?P<user>.*?)(?:/|#|\?|$)' # The maximum number we can get with each request _STEP = 50 diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py index 493504f75..5e33a69df 100644 --- a/youtube_dl/extractor/bliptv.py +++ b/youtube_dl/extractor/bliptv.py @@ -51,8 +51,7 @@ class BlipTVIE(InfoExtractor): url = 'http://blip.tv/play/g_%s' % api_mobj.group('video_id') urlp = compat_urllib_parse_urlparse(url) if urlp.path.startswith('/play/'): - request = compat_urllib_request.Request(url) - response = compat_urllib_request.urlopen(request) + response = self._request_webpage(url, None, False) redirecturl = response.geturl() rurlp = compat_urllib_parse_urlparse(redirecturl) file_id = compat_parse_qs(rurlp.fragment)['file'][0].rpartition('/')[2] @@ -69,25 +68,23 @@ class BlipTVIE(InfoExtractor): request.add_header('User-Agent', 'iTunes/10.6.1') self.report_extraction(mobj.group(1)) info = None - try: - urlh = compat_urllib_request.urlopen(request) - if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download - basename = url.split('/')[-1] - title,ext = os.path.splitext(basename) - title = title.decode('UTF-8') - ext = ext.replace('.', '') - self.report_direct_download(title) - info = { - 'id': title, - 'url': url, - 'uploader': None, - 'upload_date': None, - 'title': title, - 'ext': ext, - 'urlhandle': urlh - } - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'ERROR: unable to download video info webpage: %s' % compat_str(err)) + urlh = self._request_webpage(request, None, False, + u'unable to download video info webpage') + if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download + basename = url.split('/')[-1] + title,ext = os.path.splitext(basename) + title = title.decode('UTF-8') + ext = ext.replace('.', '') + self.report_direct_download(title) + info = { + 'id': title, + 'url': url, + 'uploader': None, + 'upload_date': None, + 'title': title, + 'ext': ext, + 'urlhandle': urlh + } if info is None: # Regular URL try: json_code_bytes = urlh.read() diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index 3666a780b..755d9c9ef 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -4,7 +4,7 @@ from .common import InfoExtractor class BloombergIE(InfoExtractor): - _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?).html' + _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', diff --git a/youtube_dl/extractor/clipfish.py b/youtube_dl/extractor/clipfish.py index 0d18e9a7a..43efb08bf 100644 --- a/youtube_dl/extractor/clipfish.py +++ b/youtube_dl/extractor/clipfish.py @@ -17,7 +17,8 @@ class ClipfishIE(InfoExtractor): u'info_dict': { u'title': u'FIFA 14 - E3 2013 Trailer', u'duration': 82, - } + }, + u'skip': 'Blocked in the US' } def _real_extract(self, url): diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index 23647f99e..a54ce3ee7 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -1,7 +1,7 @@ import re from .common import InfoExtractor -from .mtv import MTVIE, _media_xml_tag +from .mtv import MTVServicesInfoExtractor from ..utils import ( compat_str, compat_urllib_parse, @@ -11,8 +11,8 @@ from ..utils import ( ) -class ComedyCentralIE(MTVIE): - _VALID_URL = r'http://www.comedycentral.com/(video-clips|episodes|cc-studios)/(?P<title>.*)' +class ComedyCentralIE(MTVServicesInfoExtractor): + _VALID_URL = r'https?://(?:www.)?comedycentral.com/(video-clips|episodes|cc-studios)/(?P<title>.*)' _FEED_URL = u'http://comedycentral.com/feeds/mrss/' _TEST = { @@ -25,12 +25,6 @@ class ComedyCentralIE(MTVIE): u'description': u'After a certain point, breastfeeding becomes c**kblocking.', }, } - # Overwrite MTVIE properties we don't want - _TESTS = [] - - def _get_thumbnail_url(self, uri, itemdoc): - search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail')) - return itemdoc.find(search_path).attrib['url'] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -197,7 +191,7 @@ class ComedyCentralShowsIE(InfoExtractor): }) effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1) - info = { + results.append({ 'id': shortMediaId, 'formats': formats, 'uploader': showId, @@ -205,11 +199,6 @@ class ComedyCentralShowsIE(InfoExtractor): 'title': effTitle, 'thumbnail': None, 'description': compat_str(officialTitle), - } - - # TODO: Remove when #980 has been merged - info.update(info['formats'][-1]) - - results.append(info) + }) return results diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 4f1b50880..534908a2b 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -55,6 +55,9 @@ class InfoExtractor(object): subtitles: The subtitle file contents as a dictionary in the format {language: subtitles}. view_count: How many users have watched the video on the platform. + like_count: Number of positive ratings of the video + dislike_count: Number of negative ratings of the video + comment_count: Number of comments on the video urlhandle: [internal] The urlHandle to be used to download the file, like returned by urllib.request.urlopen age_limit: Age restriction for the video, as an integer (years) @@ -151,27 +154,38 @@ class InfoExtractor(object): def IE_NAME(self): return type(self).__name__[:-2] - def _request_webpage(self, url_or_request, video_id, note=None, errnote=None): + def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): """ Returns the response handle """ if note is None: self.report_download_webpage(video_id) elif note is not False: - self.to_screen(u'%s: %s' % (video_id, note)) + if video_id is None: + self.to_screen(u'%s' % (note,)) + else: + self.to_screen(u'%s: %s' % (video_id, note)) try: return self._downloader.urlopen(url_or_request) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: if errnote is None: errnote = u'Unable to download webpage' - raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2], cause=err) + errmsg = u'%s: %s' % (errnote, compat_str(err)) + if fatal: + raise ExtractorError(errmsg, sys.exc_info()[2], cause=err) + else: + self._downloader.report_warning(errmsg) + return False - def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None): + def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True): """ Returns a tuple (page content as string, URL handle) """ # Strip hashes from the URL (#1038) if isinstance(url_or_request, (compat_str, str)): url_or_request = url_or_request.partition('#')[0] - urlh = self._request_webpage(url_or_request, video_id, note, errnote) + urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal) + if urlh is False: + assert not fatal + return False content_type = urlh.headers.get('Content-Type', '') webpage_bytes = urlh.read() m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type) @@ -206,9 +220,14 @@ class InfoExtractor(object): content = webpage_bytes.decode(encoding, 'replace') return (content, urlh) - def _download_webpage(self, url_or_request, video_id, note=None, errnote=None): + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): """ Returns the data of the page as a string """ - return self._download_webpage_handle(url_or_request, video_id, note, errnote)[0] + res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal) + if res is False: + return res + else: + content, _ = res + return content def _download_xml(self, url_or_request, video_id, note=u'Downloading XML', errnote=u'Unable to download XML'): @@ -364,7 +383,8 @@ class InfoExtractor(object): if display_name is None: display_name = name return self._html_search_regex( - r'''(?ix)<meta(?=[^>]+(?:name|property)=["\']%s["\']) + r'''(?ix)<meta + (?=[^>]+(?:itemprop|name|property)=["\']%s["\']) [^>]+content=["\']([^"\']+)["\']''' % re.escape(name), html, display_name, fatal=False) diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index 7bf03c584..d5730684d 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -6,7 +6,7 @@ from ..utils import ( ) class CSpanIE(InfoExtractor): - _VALID_URL = r'http://www.c-spanvideo.org/program/(.*)' + _VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)' _TEST = { u'url': u'http://www.c-spanvideo.org/program/HolderonV', u'file': u'315139.flv', diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 71f5e03ee..3bd0b862c 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -11,6 +11,7 @@ from ..utils import ( get_element_by_attribute, get_element_by_id, orderedSet, + str_to_int, ExtractorError, ) @@ -146,6 +147,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): self._list_available_subtitles(video_id, webpage) return + view_count = str_to_int(self._search_regex( + r'video_views_value[^>]+>([\d\.,]+)<', webpage, u'view count')) + return { 'id': video_id, 'formats': formats, @@ -155,6 +159,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): 'subtitles': video_subtitles, 'thumbnail': info['thumbnail_url'], 'age_limit': age_limit, + 'view_count': view_count, } def _get_available_subtitles(self, video_id, webpage): diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py index 3d1dcb793..d418ce4a8 100644 --- a/youtube_dl/extractor/daum.py +++ b/youtube_dl/extractor/daum.py @@ -28,7 +28,8 @@ class DaumIE(InfoExtractor): video_id = mobj.group(1) canonical_url = 'http://tvpot.daum.net/v/%s' % video_id webpage = self._download_webpage(canonical_url, video_id) - full_id = self._search_regex(r'<link rel="video_src" href=".+?vid=(.+?)"', + full_id = self._search_regex( + r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]', webpage, u'full id') query = compat_urllib_parse.urlencode({'vid': full_id}) info = self._download_xml( @@ -56,7 +57,7 @@ class DaumIE(InfoExtractor): 'format_id': profile, }) - info = { + return { 'id': video_id, 'title': info.find('TITLE').text, 'formats': formats, @@ -65,6 +66,3 @@ class DaumIE(InfoExtractor): 'duration': int(info.find('DURATION').text), 'upload_date': info.find('REGDTTM').text[:8], } - # TODO: Remove when #980 has been merged - info.update(formats[-1]) - return info diff --git a/youtube_dl/extractor/dreisat.py b/youtube_dl/extractor/dreisat.py index 3cb382e12..cb7226f82 100644 --- a/youtube_dl/extractor/dreisat.py +++ b/youtube_dl/extractor/dreisat.py @@ -11,7 +11,7 @@ from ..utils import ( class DreiSatIE(InfoExtractor): IE_NAME = '3sat' - _VALID_URL = r'(?:http://)?(?:www\.)