diff options
Diffstat (limited to 'youtube_dl/extractor')
29 files changed, 1009 insertions, 195 deletions
diff --git a/youtube_dl/extractor/AddAnime.py b/youtube_dl/extractor/AddAnime.py deleted file mode 100644 index a312fa97e..000000000 --- a/youtube_dl/extractor/AddAnime.py +++ /dev/null @@ -1,51 +0,0 @@ -import re - -from .common import InfoExtractor - -class AddAnimeIE(InfoExtractor): - - _VALID_URL = r'^(?:http?://)?(?:\w+\.)?add-anime\.net/watch_video.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)' - IE_NAME = u'AddAnime' - _TEST = { - u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9', - u'file': u'137499050692ced.flv', - u'md5': u'0813c2430bea7a46bf13acf3406992f4', - u'info_dict': { - u"description": u"One Piece 606", - u"title": u"One Piece 606" - } - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - - video_id = mobj.group('video_id') - - webpage = self._download_webpage(url, video_id) - - - def find_between( webpage, first, last ): - try: - start = webpage.index( first ) + len( first ) - end = webpage.index( last, start ) - return webpage[start:end] - except ValueError: - return "" - - video_url = find_between( webpage, "var normal_video_file = '", "';" ) - - video_title = self._og_search_title(webpage) - - video_description = self._og_search_description(webpage) - - info = { - 'id': video_id, - 'url': video_url, - 'ext': 'flv', - 'title': video_title, - 'description': video_description - } - - return [info] diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 28dcb2cc4..c76b99a81 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -1,5 +1,5 @@ - -from .AddAnime import AddAnimeIE +from .appletrailers import AppleTrailersIE +from .addanime import AddAnimeIE from .archiveorg import ArchiveOrgIE from .ard import ARDIE from .arte import ArteTvIE @@ -8,7 +8,10 @@ from .bandcamp import BandcampIE from .bliptv import BlipTVIE, BlipTVUserIE from .breakcom import BreakIE from .brightcove import BrightcoveIE +from .c56 import C56IE from .canalplus import CanalplusIE +from .canalc2 import Canalc2IE +from .cnn import CNNIE from .collegehumor import CollegeHumorIE from .comedycentral import ComedyCentralIE from .condenast import CondeNastIE @@ -31,6 +34,7 @@ from .gametrailers import GametrailersIE from .generic import GenericIE from .googleplus import GooglePlusIE from .googlesearch import GoogleSearchIE +from .hark import HarkIE from .hotnewhiphop import HotNewHipHopIE from .howcast import HowcastIE from .hypem import HypemIE @@ -38,6 +42,7 @@ from .ign import IGNIE, OneUPIE from .ina import InaIE from .infoq import InfoQIE from .instagram import InstagramIE +from .jeuxvideo import JeuxVideoIE from .jukebox import JukeboxIE from .justintv import JustinTVIE from .kankan import KankanIE @@ -51,14 +56,19 @@ from .muzu import MuzuTVIE from .myspass import MySpassIE from .myvideo import MyVideoIE from .nba import NBAIE +from .nbc import NBCNewsIE from .ooyala import OoyalaIE +from .pbs import PBSIE from .photobucket import PhotobucketIE from .pornotube import PornotubeIE from .rbmaradio import RBMARadioIE from .redtube import RedTubeIE from .ringtv import RingTVIE +from .ro220 import Ro220IE from .roxwel import RoxwelIE +from .rtlnow import RTLnowIE from .sina import SinaIE +from .slashdot import SlashdotIE from .soundcloud import SoundcloudIE, SoundcloudSetIE from .spiegel import SpiegelIE from .stanfordoc import StanfordOpenClassroomIE @@ -69,9 +79,11 @@ from .ted import TEDIE from .tf1 import TF1IE from .thisav import ThisAVIE from .traileraddict import TrailerAddictIE +from .trilulilu import TriluliluIE from .tudou import TudouIE from .tumblr import TumblrIE from .tutv import TutvIE +from .unistra import UnistraIE from .ustream import UstreamIE from .vbox7 import Vbox7IE from .veoh import VeohIE @@ -79,7 +91,6 @@ from .vevo import VevoIE from .videofyme import VideofyMeIE from .vimeo import VimeoIE, VimeoChannelIE from .vine import VineIE -from .c56 import C56IE from .wat import WatIE from .weibo import WeiboIE from .wimp import WimpIE @@ -113,12 +124,14 @@ _ALL_CLASSES = [ ] _ALL_CLASSES.append(GenericIE) + def gen_extractors(): """ Return a list of an instance of every supported extractor. The order does matter; the first extractor matched is the one handling the URL. """ return [klass() for klass in _ALL_CLASSES] + def get_info_extractor(ie_name): """Returns the info extractor class with the given ie_name""" return globals()[ie_name+'IE'] diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py new file mode 100644 index 000000000..b3bdb2955 --- /dev/null +++ b/youtube_dl/extractor/appletrailers.py @@ -0,0 +1,167 @@ +import re +import xml.etree.ElementTree + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + ExtractorError, +) + + +class AppleTrailersIE(InfoExtractor): + _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": [ + { + u"file": u"manofsteel-trailer4.mov", + u"md5": u"11874af099d480cc09e103b189805d5f", + u"info_dict": { + u"duration": 111, + u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_11624.jpg", + u"title": u"Trailer 4", + u"upload_date": u"20130523", + u"uploader_id": u"wb", + }, + }, + { + u"file": u"manofsteel-trailer3.mov", + u"md5": u"07a0a262aae5afe68120eed61137ab34", + u"info_dict": { + u"duration": 182, + u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_10793.jpg", + u"title": u"Trailer 3", + u"upload_date": u"20130417", + u"uploader_id": u"wb", + }, + }, + { + u"file": u"manofsteel-trailer.mov", + u"md5": u"e401fde0813008e3307e54b6f384cff1", + u"info_dict": { + u"duration": 148, + u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_8703.jpg", + u"title": u"Trailer", + u"upload_date": u"20121212", + u"uploader_id": u"wb", + }, + }, + { + u"file": u"manofsteel-teaser.mov", + u"md5": u"76b392f2ae9e7c98b22913c10a639c97", + u"info_dict": { + u"duration": 93, + u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_6899.jpg", + u"title": u"Teaser", + u"upload_date": u"20120721", + u"uploader_id": u"wb", + }, + } + ] + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + movie = mobj.group('movie') + uploader_id = mobj.group('company') + + playlist_url = url.partition(u'?')[0] + u'/includes/playlists/web.inc' + playlist_snippet = self._download_webpage(playlist_url, movie) + playlist_cleaned = re.sub(r'(?s)<script>.*?</script>', u'', playlist_snippet) + playlist_html = u'<html>' + playlist_cleaned + u'</html>' + + size_cache = {} + + doc = xml.etree.ElementTree.fromstring(playlist_html) + playlist = [] + for li in doc.findall('./div/ul/li'): + title = li.find('.//h3').text + video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower() + thumbnail = li.find('.//img').attrib['src'] + + date_el = li.find('.//p') + upload_date = None + m = re.search(r':\s?(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<year>[0-9]{2})', date_el.text) + if m: + upload_date = u'20' + m.group('year') + m.group('month') + m.group('day') + runtime_el = date_el.find('./br') + m = re.search(r':\s?(?P<minutes>[0-9]+):(?P<seconds>[0-9]{1,2})', runtime_el.tail) + duration = None + if m: + duration = 60 * int(m.group('minutes')) + int(m.group('seconds')) + + formats = [] + for formats_el in li.findall('.