?3sat.de/mediathek/index.php\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$' + _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/index\.php\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$' _TEST = { u"url": u"http://www.3sat.de/mediathek/index.php?obj=36983", u'file': u'36983.webm', @@ -65,7 +65,7 @@ class DreiSatIE(InfoExtractor): return (qidx, prefer_http, format['video_bitrate']) formats.sort(key=_sortkey) - info = { + return { '_type': 'video', 'id': video_id, 'title': video_title, @@ -76,8 +76,3 @@ class DreiSatIE(InfoExtractor): 'uploader': video_uploader, 'upload_date': upload_date, } - - # TODO: Remove when #980 has been merged - info.update(formats[-1]) - - return info diff --git a/youtube_dl/extractor/eighttracks.py b/youtube_dl/extractor/eighttracks.py index f21ef8853..88f5526b8 100644 --- a/youtube_dl/extractor/eighttracks.py +++ b/youtube_dl/extractor/eighttracks.py @@ -10,7 +10,7 @@ from ..utils import ( class EightTracksIE(InfoExtractor): IE_NAME = '8tracks' - _VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$' + _VALID_URL = r'https?://8tracks\.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$' _TEST = { u"name": u"EightTracks", u"url": u"http://8tracks.com/ytdl/youtube-dl-test-tracks-a", diff --git a/youtube_dl/extractor/exfm.py b/youtube_dl/extractor/exfm.py index a51d79b08..682901d16 100644 --- a/youtube_dl/extractor/exfm.py +++ b/youtube_dl/extractor/exfm.py @@ -8,7 +8,7 @@ class ExfmIE(InfoExtractor): IE_NAME = u'exfm' IE_DESC = u'ex.fm' _VALID_URL = r'(?:http://)?(?:www\.)?ex\.fm/song/([^/]+)' - _SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud.com/tracks/([^/]+)/stream' + _SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud\.com/tracks/([^/]+)/stream' _TESTS = [ { u'url': u'http://ex.fm/song/eh359', diff --git a/youtube_dl/extractor/faz.py b/youtube_dl/extractor/faz.py index c0169de04..c6ab6952e 100644 --- a/youtube_dl/extractor/faz.py +++ b/youtube_dl/extractor/faz.py @@ -9,7 +9,7 @@ from ..utils import ( class FazIE(InfoExtractor): IE_NAME = u'faz.net' - _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+).html' + _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+)\.html' _TEST = { u'url': u'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html', @@ -44,13 +44,10 @@ class FazIE(InfoExtractor): }) descr = self._html_search_regex(r'<p class="Content Copy">(.*?)</p>', webpage, u'description') - info = { + return { 'id': video_id, 'title': self._og_search_title(webpage), 'formats': formats, 'description': descr, 'thumbnail': config.find('STILL/STILL_BIG').text, } - # TODO: Remove when #980 has been merged - info.update(formats[-1]) - return info diff --git a/youtube_dl/extractor/fktv.py b/youtube_dl/extractor/fktv.py index dba1a8dc2..d7048c8c1 100644 --- a/youtube_dl/extractor/fktv.py +++ b/youtube_dl/extractor/fktv.py @@ -12,7 +12,7 @@ from ..utils import ( class FKTVIE(InfoExtractor): IE_NAME = u'fernsehkritik.tv' - _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik.tv/folge-(?P<ep>[0-9]+)(?:/.*)?' + _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?' _TEST = { u'url': u'http://fernsehkritik.tv/folge-1', @@ -52,7 +52,7 @@ class FKTVIE(InfoExtractor): class FKTVPosteckeIE(InfoExtractor): IE_NAME = u'fernsehkritik.tv:postecke' - _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik.tv/inline-video/postecke.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)' + _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)' _TEST = { u'url': u'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120', u'file': u'0120.flv', diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 6e1971043..ad85bc16d 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -21,7 +21,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor): thumbnail_path = info.find('image').text return {'id': video_id, - 'ext': 'mp4', + 'ext': 'flv' if video_url.startswith('rtmp') else 'mp4', 'url': video_url, 'title': info.find('titre').text, 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path), @@ -45,7 +45,7 @@ class PluzzIE(FranceTVBaseInfoExtractor): class FranceTvInfoIE(FranceTVBaseInfoExtractor): IE_NAME = u'francetvinfo.fr' - _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+).html' + _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+)\.html' _TEST = { u'url': u'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html', @@ -66,35 +66,101 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor): return self._extract_video(video_id) -class France2IE(FranceTVBaseInfoExtractor): - IE_NAME = u'france2.fr' - _VALID_URL = r'''(?x)https?://www\.france2\.fr/ +class FranceTVIE(FranceTVBaseInfoExtractor): + IE_NAME = u'francetv' + IE_DESC = u'France 2, 3, 4, 5 and Ô' + _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/ (?: - emissions/.*?/videos/(?P<id>\d+) - | emission/(?P<key>[^/?]+) + emissions/.*?/(videos|emissions)/(?P<id>[^/?]+) + | (emissions?|jt)/(?P<key>[^/?]+) )''' - _TEST = { - u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104', - u'file': u'75540104.mp4', - u'info_dict': { - u'title': u'13h15, le samedi...', - u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d', + _TESTS = [ + # france2 + { + u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104', + u'file': u'75540104.mp4', + u'info_dict': { + u'title': u'13h15, le samedi...', + u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d', + }, + u'params': { + # m3u8 download + u'skip_download': True, + }, }, - u'params': { - u'skip_download': True, + # france3 + { + u'url': u'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575', + u'info_dict': { + u'id': u'000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au', + u'ext': u'flv', + u'title': u'Le scandale du prix des médicaments', + u'description': u'md5:1384089fbee2f04fc6c9de025ee2e9ce', + }, + u'params': { + # rtmp download + u'skip_download': True, + }, }, - } + # france4 + { + u'url': u'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4', + u'info_dict': { + u'id': u'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4', + u'ext': u'flv', + u'title': u'Hero Corp Making of - Extrait 1', + u'description': u'md5:c87d54871b1790679aec1197e73d650a', + }, + u'params': { + # rtmp download + u'skip_download': True, + }, + }, + # france5 + { + u'url': u'http://www.france5.fr/emissions/c-a-dire/videos/92837968', + u'info_dict': { + u'id': u'92837968', + u'ext': u'mp4', + u'title': u'C à dire ?!', + u'description': u'md5:fb1db1cbad784dcce7c7a7bd177c8e2f', + }, + u'params': { + # m3u8 download + u'skip_download': True, + }, + }, + # franceo + { + u'url': u'http://www.franceo.fr/jt/info-afrique/04-12-2013', + u'info_dict': { + u'id': u'92327925', + u'ext': u'mp4', + u'title': u'Infô-Afrique', + u'description': u'md5:ebf346da789428841bee0fd2a935ea55', + }, + u'params': { + # m3u8 download + u'skip_download': True, + }, + u'skip': u'The id changes frequently', + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj.group('key'): webpage = self._download_webpage(url, mobj.group('key')) - video_id = self._html_search_regex( - r'''(?x)<div\s+class="video-player">\s* + id_res = [ + (r'''(?x)<div\s+class="video-player">\s* <a\s+href="http://videos.francetv.fr/video/([0-9]+)"\s+ - class="francetv-video-player">''', - webpage, u'video ID') + class="francetv-video-player">'''), + (r'<a id="player_direct" href="http://info\.francetelevisions' + '\.fr/\?id-video=([^"/&]+)'), + (r'<a class="video" id="ftv_player_(.+?)"'), + ] + video_id = self._html_search_regex(id_res, webpage, u'video ID') else: video_id = mobj.group('id') return self._extract_video(video_id) diff --git a/youtube_dl/extractor/gamekings.py b/youtube_dl/extractor/gamekings.py index c91669b0e..a3a5251fe 100644 --- a/youtube_dl/extractor/gamekings.py +++ b/youtube_dl/extractor/gamekings.py @@ -4,7 +4,7 @@ from .common import InfoExtractor class GamekingsIE(InfoExtractor): - _VALID_URL = r'http?://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)' + _VALID_URL = r'http://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)' _TEST = { u"url": u"http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/", u'file': u'20130811.mp4', diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index 9645b00c3..26b7d2ae5 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -47,13 +47,10 @@ class GameSpotIE(InfoExtractor): 'format_id': q, }) - info = { + return { 'id': data_video['guid'], 'title': compat_urllib_parse.unquote(data_video['title']), 'formats': formats, 'description': get_meta_content('description', webpage), 'thumbnail': self._og_search_thumbnail(webpage), } - # TODO: Remove when #980 has been merged - info.update(formats[-1]) - return info diff --git a/youtube_dl/extractor/gametrailers.py b/youtube_dl/extractor/gametrailers.py index 3cc02d97e..d82a5d4b2 100644 --- a/youtube_dl/extractor/gametrailers.py +++ b/youtube_dl/extractor/gametrailers.py @@ -1,13 +1,10 @@ import re -from .mtv import MTVIE, _media_xml_tag +from .mtv import MTVServicesInfoExtractor -class GametrailersIE(MTVIE): - """ - Gametrailers use the same videos system as MTVIE, it just changes the feed - url, where the uri is and the method to get the thumbnails. - """ - _VALID_URL = r'http://www.gametrailers.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)' + +class GametrailersIE(MTVServicesInfoExtractor): + _VALID_URL = r'http://www\.gametrailers\.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)' _TEST = { u'url': u'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer', u'file': u'70e9a5d7-cf25-4a10-9104-6f3e7342ae0d.mp4', @@ -17,15 +14,9 @@ class GametrailersIE(MTVIE): u'description': u'Faith is back! Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!', }, } - # Overwrite MTVIE properties we don't want - _TESTS = [] _FEED_URL = 'http://www.gametrailers.com/feeds/mrss' - def _get_thumbnail_url(self, uri, itemdoc): - search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail')) - return itemdoc.find(search_path).attrib['url'] - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 37671430a..216e03218 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -169,8 +169,13 @@ class GenericIE(InfoExtractor): # Site Name | Video Title # Video Title - Tagline | Site Name # and so on and so forth; it's just not practical - video_title = self._html_search_regex(r'<title>(.*)</title>', - webpage, u'video title', default=u'video', flags=re.DOTALL) + video_title = self._html_search_regex( + r'(?s)<title>(.*?)</title>', webpage, u'video title', + default=u'video') + + # video uploader is domain name + video_uploader = self._search_regex( + r'^(?:https?://)?([^/]*)/.*', url, u'video uploader') # Look for BrightCove: bc_url = BrightcoveIE._extract_brightcove_url(webpage) @@ -188,13 +193,35 @@ class GenericIE(InfoExtractor): # Look for embedded YouTube player matches = re.findall( - r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?youtube.com/embed/.+?)\1', webpage) + r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?youtube\.com/embed/.+?)\1', webpage) if matches: urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube') for tuppl in matches] return self.playlist_result( urlrs, playlist_id=video_id, playlist_title=video_title) + # Look for embedded Dailymotion player + matches = re.findall( + r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage) + if matches: + urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Dailymotion') + for tuppl in matches] + return self.playlist_result( + urlrs, playlist_id=video_id, playlist_title=video_title) + + # Look for embedded Wistia player + match = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage) + if match: + return { + '_type': 'url_transparent', + 'url': unescapeHTML(match.group('url')), + 'ie_key': 'Wistia', + 'uploader': video_uploader, + 'title': video_title, + 'id': video_id, + } + # Look for Bandcamp pages with custom domain mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage) if mobj is not None: @@ -238,14 +265,9 @@ class GenericIE(InfoExtractor): # here's a fun little line of code for you: video_id = os.path.splitext(video_id)[0] - # video uploader is domain name - video_uploader = self._search_regex(r'(?:https?://)?([^/]*)/.*', - url, u'video uploader') - return { 'id': video_id, 'url': video_url, 'uploader': video_uploader, - 'upload_date': None, 'title': video_title, } diff --git a/youtube_dl/extractor/hotnewhiphop.py b/youtube_dl/extractor/hotnewhiphop.py index 3798118a7..0ee74fb38 100644 --- a/youtube_dl/extractor/hotnewhiphop.py +++ b/youtube_dl/extractor/hotnewhiphop.py @@ -11,7 +11,7 @@ class HotNewHipHopIE(InfoExtractor): u'file': u'1435540.mp3', u'md5': u'2c2cd2f76ef11a9b3b581e8b232f3d96', u'info_dict': { - u"title": u"Freddie Gibbs - Lay It Down" + u"title": u'Freddie Gibbs "Lay It Down"' } } diff --git a/youtube_dl/extractor/ign.py b/youtube_dl/extractor/ign.py index c52146f7d..57b79a336 100644 --- a/youtube_dl/extractor/ign.py +++ b/youtube_dl/extractor/ign.py @@ -103,7 +103,7 @@ class IGNIE(InfoExtractor): 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>.+)' + _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>' diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index d8e9712a7..6fb373db2 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -21,7 +21,6 @@ class ImdbIE(InfoExtractor): u'ext': u'mp4', u'title': u'Ice Age: Continental Drift Trailer (No. 2) - IMDb', u'description': u'md5:9061c2219254e5d14e03c25c98e96a81', - u'duration': 151, } } @@ -35,6 +34,7 @@ class ImdbIE(InfoExtractor): flags=re.MULTILINE) formats = [] for f_id, f_path in available_formats: + f_path = f_path.strip() format_page = self._download_webpage( compat_urlparse.urljoin(url, f_path), u'Downloading info for %s format' % f_id) @@ -46,7 +46,6 @@ class ImdbIE(InfoExtractor): formats.append({ 'format_id': f_id, 'url': format_info['url'], - 'height': int(info['titleObject']['encoding']['selected'][:-1]), }) return { @@ -55,5 +54,4 @@ class ImdbIE(InfoExtractor): 'formats': formats, 'description': descr, 'thumbnail': format_info['slate'], - 'duration': int(info['titleObject']['title']['duration_seconds']), } diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index 213aac428..660573d02 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -3,7 +3,7 @@ import re from .common import InfoExtractor class InstagramIE(InfoExtractor): - _VALID_URL = r'(?:http://)?instagram.com/p/(.*?)/' + _VALID_URL = r'(?:http://)?instagram\.com/p/(.*?)/' _TEST = { u'url': u'http://instagram.com/p/aye83DjauH/?foo=bar#abc', u'file': u'aye83DjauH.mp4', diff --git a/youtube_dl/extractor/jukebox.py b/youtube_dl/extractor/jukebox.py index c7bb234fe..592c64e1d 100644 --- a/youtube_dl/extractor/jukebox.py +++ b/youtube_dl/extractor/jukebox.py @@ -8,7 +8,7 @@ from ..utils import ( ) class JukeboxIE(InfoExtractor): - _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<video_id>[a-z0-9\-]+).html' + _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<video_id>[a-z0-9\-]+)\.html' _IFRAME = r'<iframe .*src="(?P<iframe>[^"]*)".*>' _VIDEO_URL = r'"config":{"file":"(?P<video_url>http:[^"]+[.](?P<video_ext>[^.?]+)[?]mdtk=[0-9]+)"' _TITLE = r'<h1 class="inline">(?P<title>[^<]+)</h1>.*<span id="infos_article_artist">(?P<artist>[^<]+)</span>' diff --git a/youtube_dl/extractor/liveleak.py b/youtube_dl/extractor/liveleak.py index dd062a14e..5ae57a77c 100644 --- a/youtube_dl/extractor/liveleak.py +++ b/youtube_dl/extractor/liveleak.py @@ -8,7 +8,7 @@ from ..utils import ( class LiveLeakIE(InfoExtractor): - _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)' + _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)' IE_NAME = u'liveleak' _TEST = { u'url': u'http://www.liveleak.com/view?i=757_1364311680', diff --git a/youtube_dl/extractor/livestream.py b/youtube_dl/extractor/livestream.py index 9bc35b115..1dcd1fb2d 100644 --- a/youtube_dl/extractor/livestream.py +++ b/youtube_dl/extractor/livestream.py @@ -11,7 +11,7 @@ from ..utils import ( class LivestreamIE(InfoExtractor): IE_NAME = u'livestream' - _VALID_URL = r'http://new.livestream.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$' + _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$' _TEST = { u'url': u'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370', u'file': u'4719370.mp4', diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py index 91480ba87..bd044fb60 100644 --- a/youtube_dl/extractor/metacafe.py +++ b/youtube_dl/extractor/metacafe.py @@ -1,11 +1,8 @@ import re -import socket from .common import InfoExtractor from ..utils import ( - compat_http_client, compat_parse_qs, - compat_urllib_error, compat_urllib_parse, compat_urllib_request, compat_str, @@ -69,6 +66,21 @@ class MetacafeIE(InfoExtractor): u'age_limit': 18, }, }, + # cbs video + { + u'url': u'http://www.metacafe.com/watch/cb-0rOxMBabDXN6/samsung_galaxy_note_2_samsungs_next_generation_phablet/', + u'info_dict': { + u'id': u'0rOxMBabDXN6', + u'ext': u'flv', + u'title': u'Samsung Galaxy Note 2: Samsung\'s next-generation phablet', + u'description': u'md5:54d49fac53d26d5a0aaeccd061ada09d', + u'duration': 129, + }, + u'params': { + # rtmp download + u'skip_download': True, + }, + }, ] @@ -78,12 +90,8 @@ class MetacafeIE(InfoExtractor): def _real_initialize(self): # Retrieve disclaimer - request = compat_urllib_request.Request(self._DISCLAIMER) - try: - self.report_disclaimer() - compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err)) + self.report_disclaimer() + self._download_webpage(self._DISCLAIMER, None, False, u'Unable to retrieve disclaimer') # Confirm age disclaimer_form = { @@ -92,11 +100,8 @@ class MetacafeIE(InfoExtractor): } request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') - try: - self.report_age_confirmation() - compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err)) + self.report_age_confirmation() + self._download_webpage(request, None, False, u'Unable to confirm age') def _real_extract(self, url): # Extract id and simplified title from URL @@ -106,10 +111,16 @@ class MetacafeIE(InfoExtractor): video_id = mobj.group(1) - # Check if video comes from YouTube - mobj2 = re.match(r'^yt-(.*)$', video_id) - if mobj2 is not None: - return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')] + # the video may come from an external site + m_external = re.match('^(\w{2})-(.*)$', video_id) + if m_external is not None: + prefix, ext_id = m_external.groups() + # Check if video comes from YouTube + if prefix == 'yt': + return self.url_result('http://www.youtube.com/watch?v=%s' % ext_id, 'Youtube') + # CBS videos use theplatform.com + if prefix == 'cb': + return self.url_result('theplatform:%s' % ext_id, 'ThePlatform') # Retrieve video webpage to extract further information req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id) diff --git a/youtube_dl/extractor/metacritic.py b/youtube_dl/extractor/metacritic.py index 449138b56..6b95b4998 100644 --- a/youtube_dl/extractor/metacritic.py +++ b/youtube_dl/extractor/metacritic.py @@ -43,13 +43,10 @@ class MetacriticIE(InfoExtractor): description = self._html_search_regex(r'<b>Description:</b>(.*?)