//a'): + if formats_el.attrib['class'] != 'OverlayPanel': + continue + target = formats_el.attrib['target'] + + format_code = formats_el.text + if 'Automatic' in format_code: + continue + + size_q = formats_el.attrib['href'] + size_id = size_q.rpartition('#videos-')[2] + if size_id not in size_cache: + size_url = url + size_q + sizepage_html = self._download_webpage( + size_url, movie, + note=u'Downloading size info %s' % size_id, + errnote=u'Error while downloading size info %s' % size_id, + ) + _doc = xml.etree.ElementTree.fromstring(sizepage_html) + size_cache[size_id] = _doc + + sizepage_doc = size_cache[size_id] + links = sizepage_doc.findall('.//{http://www.w3.org/1999/xhtml}ul/{http://www.w3.org/1999/xhtml}li/{http://www.w3.org/1999/xhtml}a') + for vid_a in links: + href = vid_a.get('href') + if not href.endswith(target): + continue + detail_q = href.partition('#')[0] + detail_url = url + '/' + detail_q + + m = re.match(r'includes/(?P<detail_id>[^/]+)/', detail_q) + detail_id = m.group('detail_id') + + detail_html = self._download_webpage( + detail_url, movie, + note=u'Downloading detail %s %s' % (detail_id, size_id), + errnote=u'Error while downloading detail %s %s' % (detail_id, size_id) + ) + detail_doc = xml.etree.ElementTree.fromstring(detail_html) + movie_link_el = detail_doc.find('.//{http://www.w3.org/1999/xhtml}a') + assert movie_link_el.get('class') == 'movieLink' + movie_link = movie_link_el.get('href').partition('?')[0].replace('_', '_h') + ext = determine_ext(movie_link) + assert ext == 'mov' + + formats.append({ + 'format': format_code, + 'ext': ext, + 'url': movie_link, + }) + + info = { + '_type': 'video', + 'id': video_id, + 'title': title, + 'formats': formats, + 'title': title, + 'duration': duration, + 'thumbnail': thumbnail, + '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', + 'id': movie, + 'entries': playlist, + } diff --git a/youtube_dl/extractor/c56.py b/youtube_dl/extractor/c56.py index 4c8a8af09..dc3a8d47d 100644 --- a/youtube_dl/extractor/c56.py +++ b/youtube_dl/extractor/c56.py @@ -12,8 +12,8 @@ class C56IE(InfoExtractor): _TEST ={ u'url': u'http://www.56.com/u39/v_OTM0NDA3MTY.html', - u'file': u'93440716.mp4', - u'md5': u'9dc07b5c8e978112a6441f9e75d2b59e', + u'file': u'93440716.flv', + u'md5': u'e59995ac63d0457783ea05f93f12a866', u'info_dict': { u'title': u'网事知多少 第32期：车怒', }, diff --git a/youtube_dl/extractor/canalc2.py b/youtube_dl/extractor/canalc2.py new file mode 100644 index 000000000..50832217a --- /dev/null +++ b/youtube_dl/extractor/canalc2.py @@ -0,0 +1,35 @@ +# coding: utf-8 +import re + +from .common import InfoExtractor + + +class Canalc2IE(InfoExtractor): + _IE_NAME = 'canalc2.tv' + _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?idVideo=(\d+)&voir=oui' + + _TEST = { + u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui', + u'file': u'12163.mp4', + u'md5': u'060158428b650f896c542dfbb3d6487f', + u'info_dict': { + u'title': u'Terrasses du Numérique' + } + } + + def _real_extract(self, url): + video_id = re.match(self._VALID_URL, url).group(1) + webpage = self._download_webpage(url, video_id) + file_name = self._search_regex( + r"so\.addVariable\('file','(.*?)'\);", + webpage, 'file name') + video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name + + title = self._html_search_regex( + r'class="evenement8">(.*?)</a>', webpage, u'title') + + return {'id': video_id, + 'ext': 'mp4', + 'url': video_url, + 'title': title, + } diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py index 3b1c88876..1f02519a0 100644 --- a/youtube_dl/extractor/canalplus.py +++ b/youtube_dl/extractor/canalplus.py @@ -5,7 +5,7 @@ from .common import InfoExtractor from ..utils import unified_strdate class CanalplusIE(InfoExtractor): - _VALID_URL = r'https?://www\.canalplus\.fr/.*?\?vid=(?P<id>\d+)' + _VALID_URL = r'https?://(www\.canalplus\.fr/.*?