</p>', webpage, u'description', flags=re.DOTALL) - info = { + return { 'id': video_id, 'title': clip.find('title').text, 'formats': formats, 'description': description, 'duration': int(clip.find('duration').text), } - # TODO: Remove when #980 has been merged - info.update(formats[-1]) - return info diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index e2baf44d7..04fa3ac7a 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -1,13 +1,10 @@ import json import re -import socket from .common import InfoExtractor from ..utils import ( - compat_http_client, - compat_urllib_error, - compat_urllib_request, unified_strdate, + ExtractorError, ) @@ -31,9 +28,11 @@ class MixcloudIE(InfoExtractor): """Returns 1st active url from list""" for url in url_list: try: - compat_urllib_request.urlopen(url) + # We only want to know if the request succeed + # don't download the whole file + self._request_webpage(url, None, False) return url - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error): + except ExtractorError: url = None return None diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index 42aee58be..6b3feb560 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -10,35 +10,8 @@ from ..utils import ( def _media_xml_tag(tag): return '{http://search.yahoo.com/mrss/}%s' % tag -class MTVIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$' - - _FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/' - - _TESTS = [ - { - u'url': u'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml', - u'file': u'853555.mp4', - u'md5': u'850f3f143316b1e71fa56a4edfd6e0f8', - u'info_dict': { - u'title': u'Taylor Swift - "Ours (VH1 Storytellers)"', - u'description': u'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.', - }, - }, - { - u'add_ie': ['Vevo'], - u'url': u'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml', - u'file': u'USCJY1331283.mp4', - u'md5': u'73b4e7fcadd88929292fe52c3ced8caf', - u'info_dict': { - u'title': u'Everything Has Changed', - u'upload_date': u'20130606', - u'uploader': u'Taylor Swift', - }, - u'skip': u'VEVO is only available in some countries', - }, - ] +class MTVServicesInfoExtractor(InfoExtractor): @staticmethod def _id_from_uri(uri): return uri.split(':')[-1] @@ -53,7 +26,12 @@ class MTVIE(InfoExtractor): return base + m.group('finalid') def _get_thumbnail_url(self, uri, itemdoc): - return 'http://mtv.mtvnimages.com/uri/' + uri + search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail')) + thumb_node = itemdoc.find(search_path) + if thumb_node is None: + return None + else: + return thumb_node.attrib['url'] def _extract_video_formats(self, metadataXml): if '/error_country_block.swf' in metadataXml: @@ -93,7 +71,7 @@ class MTVIE(InfoExtractor): else: description = None - info = { + return { 'title': itemdoc.find('title').text, 'formats': self._extract_video_formats(mediagen_page), 'id': video_id, @@ -101,11 +79,6 @@ class MTVIE(InfoExtractor): 'description': description, } - # TODO: Remove when #980 has been merged - info.update(info['formats'][-1]) - - return info - def _get_videos_info(self, uri): video_id = self._id_from_uri(uri) data = compat_urllib_parse.urlencode({'uri': uri}) @@ -113,6 +86,39 @@ class MTVIE(InfoExtractor): u'Downloading info') return [self._get_video_info(item) for item in idoc.findall('.//item')] + +class MTVIE(MTVServicesInfoExtractor): + _VALID_URL = r'^https?://(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$' + + _FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/' + + _TESTS = [ + { + u'url': u'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml', + u'file': u'853555.mp4', + u'md5': u'850f3f143316b1e71fa56a4edfd6e0f8', + u'info_dict': { + u'title': u'Taylor Swift - "Ours (VH1 Storytellers)"', + u'description': u'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.', + }, + }, + { + u'add_ie': ['Vevo'], + u'url': u'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml', + u'file': u'USCJY1331283.mp4', + u'md5': u'73b4e7fcadd88929292fe52c3ced8caf', + u'info_dict': { + u'title': u'Everything Has Changed', + u'upload_date': u'20130606', + u'uploader': u'Taylor Swift', + }, + u'skip': u'VEVO is only available in some countries', + }, + ] + + def _get_thumbnail_url(self, uri, itemdoc): + return 'http://mtv.mtvnimages.com/uri/' + uri + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('videoid') diff --git a/youtube_dl/extractor/muzu.py b/youtube_dl/extractor/muzu.py index 03e31ea1c..1772b7f9a 100644 --- a/youtube_dl/extractor/muzu.py +++ b/youtube_dl/extractor/muzu.py @@ -9,7 +9,7 @@ from ..utils import ( class MuzuTVIE(InfoExtractor): - _VALID_URL = r'https?://www.muzu.tv/(.+?)/(.+?)/(?P<id>\d+)' + _VALID_URL = r'https?://www\.muzu\.tv/(.+?)/(.+?)/(?P<id>\d+)' IE_NAME = u'muzu.tv' _TEST = { diff --git a/youtube_dl/extractor/myspass.py b/youtube_dl/extractor/myspass.py index 0067bf134..4becddee6 100644 --- a/youtube_dl/extractor/myspass.py +++ b/youtube_dl/extractor/myspass.py @@ -9,7 +9,7 @@ from ..utils import ( class MySpassIE(InfoExtractor): - _VALID_URL = r'http://www.myspass.de/.*' + _VALID_URL = r'http://www\.myspass\.de/.*' _TEST = { u'url': u'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/', u'file': u'11741.mp4', diff --git a/youtube_dl/extractor/naver.py b/youtube_dl/extractor/naver.py index d290397c7..c012ec0cf 100644 --- a/youtube_dl/extractor/naver.py +++ b/youtube_dl/extractor/naver.py @@ -56,7 +56,7 @@ class NaverIE(InfoExtractor): 'height': int(format_el.find('height').text), }) - info = { + return { 'id': video_id, 'title': info.find('Subject').text, 'formats': formats, @@ -65,6 +65,3 @@ class NaverIE(InfoExtractor): 'upload_date': info.find('WriteDate').text.replace('.', ''), 'view_count': int(info.find('PlayCount').text), } - # TODO: Remove when #980 has been merged - info.update(formats[-1]) - return info diff --git a/youtube_dl/extractor/ninegag.py b/youtube_dl/extractor/ninegag.py new file mode 100644 index 000000000..ea986c00e --- /dev/null +++ b/youtube_dl/extractor/ninegag.py @@ -0,0 +1,43 @@ +import json +import re + +from .common import InfoExtractor + + +class NineGagIE(InfoExtractor): + IE_NAME = '9gag' + _VALID_URL = r'^https?://(?:www\.)?9gag\.tv/v/(?P<id>[0-9]+)' + + _TEST = { + u"url": u"http://9gag.tv/v/1912", + u"file": u"1912.mp4", + u"info_dict": { + u"description": u"This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)", + u"title": u"\"People Are Awesome 2013\" Is Absolutely Awesome" + }, + u'add_ie': [u'Youtube'] + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + data_json = self._html_search_regex(r'''(?x) + <div\s*id="tv-video"\s*data-video-source="youtube"\s* + data-video-meta="([^"]+)"''', webpage, u'video metadata') + + data = json.loads(data_json) + + return { + '_type': 'url_transparent', + 'url': data['youtubeVideoId'], + 'ie_key': 'Youtube', + 'id': video_id, + 'title': data['title'], + 'description': data['description'], + 'view_count': int(data['view_count']), + 'like_count': int(data['statistic']['like']), + 'dislike_count': int(data['statistic']['dislike']), + 'thumbnail': data['thumbnail_url'], + } diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index cfca2a063..b42eae89a 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -12,7 +12,7 @@ from ..utils import ( ) class ORFIE(InfoExtractor): - _VALID_URL = r'https?://tvthek.orf.at/(programs/.+?/episodes|topics/.+?)/(?P<id>\d+)' + _VALID_URL = r'https?://tvthek\.orf\.at/(programs/.+?/episodes|topics/.+?)/(?P<id>\d+)' def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 65462d867..25f019231 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -5,7 +5,7 @@ from .common import InfoExtractor class PBSIE(InfoExtractor): - _VALID_URL = r'https?://video.pbs.org/video/(?P<id>\d+)/?' + _VALID_URL = r'https?://video\.pbs\.org/video/(?P<id>\d+)/?' _TEST = { u'url': u'http://video.pbs.org/video/2365006249/', diff --git a/youtube_dl/extractor/pyvideo.py b/youtube_dl/extractor/pyvideo.py new file mode 100644 index 000000000..33054591b --- /dev/null +++ b/youtube_dl/extractor/pyvideo.py @@ -0,0 +1,51 @@ +import re +import os + +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", + }, + 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', + }, + }, + ] + + 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) + + 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) + return { + 'id': video_id, + 'title': os.path.splitext(title)[0], + 'url': video_url, + } diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py index 3bbda128e..c2254ae8a 100644 --- a/youtube_dl/extractor/redtube.py +++ b/youtube_dl/extractor/redtube.py @@ -30,7 +30,7 @@ class RedTubeIE(InfoExtractor): r'<source src="(.+?)" type="video/mp4">', webpage, u'video URL') video_title = self._html_search_regex( - r'<h1 class="videoTitle slidePanelMovable">(.+?)</h1>', + r'<h1 class="videoTitle[^"]*">(.+?)</h1>', webpage, u'title') # No self-labeling, but they describe themselves as diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index a18034fe2..e3e9bc07f 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -11,7 +11,7 @@ from ..utils import ( class RutubeIE(InfoExtractor): - _VALID_URL = r'https?://rutube.ru/video/(?P<long_id>\w+)' + _VALID_URL = r'https?://rutube\.ru/video/(?P<long_id>\w+)' _TEST = { u'url': u'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/', diff --git a/youtube_dl/extractor/slashdot.py b/youtube_dl/extractor/slashdot.py index f5003c7f9..d68646d24 100644 --- a/youtube_dl/extractor/slashdot.py +++ b/youtube_dl/extractor/slashdot.py @@ -4,7 +4,7 @@ from .common import InfoExtractor class SlashdotIE(InfoExtractor): - _VALID_URL = r'https?://tv.slashdot.org/video/\?embed=(?P<id>.*?)(&|$)' + _VALID_URL = r'https?://tv\.slashdot\.org/video/\?embed=(?P<id>.*?)(&|$)' _TEST = { u'add_ie': ['Ooyala'], diff --git a/youtube_dl/extractor/smotri.py b/youtube_dl/extractor/smotri.py new file mode 100644 index 000000000..4ea89bf85 --- /dev/null +++ b/youtube_dl/extractor/smotri.py @@ -0,0 +1,356 @@ +# encoding: utf-8 + +import re +import json +import hashlib +import uuid + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, + ExtractorError, +) + + +class SmotriIE(InfoExtractor): + IE_DESC = u'Smotri.com' + IE_NAME = u'smotri' + _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/video/view/\?id=(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4}))' + + _TESTS = [ + # real video id 2610366 + { + u'url': u'http://smotri.com/video/view/?id=v261036632ab', + u'file': u'v261036632ab.mp4', + u'md5': u'2a7b08249e6f5636557579c368040eb9', + u'info_dict': { + u'title': u'катастрофа с камер видеонаблюдения', + u'uploader': u'rbc2008', + u'uploader_id': u'rbc08', + u'upload_date': u'20131118', + u'description': u'катастрофа с камер видеонаблюдения, видео катастрофа с камер видеонаблюдения', + u'thumbnail': u'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg', + }, + }, + # real video id 57591 + { + u'url': u'http://smotri.com/video/view/?id=v57591cb20', + u'file': u'v57591cb20.flv', + u'md5': u'830266dfc21f077eac5afd1883091bcd', + u'info_dict': { + u'title': u'test', + u'uploader': u'Support Photofile@photofile', + u'uploader_id': u'support-photofile', + u'upload_date': u'20070704', + u'description': u'test, видео test', + u'thumbnail': u'http://frame4.loadup.ru/03/ed/57591.2.3.jpg', + }, + }, + # video-password + { + u'url': u'http://smotri.com/video/view/?id=v1390466a13c', + u'file': u'v1390466a13c.mp4', + u'md5': u'f6331cef33cad65a0815ee482a54440b', + u'info_dict': { + u'title': u'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1', + u'uploader': u'timoxa40', + u'uploader_id': u'timoxa40', + u'upload_date': u'20100404', + u'thumbnail': u'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg', + u'description': u'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1, видео TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1', + }, + u'params': { + u'videopassword': u'qwerty', + }, + }, + # age limit + video-password + { + u'url': u'http://smotri.com/video/view/?id=v15408898bcf', + u'file': u'v15408898bcf.flv', + u'md5': u'91e909c9f0521adf5ee86fbe073aad70', + u'info_dict': { + u'title': u'этот ролик не покажут по ТВ', + u'uploader': u'zzxxx', + u'uploader_id': u'ueggb', + u'upload_date': u'20101001', + u'thumbnail': u'http://frame3.loadup.ru/75/75/1540889.1.3.jpg', + u'age_limit': 18, + u'description': u'этот ролик не покажут по ТВ, видео этот ролик не покажут по ТВ', + }, + u'params': { + u'videopassword': u'333' + } + } + ] + + _SUCCESS = 0 + _PASSWORD_NOT_VERIFIED = 1 + _PASSWORD_DETECTED = 2 + _VIDEO_NOT_FOUND = 3 + + def _search_meta(self, name, html, display_name=None): + if display_name is None: + display_name = name + return self._html_search_regex( + r'<meta itemprop="%s" content="([^"]+)" />' % re.escape(name), + html, display_name, fatal=False) + return self._html_search_meta(name, html, display_name) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('videoid') + real_video_id = mobj.group('realvideoid') + + # Download video JSON data + video_json_url = 'http://smotri.com/vt.php?id=%s' % real_video_id + video_json_page = self._download_webpage(video_json_url, video_id, u'Downloading video JSON') + video_json = json.loads(video_json_page) + + status = video_json['status'] + if status == self._VIDEO_NOT_FOUND: + raise ExtractorError(u'Video %s does not exist' % video_id, expected=True) + elif status == self._PASSWORD_DETECTED: # The video is protected by a password, retry with + # video-password set + video_password = self._downloader.params.get('videopassword', None) + if not video_password: + raise ExtractorError(u'This video is protected by a password, use the --video-password option', expected=True) + video_json_url += '&md5pass=%s' % hashlib.md5(video_password.encode('utf-8')).hexdigest() + video_json_page = self._download_webpage(video_json_url, video_id, u'Downloading video JSON (video-password set)') + video_json = json.loads(video_json_page) + status = video_json['status'] + if status == self._PASSWORD_NOT_VERIFIED: + raise ExtractorError(u'Video password is invalid', expected=True) + + if status != self._SUCCESS: + raise ExtractorError(u'Unexpected status value %s' % status) + + # Extract the URL of the video + video_url = video_json['file_data'] + + # 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 = self._download_webpage(video_page_url, video_id, u'Downloading video page') + + # Adult content + if re.search(u'EroConfirmText">', video_page) is not None: + self.report_age_confirmation() + confirm_string = self._html_search_regex( + r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id, + video_page, u'confirm string') + confirm_url = video_page_url + '&confirm=%s' % confirm_string + video_page = self._download_webpage(confirm_url, video_id, u'Downloading video page (age confirmed)') + adult_content = True + else: + adult_content = False + + # Extract the rest of meta data + video_title = self._search_meta(u'name', video_page, u'title') + if not video_title: + video_title = video_url.rsplit('/', 1)[-1] + + video_description = self._search_meta(u'description', video_page) + END_TEXT = u' на сайте Smotri.com' + if video_description.endswith(END_TEXT): + video_description = video_description[:-len(END_TEXT)] + START_TEXT = u'Смотреть онлайн ролик ' + if video_description.startswith(START_TEXT): + video_description = video_description[len(START_TEXT):] + video_thumbnail = self._search_meta(u'thumbnail', video_page) + + upload_date_str = self._search_meta(u'uploadDate', video_page, u'upload date') + upload_date_m = re.search(r'(?P<year>\d{4})\.(?P<month>\d{2})\.(?P<day>\d{2})T', upload_date_str) + video_upload_date = ( + ( + upload_date_m.group('year') + + upload_date_m.group('month') + + upload_date_m.group('day') + ) + if upload_date_m else None + ) + + duration_str = self._search_meta(u'duration', video_page) + duration_m = re.search(r'T(?P<hours>[0-9]{2})H(?P<minutes>[0-9]{2})M(?P<seconds>[0-9]{2})S', duration_str) + video_duration = ( + ( + (int(duration_m.group('hours')) * 60 * 60) + + (int(duration_m.group('minutes')) * 60) + + int(duration_m.group('seconds')) + ) + if duration_m else None + ) + + video_uploader = self._html_search_regex( + u'<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info[^"]+">(.*?)</a>', + video_page, u'uploader', fatal=False, flags=re.MULTILINE|re.DOTALL) + + video_uploader_id = self._html_search_regex( + u'<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info\\(.*?\'([^\']+)\'\\);">', + video_page, u'uploader id', fatal=False, flags=re.MULTILINE|re.DOTALL) + + video_view_count = self._html_search_regex( + u'Общее количество просмотров.*?<span class="Number">(\\d+)</span>', + video_page, u'view count', fatal=False, flags=re.MULTILINE|re.DOTALL) + + return { + 'id': video_id, + 'url': video_url, + 'title': video_title, + 'thumbnail': video_thumbnail, + 'description': video_description, + 'uploader': video_uploader, + 'upload_date': video_upload_date, + 'uploader_id': video_uploader_id, + 'video_duration': video_duration, + 'view_count': video_view_count, + 'age_limit': 18 if adult_content else 0, + 'video_page_url': video_page_url + } + + +class SmotriCommunityIE(InfoExtractor): + IE_DESC = u'Smotri.com community videos' + IE_NAME = u'smotri:community' + _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + community_id = mobj.group('communityid') + + url = 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id + rss = self._download_xml(url, community_id, u'Downloading community RSS') + + entries = [self.url_result(video_url.text, 'Smotri') + for video_url in rss.findall('./channel/item/link')] + + description_text = rss.find('./channel/description').text + community_title = self._html_search_regex( + u'^Видео сообщества "([^"]+)"$', description_text, u'community title') + + return self.playlist_result(entries, community_id, community_title) + + +class SmotriUserIE(InfoExtractor): + IE_DESC = u'Smotri.com user videos' + IE_NAME = u'smotri:user' + _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + user_id = mobj.group('userid') + + url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id + rss = self._download_xml(url, user_id, u'Downloading user RSS') + + entries = [self.url_result(video_url.text, 'Smotri') + for video_url in rss.findall('./channel/item/link')] + + description_text = rss.find('./channel/description').text + user_nickname = self._html_search_regex( + u'^Видео режиссера (.*)$', description_text, + u'user nickname') + + return self.playlist_result(entries, user_id, user_nickname) + + +class SmotriBroadcastIE(InfoExtractor): + IE_DESC = u'Smotri.com broadcasts' + IE_NAME = u'smotri:broadcast' + _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<broadcastid>[^/]+))/?.*' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + broadcast_id = mobj.group('broadcastid') + + broadcast_url = 'http://' + mobj.group('url') + broadcast_page = self._download_webpage(broadcast_url, broadcast_id, u'Downloading broadcast page') + + if re.search(u'>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None: + raise ExtractorError(u'Broadcast %s does not exist' % broadcast_id, expected=True) + + # Adult content + if re.search(u'EroConfirmText">', broadcast_page) is not None: + + (username, password) = self._get_login_info() + if username is None: + raise ExtractorError(u'Erotic broadcasts allowed only for registered users, ' + u'use --username and --password options to provide account credentials.', expected=True) + + # Log in + login_form_strs = { + u'login-hint53': '1', + u'confirm_erotic': '1', + u'login': username, + u'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_data = compat_urllib_parse.urlencode(login_form).encode('utf-8') + login_url = broadcast_url + '/?no_redirect=1' + request = compat_urllib_request.Request(login_url, login_data) + request.add_header('Content-Type', 'application/x-www-form-urlencoded') + broadcast_page = self._download_webpage( + request, broadcast_id, note=u'Logging in and confirming age') + + if re.search(u'>Неверный логин или пароль<', broadcast_page) is not None: + raise ExtractorError(u'Unable to log in: bad username or password', expected=True) + + adult_content = True + else: + adult_content = False + + ticket = self._html_search_regex( + u'window\.broadcast_control\.addFlashVar\\(\'file\', \'([^\']+)\'\\);', + broadcast_page, u'broadcast ticket') + + url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket + + broadcast_password = self._downloader.params.get('videopassword', None) + if broadcast_password: + url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest() + + broadcast_json_page = self._download_webpage(url, broadcast_id, u'Downloading broadcast JSON') + + try: + broadcast_json = json.loads(broadcast_json_page) + + protected_broadcast = broadcast_json['_pass_protected'] == 1 + if protected_broadcast and not broadcast_password: + raise ExtractorError(u'This broadcast is protected by a password, use the --video-password option', expected=True) + + broadcast_offline = broadcast_json['is_play'] == 0 + if broadcast_offline: + raise ExtractorError(u'Broadcast %s is offline' % broadcast_id, expected=True) + + rtmp_url = broadcast_json['_server'] + if not rtmp_url.startswith('rtmp://'): + raise ExtractorError(u'Unexpected broadcast rtmp URL') + + broadcast_playpath = broadcast_json['_streamName'] + broadcast_thumbnail = broadcast_json['_imgURL'] + broadcast_title = broadcast_json['title'] + broadcast_description = broadcast_json['description'] + broadcaster_nick = broadcast_json['nick'] + broadcaster_login = broadcast_json['login'] + rtmp_conn = 'S:%s' % uuid.uuid4().hex + except KeyError: + if protected_broadcast: + raise ExtractorError(u'Bad broadcast password', expected=True) + raise ExtractorError(u'Unexpected broadcast JSON') + + return { + 'id': broadcast_id, + 'url': rtmp_url, + 'title': broadcast_title, + 'thumbnail': broadcast_thumbnail, + 'description': broadcast_description, + 'uploader': broadcaster_nick, + 'uploader_id': broadcaster_login, + 'age_limit': 18 if adult_content else 0, + 'ext': 'flv', + 'play_path': broadcast_playpath, + 'rtmp_live': True, + 'rtmp_conn': rtmp_conn + } diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 3a19ab172..cb6dedab7 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -25,7 +25,7 @@ class SoundcloudIE(InfoExtractor): _VALID_URL = r'''^(?:https?://)? (?:(?:(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)/?