\?vid=|player\.canalplus\.fr/#/)(?P<id>\d+)' _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s' IE_NAME = u'canalplus.fr' diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py new file mode 100644 index 000000000..4338bd180 --- /dev/null +++ b/youtube_dl/extractor/cnn.py @@ -0,0 +1,59 @@ +import re +import xml.etree.ElementTree + +from .common import InfoExtractor +from ..utils import determine_ext + + +class CNNIE(InfoExtractor): + _VALID_URL = r'''(?x)https?://(edition\.)?cnn\.com/video/(data/.+?|\?)/ + (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))''' + + _TESTS = [{ + u'url': u'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn', + u'file': u'sports_2013_06_09_nadal-1-on-1.cnn.mp4', + u'md5': u'3e6121ea48df7e2259fe73a0628605c4', + u'info_dict': { + u'title': u'Nadal wins 8th French Open title', + u'description': u'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.', + }, + }, + { + u"url": u"http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29", + u"file": u"us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4", + u"md5": u"b5cc60c60a3477d185af8f19a2a26f4e", + u"info_dict": { + u"title": "Student's epic speech stuns new freshmen", + u"description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"" + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + path = mobj.group('path') + page_title = mobj.group('title') + info_url = u'http://cnn.com/video/data/3.0/%s/index.xml' % path + print(info_url) + info_xml = self._download_webpage(info_url, page_title) + info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')) + + formats = [] + for f in info.findall('files/file'): + mf = re.match(r'(\d+)x(\d+)(?:_(.*)k)?',f.attrib['bitrate']) + if mf is not None: + formats.append((int(mf.group(1)), int(mf.group(2)), int(mf.group(3) or 0), f.text)) + formats = sorted(formats) + (_,_,_, video_path) = formats[-1] + video_url = 'http://ht.cdn.turner.com/cnn/big%s' % video_path + + thumbnails = sorted([((int(t.attrib['height']),int(t.attrib['width'])), t.text) for t in info.findall('images/image')]) + thumbs_dict = [{'resolution': res, 'url': t_url} for (res, t_url) in thumbnails] + + return {'id': info.attrib['id'], + 'title': info.find('headline').text, + 'url': video_url, + 'ext': determine_ext(video_url), + 'thumbnail': thumbnails[-1][1], + 'thumbnails': thumbs_dict, + 'description': info.find('description').text, + } diff --git a/youtube_dl/extractor/collegehumor.py b/youtube_dl/extractor/collegehumor.py index 30b9c7549..8d4c93d6d 100644 --- a/youtube_dl/extractor/collegehumor.py +++ b/youtube_dl/extractor/collegehumor.py @@ -4,6 +4,7 @@ import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( compat_urllib_parse_urlparse, + determine_ext, ExtractorError, ) @@ -12,7 +13,7 @@ from ..utils import ( class CollegeHumorIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$' - _TEST = { + _TESTS = [{ u'url': u'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe', u'file': u'6902724.mp4', u'md5': u'1264c12ad95dca142a9f0bf7968105a0', @@ -20,7 +21,16 @@ class CollegeHumorIE(InfoExtractor): u'title': u'Comic-Con Cosplay Catastrophe', u'description': u'Fans get creative this year at San Diego. Too creative. And yes, that\'s really Joss Whedon.', }, - } + }, + { + u'url': u'http://www.collegehumor.com/video/3505939/font-conference', + u'file': u'3505939.mp4', + u'md5': u'c51ca16b82bb456a4397987791a835f5', + u'info_dict': { + u'title': u'Font Conference', + u'description': u'This video wasn\'t long enough, so we made it double-spaced.', + }, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -49,25 +59,29 @@ class CollegeHumorIE(InfoExtractor): info['description'] = videoNode.findall('./description')[0].text info['title'] = videoNode.findall('./caption')[0].text info['thumbnail'] = videoNode.findall('./thumbnail')[0].text - manifest_url = videoNode.findall('./file')[0].text + next_url = videoNode.findall('./file')[0].text