(?:[?].*)?$) |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)) - |(?P<widget>w.soundcloud.com/player/?.*?url=.*) + |(?P<widget>w\.soundcloud\.com/player/?.*?url=.*) ) ''' IE_NAME = u'soundcloud' @@ -217,7 +217,7 @@ class SoundcloudSetIE(SoundcloudIE): class SoundcloudUserIE(SoundcloudIE): - _VALID_URL = r'https?://(www\.)?soundcloud.com/(?P<user>[^/]+)(/?(tracks/)?)?(\?.*)?$' + _VALID_URL = r'https?://(www\.)?soundcloud\.com/(?P<user>[^/]+)(/?(tracks/)?)?(\?.*)?$' IE_NAME = u'soundcloud:user' # it's in tests/test_playlists.py diff --git a/youtube_dl/extractor/southparkstudios.py b/youtube_dl/extractor/southparkstudios.py index a711531e6..fd90cc5dd 100644 --- a/youtube_dl/extractor/southparkstudios.py +++ b/youtube_dl/extractor/southparkstudios.py @@ -1,15 +1,14 @@ import re -from .mtv import MTVIE, _media_xml_tag +from .mtv import MTVServicesInfoExtractor -class SouthParkStudiosIE(MTVIE): +class SouthParkStudiosIE(MTVServicesInfoExtractor): IE_NAME = u'southparkstudios.com' _VALID_URL = r'(https?://)?(www\.)?(?P<url>southparkstudios\.com/(clips|full-episodes)/(?P<id>.+?)(\?|#|$))' _FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss' - # Overwrite MTVIE properties we don't want _TESTS = [{ u'url': u'http://www.southparkstudios.com/clips/104437/bat-daded#tab=featured', u'file': u'a7bff6c2-ed00-11e0-aca6-0026b9414f30.mp4', @@ -19,14 +18,6 @@ class SouthParkStudiosIE(MTVIE): }, }] - def _get_thumbnail_url(self, uri, itemdoc): - search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail')) - thumb_node = itemdoc.find(search_path) - if thumb_node is None: - return None - else: - return thumb_node.attrib['url'] - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) url = u'http://www.' + mobj.group(u'url') diff --git a/youtube_dl/extractor/space.py b/youtube_dl/extractor/space.py index 0d32a0688..11455e0fa 100644 --- a/youtube_dl/extractor/space.py +++ b/youtube_dl/extractor/space.py @@ -6,7 +6,7 @@ from ..utils import RegexNotFoundError, ExtractorError class SpaceIE(InfoExtractor): - _VALID_URL = r'https?://www\.space\.com/\d+-(?P<title>[^/\.\?]*?)-video.html' + _VALID_URL = r'https?://www\.space\.com/\d+-(?P<title>[^/\.\?]*?)-video\.html' _TEST = { u'add_ie': ['Brightcove'], u'url': u'http://www.space.com/23373-huge-martian-landforms-detail-revealed-by-european-probe-video.html', diff --git a/youtube_dl/extractor/stanfordoc.py b/youtube_dl/extractor/stanfordoc.py index b27838bf9..d0d0989f0 100644 --- a/youtube_dl/extractor/stanfordoc.py +++ b/youtube_dl/extractor/stanfordoc.py @@ -1,13 +1,8 @@ import re -import socket -import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( - compat_http_client, compat_str, - compat_urllib_error, - compat_urllib_request, ExtractorError, orderedSet, @@ -18,7 +13,7 @@ from ..utils import ( class StanfordOpenClassroomIE(InfoExtractor): IE_NAME = u'stanfordoc' IE_DESC = u'Stanford Open ClassRoom' - _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$' + _VALID_URL = r'^(?:https?://)?openclassroom\.stanford\.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$' _TEST = { u'url': u'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100', u'file': u'PracticalUnix_intro-environment.mp4', @@ -45,11 +40,7 @@ class StanfordOpenClassroomIE(InfoExtractor): self.report_extraction(info['id']) baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/' xmlUrl = baseUrl + video + '.xml' - try: - metaXml = compat_urllib_request.urlopen(xmlUrl).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err)) - mdoc = xml.etree.ElementTree.fromstring(metaXml) + mdoc = self._download_xml(xmlUrl, info['id']) try: info['title'] = mdoc.findall('./title')[0].text info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text @@ -95,12 +86,9 @@ class StanfordOpenClassroomIE(InfoExtractor): 'upload_date': None, } - self.report_download_webpage(info['id']) rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php' - try: - rootpage = compat_urllib_request.urlopen(rootURL).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to download course info page: ' + compat_str(err)) + rootpage = self._download_webpage(rootURL, info['id'], + errnote=u'Unable to download course info page') info['title'] = info['id'] diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py index 772134a12..2c5c88be8 100644 --- a/youtube_dl/extractor/tf1.py +++ b/youtube_dl/extractor/tf1.py @@ -7,7 +7,7 @@ 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/.*-(.*?)\.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', diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py new file mode 100644 index 000000000..61452e47d --- /dev/null +++ b/youtube_dl/extractor/theplatform.py @@ -0,0 +1,68 @@ +import re +import json + +from .common import InfoExtractor +from ..utils import ( + xpath_with_ns, +) + +_x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language'}) + + +class ThePlatformIE(InfoExtractor): + _VALID_URL = r'(?:https?://link\.theplatform\.com/s/[^/]+/|theplatform:)(?P<id>[^/\?]+)' + + _TEST = { + # from http://www.metacafe.com/watch/cb-e9I_cZgTgIPd/blackberrys_big_bold_z30/ + u'url': u'http://link.theplatform.com/s/dJ5BDC/e9I_cZgTgIPd/meta.smil?format=smil&Tracking=true&mbr=true', + u'info_dict': { + u'id': u'e9I_cZgTgIPd', + u'ext': u'flv', + u'title': u'Blackberry\'s big, bold Z30', + u'description': u'The Z30 is Blackberry\'s biggest, baddest mobile messaging device yet.', + u'duration': 247, + }, + u'params': { + # rtmp download + u'skip_download': True, + }, + } + + def _get_info(self, video_id): + smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?' + 'format=smil&mbr=true'.format(video_id)) + meta = self._download_xml(smil_url, video_id) + info_url = 'http://link.theplatform.com/s/dJ5BDC/{0}?format=preview'.format(video_id) + info_json = self._download_webpage(info_url, video_id) + info = json.loads(info_json) + + head = meta.find(_x('smil:head')) + body = meta.find(_x('smil:body')) + base_url = head.find(_x('smil:meta')).attrib['base'] + switch = body.find(_x('smil:switch')) + formats = [] + for f in switch.findall(_x('smil:video')): + attr = f.attrib + formats.append({ + 'url': base_url, + 'play_path': 'mp4:' + attr['src'], + 'ext': 'flv', + 'width': int(attr['width']), + 'height': int(attr['height']), + 'vbr': int(attr['system-bitrate']), + }) + formats.sort(key=lambda f: (f['height'], f['width'], f['vbr'])) + + return { + 'id': video_id, + 'title': info['title'], + 'formats': formats, + 'description': info['description'], + 'thumbnail': info['defaultThumbnailUrl'], + 'duration': info['duration']//1000, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + return self._get_info(video_id) diff --git a/youtube_dl/extractor/trilulilu.py b/youtube_dl/extractor/trilulilu.py index 1c49e580d..d64aaa41f 100644 --- a/youtube_dl/extractor/trilulilu.py +++ b/youtube_dl/extractor/trilulilu.py @@ -55,7 +55,7 @@ class TriluliluIE(InfoExtractor): for fnode in format_doc.findall('./formats/format') ] - info = { + return { '_type': 'video', 'id': video_id, 'formats': formats, @@ -64,7 +64,3 @@ class TriluliluIE(InfoExtractor): 'thumbnail': thumbnail, } - # TODO: Remove when #980 has been merged - info.update(formats[-1]) - - return info diff --git a/youtube_dl/extractor/unistra.py b/youtube_dl/extractor/unistra.py index 516e18914..474610eec 100644 --- a/youtube_dl/extractor/unistra.py +++ b/youtube_dl/extractor/unistra.py @@ -3,7 +3,7 @@ import re from .common import InfoExtractor class UnistraIE(InfoExtractor): - _VALID_URL = r'http://utv.unistra.fr/(?:index|video).php\?id_video\=(\d+)' + _VALID_URL = r'http://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(\d+)' _TEST = { u'url': u'http://utv.unistra.fr/video.php?id_video=154', diff --git a/youtube_dl/extractor/veehd.py b/youtube_dl/extractor/veehd.py index 3a99a29c6..3cf8c853d 100644 --- a/youtube_dl/extractor/veehd.py +++ b/youtube_dl/extractor/veehd.py @@ -9,7 +9,7 @@ from ..utils import ( ) class VeeHDIE(InfoExtractor): - _VALID_URL = r'https?://veehd.com/video/(?P<id>\d+)' + _VALID_URL = r'https?://veehd\.com/video/(?P<id>\d+)' _TEST = { u'url': u'http://veehd.com/video/4686958', diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py index 4378b1780..4823992ef 100644 --- a/youtube_dl/extractor/vevo.py +++ b/youtube_dl/extractor/vevo.py @@ -15,7 +15,7 @@ class VevoIE(InfoExtractor): Accepts urls from vevo.com or in the format 'vevo:{id}' (currently used by MTVIE) """ - _VALID_URL = r'((http://www.vevo.com/watch/.*?/.*?/)|(vevo:))(?P<id>.*?)(\?|$)' + _VALID_URL = r'((http://www\.vevo\.com/watch/(?:[^/]+/[^/]+/)?)|(vevo:))(?P<id>.*?)(\?|$)' _TESTS = [{ u'url': u'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280', u'file': u'GB1101300280.mp4', @@ -24,7 +24,7 @@ class VevoIE(InfoExtractor): u"upload_date": u"20130624", u"uploader": u"Hurts", u"title": u"Somebody to Die For", - u"duration": 230, + u"duration": 230.12, u"width": 1920, u"height": 1080, } diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py index 6b93afa50..87812d6af 100644 --- a/youtube_dl/extractor/vice.py +++ b/youtube_dl/extractor/vice.py @@ -6,7 +6,7 @@ from ..utils import ExtractorError class ViceIE(InfoExtractor): - _VALID_URL = r'http://www.vice.com/.*?/(?P<name>.+)' + _VALID_URL = r'http://www\.vice\.com/.*?/(?P<name>.+)' _TEST = { u'url': u'http://www.vice.com/Fringes/cowboy-capitalists-part-1', diff --git a/youtube_dl/extractor/viddler.py b/youtube_dl/extractor/viddler.py index 826804af3..9328ef4a2 100644 --- a/youtube_dl/extractor/viddler.py +++ b/youtube_dl/extractor/viddler.py @@ -2,13 +2,10 @@ import json import re from .common import InfoExtractor -from ..utils import ( - determine_ext, -) class ViddlerIE(InfoExtractor): - _VALID_URL = r'(?P<domain>https?://(?:www\.)