except IndexError: raise ExtractorError(u'Invalid metadata XML file') - manifest_url += '?hdcore=2.10.3' - manifestXml = self._download_webpage(manifest_url, video_id, - u'Downloading XML manifest', - u'Unable to download video info XML') - - adoc = xml.etree.ElementTree.fromstring(manifestXml) - try: - media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0] - node_id = media_node.attrib['url'] - video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text - except IndexError as err: - raise ExtractorError(u'Invalid manifest file') + if next_url.endswith(u'manifest.f4m'): + manifest_url = next_url + '?hdcore=2.10.3' + manifestXml = self._download_webpage(manifest_url, video_id, + u'Downloading XML manifest', + u'Unable to download video info XML') - url_pr = compat_urllib_parse_urlparse(info['thumbnail']) + adoc = xml.etree.ElementTree.fromstring(manifestXml) + try: + media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0] + node_id = media_node.attrib['url'] + video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text + except IndexError as err: + raise ExtractorError(u'Invalid manifest file') + url_pr = compat_urllib_parse_urlparse(info['thumbnail']) + info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','') + info['ext'] = 'mp4' + else: + # Old-style direct links + info['url'] = next_url + info['ext'] = determine_ext(info['url']) - info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','') - info['ext'] = 'mp4' - return [info] + return info diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index da50abfc1..12169b2bb 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -47,7 +47,8 @@ class InfoExtractor(object): uploader_id: Nickname or id of the video uploader. location: Physical location of the video. player_url: SWF Player URL (used for rtmpdump). - subtitles: The subtitle file contents. + 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. urlhandle: [internal] The urlHandle to be used to download the file, like returned by urllib.request.urlopen @@ -77,7 +78,13 @@ class InfoExtractor(object): @classmethod def suitable(cls, url): """Receives a URL and returns True if suitable for this IE.""" - return re.match(cls._VALID_URL, url) is not None + + # This does not use has/getattr intentionally - we want to know whether + # we have cached the regexp for *this* class, whereas getattr would also + # match the superclass + if '_VALID_URL_RE' not in cls.__dict__: + cls._VALID_URL_RE = re.compile(cls._VALID_URL) + return cls._VALID_URL_RE.match(url) is not None @classmethod def working(cls): @@ -122,7 +129,7 @@ class InfoExtractor(object): 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]) + raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2], cause=err) def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None): """ Returns a tuple (page content as string, URL handle) """ diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index fa8c630d0..1ea449ca8 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -21,7 +21,7 @@ class DailymotionIE(InfoExtractor): u'file': u'x33vw9.mp4', u'md5': u'392c4b85a60a90dc4792da41ce3144eb', u'info_dict': { - u"uploader": u"Alex and Van .", + u"uploader": u"Amphora Alex and Van .", u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\"" } } diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py index 67a7e5f76..4508f0dfa 100644 --- a/youtube_dl/extractor/funnyordie.py +++ b/youtube_dl/extractor/funnyordie.py @@ -21,17 +21,14 @@ class FunnyOrDieIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - video_url = self._html_search_regex(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"', + video_url = self._search_regex(r'type: "video/mp4", src: "(.