?viddler.com)/(?:v|embed|player)/(?P<id>[a-z0-9]+)' + _VALID_URL = r'(?P<domain>https?://(?:www\.)?viddler\.com)/(?:v|embed|player)/(?P<id>[a-z0-9]+)' _TEST = { u"url": u"http://www.viddler.com/v/43903784", u'file': u'43903784.mp4', @@ -47,7 +44,7 @@ class ViddlerIE(InfoExtractor): r"thumbnail\s*:\s*'([^']*)'", webpage, u'thumbnail', fatal=False) - info = { + return { '_type': 'video', 'id': video_id, 'title': title, @@ -56,9 +53,3 @@ class ViddlerIE(InfoExtractor): 'duration': duration, 'formats': formats, } - - # TODO: Remove when #980 has been merged - info['formats'][-1]['ext'] = determine_ext(info['formats'][-1]['url']) - info.update(info['formats'][-1]) - - return info diff --git a/youtube_dl/extractor/videofyme.py b/youtube_dl/extractor/videofyme.py index 912802d9a..f75169041 100644 --- a/youtube_dl/extractor/videofyme.py +++ b/youtube_dl/extractor/videofyme.py @@ -7,7 +7,7 @@ from ..utils import ( ) class VideofyMeIE(InfoExtractor): - _VALID_URL = r'https?://(www.videofy.me/.+?|p.videofy.me/v)/(?P<id>\d+)(&|#|$)' + _VALID_URL = r'https?://(www\.videofy\.me/.+?|p\.videofy\.me/v)/(?P<id>\d+)(&|#|$)' IE_NAME = u'videofy.me' _TEST = { diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 7d82c2cfa..fb2bd225a 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -20,7 +20,7 @@ class VimeoIE(InfoExtractor): """Information extractor for vimeo.com.""" # _VALID_URL matches Vimeo URLs - _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|(?P<player>player))\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?(?:#.*)?$' + _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|(?P<player>player))\.)?vimeo(?P<pro>pro)?\.com/(?:.*?/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?(?:#.*)?$' _NETRC_MACHINE = 'vimeo' IE_NAME = u'vimeo' _TESTS = [ @@ -196,6 +196,16 @@ class VimeoIE(InfoExtractor): if mobj is not None: video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3) + try: + view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, u'view count')) + like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, u'like count')) + comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, u'comment count')) + except RegexNotFoundError: + # This info is only available in vimeo.com/{id} urls + view_count = None + like_count = None + comment_count = None + # Vimeo specific: extract request signature and timestamp sig = config['request']['signature'] timestamp = config['request']['timestamp'] @@ -242,6 +252,9 @@ class VimeoIE(InfoExtractor): 'description': video_description, 'formats': formats, 'webpage_url': url, + 'view_count': view_count, + 'like_count': like_count, + 'comment_count': comment_count, } @@ -249,25 +262,77 @@ class VimeoChannelIE(InfoExtractor): IE_NAME = u'vimeo:channel' _VALID_URL = r'(?:https?://)?vimeo.\com/channels/(?P<id>[^/]+)' _MORE_PAGES_INDICATOR = r'<a.+?rel="next"' + _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"' - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - channel_id = mobj.group('id') - video_ids = [] + def _page_url(self, base_url, pagenum): + return '%s/videos/page:%d/' % (base_url, pagenum) + def _extract_list_title(self, webpage): + return self._html_search_regex(self._TITLE_RE, webpage, u'list title') + + def _extract_videos(self, list_id, base_url): + video_ids = [] for pagenum in itertools.count(1): - webpage = self._download_webpage('http://vimeo.com/channels/%s/videos/page:%d' % (channel_id, pagenum), - channel_id, u'Downloading page %s' % pagenum) + webpage = self._download_webpage( + self._page_url(base_url, pagenum) ,list_id, + u'Downloading page %s' % pagenum) video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage)) if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: break entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo') for video_id in video_ids] - channel_title = self._html_search_regex(r'<a href="/channels/%s">(.*?)</a>' % channel_id, - webpage, u'channel title') return {'_type': 'playlist', - 'id': channel_id, - 'title': channel_title, + 'id': list_id, + 'title': self._extract_list_title(webpage), 'entries': entries, } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + channel_id = mobj.group('id') + return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id) + + +class VimeoUserIE(VimeoChannelIE): + IE_NAME = u'vimeo:user' + _VALID_URL = r'(?:https?://)?vimeo.\com/(?P<name>[^/]+)' + _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>' + + @classmethod + def suitable(cls, url): + if VimeoChannelIE.suitable(url) or VimeoIE.suitable(url) or VimeoAlbumIE.suitable(url) or VimeoGroupsIE.suitable(url): + return False + return super(VimeoUserIE, cls).suitable(url) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + name = mobj.group('name') + return self._extract_videos(name, 'http://vimeo.com/%s' % name) + + +class VimeoAlbumIE(VimeoChannelIE): + IE_NAME = u'vimeo:album' + _VALID_URL = r'(?:https?://)?vimeo.\com/album/(?P<id>\d+)' + _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>' + + def _page_url(self, base_url, pagenum): + return '%s/page:%d/' % (base_url, pagenum) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + album_id = mobj.group('id') + return self._extract_videos(album_id, 'http://vimeo.com/album/%s' % album_id) + + +class VimeoGroupsIE(VimeoAlbumIE): + IE_NAME = u'vimeo:group' + _VALID_URL = r'(?:https?://)?vimeo.\com/groups/(?P<name>[^/]+)' + + def _extract_list_title(self, webpage): + return self._og_search_title(webpage) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + name = mobj.group('name') + return self._extract_videos(name, 'http://vimeo.com/groups/%s' % name) diff --git a/youtube_dl/extractor/wat.py b/youtube_dl/extractor/wat.py index 29c25f0e3..4fab6c6e8 100644 --- a/youtube_dl/extractor/wat.py +++ b/youtube_dl/extractor/wat.py @@ -11,7 +11,7 @@ from ..utils import ( 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', diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index b9c3b13f9..3635691e7 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -11,7 +11,8 @@ class WimpIE(InfoExtractor): u'file': u'deerfence.flv', u'md5': u'8b215e2e0168c6081a1cf84b2846a2b5', u'info_dict': { - u"title": u"Watch Till End: Herd of deer jump over a fence." + u"title": u"Watch Till End: Herd of deer jump over a fence.", + u"description": u"These deer look as fluid as running water when they jump over this fence as a herd. This video is one that needs to be watched until the very end for the true majesty to be witnessed, but once it comes, it's sure to take your breath away.", } } @@ -19,18 +20,15 @@ class WimpIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group(1) webpage = self._download_webpage(url, video_id) - title = self._search_regex(r'<meta name="description" content="(.+?)" />',webpage, 'video title') - thumbnail_url = self._search_regex(r'<meta property="og\:image" content="(.+?)" />', webpage,'video thumbnail') + title = self._html_search_meta('description', webpage, u'video title') googleString = self._search_regex("googleCode = '(.*?)'", webpage, 'file url') googleString = base64.b64decode(googleString).decode('ascii') final_url = self._search_regex('","(.*?)"', googleString,'final video url') - ext = final_url.rpartition(u'.')[2] - - return [{ - 'id': video_id, - 'url': final_url, - 'ext': ext, - 'title': title, - 'thumbnail': thumbnail_url, - }] + return { + 'id': video_id, + 'url': final_url, + 'title': self._og_search_title(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + 'description': self._og_search_description(webpage), + } diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py new file mode 100644 index 000000000..e1748c261 --- /dev/null +++ b/youtube_dl/extractor/wistia.py @@ -0,0 +1,55 @@ +import json +import re + +from .common import InfoExtractor + + +class WistiaIE(InfoExtractor): + _VALID_URL = r'^https?://(?:fast\.)?wistia\.net/embed/iframe/(?P<id>[a-z0-9]+)' + + _TEST = { + u"url": u"http://fast.wistia.net/embed/iframe/sh7fpupwlt", + u"file": u"sh7fpupwlt.mov", + u"md5": u"cafeb56ec0c53c18c97405eecb3133df", + u"info_dict": { + u"title": u"cfh_resourceful_zdkh_final_1" + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + data_json = self._html_search_regex( + r'Wistia.iframeInit\((.*?), {}\);', webpage, u'video data') + + data = json.loads(data_json) + + formats = [] + thumbnails = [] + for atype, a in data['assets'].items(): + if atype == 'still': + thumbnails.append({ + 'url': a['url'], + 'resolution': '%dx%d' % (a['width'], a['height']), + }) + continue + if atype == 'preview': + continue + formats.append({ + 'format_id': atype, + 'url': a['url'], + 'width': a['width'], + 'height': a['height'], + 'filesize': a['size'], + 'ext': a['ext'], + }) + formats.sort(key=lambda a: a['filesize']) + + return { + 'id': video_id, + 'title': data['name'], + 'formats': formats, + 'thumbnails': thumbnails, + } diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 7444d3393..ef9997ee4 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -46,7 +46,7 @@ class XHamsterIE(InfoExtractor): return mobj.group('server')+'/key='+mobj.group('file') def is_hd(webpage): - return webpage.find('<div class=\'icon iconHD\'>') != -1 + return webpage.find('<div class=\'icon iconHD\'') != -1 mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index e457c4707..5c9c361b9 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -47,7 +47,7 @@ class YahooIE(InfoExtractor): # The 'meta' field is not always in the video webpage, we request it # from another page long_id = info['id'] - return self._get_info(info['id'], video_id) + return self._get_info(long_id, video_id) def _get_info(self, long_id, video_id): query = ('SELECT * FROM yahoo.media.video.streams WHERE id="%s"' diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py index 1fcc518ac..e971b5b4b 100644 --- a/youtube_dl/extractor/youjizz.py +++ b/youtube_dl/extractor/youjizz.py @@ -7,7 +7,7 @@ from ..utils import ( class YouJizzIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$' + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$' _TEST = { u'url': u'http://www.youjizz.com/videos/zeichentrick-1-2189178.html', u'file': u'2189178.flv', diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index a1a4d896d..874429b78 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -7,7 +7,6 @@ import itertools import json import os.path import re -import socket import string import struct import traceback @@ -17,9 +16,7 @@ from .common import InfoExtractor, SearchInfoExtractor from .subtitles import SubtitlesInfoExtractor from ..utils import ( compat_chr, - compat_http_client, compat_parse_qs, - compat_urllib_error, compat_urllib_parse, compat_urllib_request, compat_urlparse, @@ -45,19 +42,11 @@ class YoutubeBaseInfoExtractor(InfoExtractor): # If True it will raise an error if no login info is provided _LOGIN_REQUIRED = False - def report_lang(self): - """Report attempt to set language.""" - self.to_screen(u'Setting language') - def _set_language(self): - request = compat_urllib_request.Request(self._LANG_URL) - try: - self.report_lang() - compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.report_warning(u'unable to set language: %s' % compat_str(err)) - return False - return True + return bool(self._download_webpage( + self._LANG_URL, None, + note=u'Setting language', errnote='unable to set language', + fatal=False)) def _login(self): (username, password) = self._get_login_info() @@ -67,12 +56,12 @@ class YoutubeBaseInfoExtractor(InfoExtractor): raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True) return False - request = compat_urllib_request.Request(self._LOGIN_URL) - try: - login_page = compat_urllib_request.urlopen(request).read().decode('utf-8') - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.report_warning(u'unable to fetch login page: %s' % compat_str(err)) - return False + login_page = self._download_webpage( + self._LOGIN_URL, None, + note=u'Downloading login page', + errnote=u'unable to fetch login page', fatal=False) + if login_page is False: + return galx = self._search_regex(r'(?s)<input.+?name="GALX".+?value="(.+?)"', login_page, u'Login GALX parameter') @@ -102,29 +91,28 @@ class YoutubeBaseInfoExtractor(InfoExtractor): # chokes on unicode 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('ascii') - request = compat_urllib_request.Request(self._LOGIN_URL, login_data) - try: - self.report_login() - login_results = compat_urllib_request.urlopen(request).read().decode('utf-8') - if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None: - self._downloader.report_warning(u'unable to log in: bad username or password') - return False - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.report_warning(u'unable to log in: %s' % compat_str(err)) + + req = compat_urllib_request.Request(self._LOGIN_URL, login_data) + login_results = self._download_webpage( + req, None, + note=u'Logging in', errnote=u'unable to log in', fatal=False) + if login_results is False: + return False + if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None: + self._downloader.report_warning(u'unable to log in: bad username or password') return False return True def _confirm_age(self): age_form = { - 'next_url': '/', - 'action_confirm': 'Confirm', - } - request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form)) - try: - self.report_age_confirmation() - compat_urllib_request.urlopen(request).read().decode('utf-8') - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err)) + 'next_url': '/', + 'action_confirm': 'Confirm', + } + req = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form)) + + self._download_webpage( + req, None, + note=u'Confirming age', errnote=u'Unable to confirm age') return True def _real_initialize(self): @@ -336,7 +324,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): u"uploader": u"Philipp Hagemeister", u"uploader_id": u"phihag", u"upload_date": u"20121002", - u"description": u"test chars: \"'/\\ä↭𝕐\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de ." + u"description": u"test chars: \"'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de ." } }, { @@ -388,10 +376,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): super(YoutubeIE, self).__init__(*args, **kwargs) self._player_cache = {} - def report_video_webpage_download(self, video_id): - """Report attempt to download video webpage.""" - self.to_screen(u'%s: Downloading video webpage' % video_id) - def report_video_info_webpage_download(self, video_id): """Report attempt to download video info webpage.""" self.to_screen(u'%s: Downloading video info webpage' % video_id) @@ -1258,15 +1242,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): video_id = self._extract_id(url) # Get video webpage - self.report_video_webpage_download(video_id) url = 'https://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id - request = compat_urllib_request.Request(url) - try: - video_webpage_bytes = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to download video webpage: %s' % compat_str(err)) - - video_webpage = video_webpage_bytes.decode('utf-8', 'ignore') + video_webpage = self._download_webpage(url, video_id) # Attempt to extract SWF player URL mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) @@ -1366,6 +1343,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): # description video_description = get_element_by_id("eow-description", video_webpage) if video_description: + video_description = re.sub(r'''(?x) + <a\s+ + (?:[a-zA-Z-]+="[^"]+"\s+)*? + title="([^"]+)"\s+ + (?:[a-zA-Z-]+="[^"]+"\s+)*? + class="yt-uix-redirect-link"\s*> + [^<]+ + </a> + ''', r'\1', video_description) video_description = clean_html(video_description) else: fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage) @@ -1374,6 +1360,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): else: video_description = u'' + def _extract_count(klass): + count = self._search_regex(r'class="%s">([\d,]+)</span>' % re.escape(klass), video_webpage, klass, fatal=False) + if count is not None: + return int(count.replace(',', '')) + return None + like_count = _extract_count(u'likes-count') + dislike_count = _extract_count(u'dislikes-count') + # subtitles video_subtitles = self.extract_subtitles(video_id, video_webpage) @@ -1506,6 +1500,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'annotations': video_annotations, 'webpage_url': 'https://www.youtube.com/watch?v=%s' % video_id, 'view_count': view_count, + 'like_count': like_count, + 'dislike_count': dislike_count, }) return results @@ -1520,10 +1516,10 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): \? (?:.*?&)*? (?:p|a|list)= | p/ ) - ((?:PL|EC|UU|FL)?[0-9A-Za-z-_]{10,}) + ((?:PL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,}) .* | - ((?:PL|EC|UU|FL)[0-9A-Za-z-_]{10,}) + ((?:PL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,}) )""" _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&page=%s' _MORE_PAGES_INDICATOR = r'data-link-type="next"' @@ -1545,7 +1541,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): def _extract_mix(self, playlist_id): # The mixes are generated from a a single video # the id of the playlist is just 'RD' + video_id - url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[2:], playlist_id) + url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id) webpage = self._download_webpage(url, playlist_id, u'Downloading Youtube mix') title_span = (get_element_by_attribute('class', 'title long-title', webpage) or get_element_by_attribute('class', 'title ', webpage)) @@ -1573,7 +1569,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): else: self.to_screen(u'Downloading playlist PL%s - add --no-playlist to just download video %s' % (playlist_id, video_id)) - if len(playlist_id) == 13: # 'RD' + 11 characters for the video id + if playlist_id.startswith('RD'): # Mixes require a custom extraction process return self._extract_mix(playlist_id) if playlist_id.startswith('TL'): @@ -1658,10 +1654,11 @@ class YoutubeChannelIE(InfoExtractor): video_ids = [] url = 'https://www.youtube.com/channel/%s/videos' % channel_id channel_page = self._download_webpage(url, channel_id) - if re.search(r'channel-header-autogenerated-label', channel_page) is not None: - autogenerated = True - else: - autogenerated = False + autogenerated = re.search(r'''(?x) + class="[^"]*?(?: + channel-header-autogenerated-label| + yt-channel-title-autogenerated + )[^"]*"''', channel_page) is not None if autogenerated: # The videos are contained in a single page @@ -1763,10 +1760,6 @@ class YoutubeSearchIE(SearchInfoExtractor): IE_NAME = u'youtube:search' _SEARCH_KEY = 'ytsearch' - def report_download_page(self, query, pagenum): - """Report attempt to download search page with given number.""" - self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) - def _get_n_results(self, query, n): """Get a specified number of results for a query""" @@ -1775,16 +1768,15 @@ class YoutubeSearchIE(SearchInfoExtractor): limit = n while (50 * pagenum) < limit: - self.report_download_page(query, pagenum+1) result_url = self._API_URL % (compat_urllib_parse.quote_plus(query), (50*pagenum)+1) - request = compat_urllib_request.Request(result_url) - try: - data = compat_urllib_request.urlopen(request).read().decode('utf-8') - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to download API page: %s' % compat_str(err)) - api_response = json.loads(data)['data'] - - if not 'items' in api_response: + data_json = self._download_webpage( + result_url, video_id=u'query "%s"' % query, + note=u'Downloading page %s' % (pagenum + 1), + errnote=u'Unable to download API page') + data = json.loads(data_json) + api_response = data['data'] + + if 'items' not in api_response: raise ExtractorError(u'[youtube] No video results') new_ids = list(video['id'] for video in api_response['items']) @@ -1800,6 +1792,7 @@ class YoutubeSearchIE(SearchInfoExtractor): return self.playlist_result(videos, query) class YoutubeSearchDateIE(YoutubeSearchIE): + IE_NAME = YoutubeSearchIE.IE_NAME + ':date' _API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc&orderby=published' _SEARCH_KEY = 'ytsearchdate' IE_DESC = u'YouTube.com searches, newest videos first' |