*?)"', webpage, u'video URL', flags=re.DOTALL) - title = self._html_search_regex((r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>", - r'<title>(?P<title>[^<]+?)</title>'), webpage, 'title', flags=re.DOTALL) - info = { 'id': video_id, 'url': video_url, 'ext': 'mp4', - 'title': title, + 'title': self._og_search_title(webpage), 'description': self._og_search_description(webpage), } return [info] diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index b633e896c..d034a11bb 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -7,12 +7,14 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_error, compat_urllib_parse, + compat_urllib_parse_urlparse, compat_urllib_request, ExtractorError, ) from .brightcove import BrightcoveIE + class GenericIE(InfoExtractor): IE_DESC = u'Generic downloader that works on some sites' _VALID_URL = r'.*' @@ -23,7 +25,7 @@ class GenericIE(InfoExtractor): u'file': u'13601338388002.mp4', u'md5': u'85b90ccc9d73b4acd9138d3af4c27f89', u'info_dict': { - u"uploader": u"www.hodiho.fr", + u"uploader": u"www.hodiho.fr", u"title": u"R\u00e9gis plante sa Jeep" } }, @@ -107,8 +109,13 @@ class GenericIE(InfoExtractor): return new_url def _real_extract(self, url): - new_url = self._test_redirect(url) - if new_url: return [self.url_result(new_url)] + try: + new_url = self._test_redirect(url) + if new_url: + return [self.url_result(new_url)] + except compat_urllib_error.HTTPError: + # This may be a stupid server that doesn't like HEAD, our UA, or so + pass video_id = url.split('/')[-1] try: @@ -119,7 +126,7 @@ class GenericIE(InfoExtractor): raise ExtractorError(u'Invalid URL: %s' % url) self.report_extraction(video_id) - # Look for BrigthCove: + # Look for BrightCove: m_brightcove = re.search(r'<object.+?class=([\'"]).*?BrightcoveExperience.*?\1.+?</object>', webpage, re.DOTALL) if m_brightcove is not None: self.to_screen(u'Brightcove video detected.') @@ -145,6 +152,9 @@ class GenericIE(InfoExtractor): if m_video_type is not None: mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage) if mobj is None: + # HTML5 video + mobj = re.search(r'<video[^<]*>.*?<source .*?src="([^"]+)"', webpage, flags=re.DOTALL) + if mobj is None: raise ExtractorError(u'Invalid URL: %s' % url) # It's possible that one of the regexes @@ -153,6 +163,10 @@ class GenericIE(InfoExtractor): raise ExtractorError(u'Invalid URL: %s' % url) video_url = compat_urllib_parse.unquote(mobj.group(1)) + if video_url.startswith('//'): + video_url = compat_urllib_parse_urlparse(url).scheme + ':' + video_url + if '://' not in video_url: + video_url = url + ('' if url.endswith('/') else '/') + video_url video_id = os.path.basename(video_url) # here's a fun little line of code for you: diff --git a/youtube_dl/extractor/googleplus.py b/youtube_dl/extractor/googleplus.py index 9f7fc19a4..f1cd88983 100644 --- a/youtube_dl/extractor/googleplus.py +++ b/youtube_dl/extractor/googleplus.py @@ -57,8 +57,8 @@ class GooglePlusIE(InfoExtractor): webpage, 'title', default=u'NA') # Step 2, Simulate clicking the image box to launch video - DOMAIN = 'https://plus.google.com' - video_page = self._search_regex(r'<a href="((?:%s)?/photos/.*?)"' % re.escape(DOMAIN), + DOMAIN = 'https://plus.google.com/' + video_page = self._search_regex(r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN), webpage, u'video page URL') if not video_page.startswith(DOMAIN): video_page = DOMAIN + video_page diff --git a/youtube_dl/extractor/hark.py b/youtube_dl/extractor/hark.py new file mode 100644 index 000000000..5bdd08afa --- /dev/null +++ b/youtube_dl/extractor/hark.py @@ -0,0 +1,37 @@ +# -*- coding: utf-8 -*- + +import re +import json + +from .common import InfoExtractor +from ..utils import determine_ext + +class HarkIE(InfoExtractor): + _VALID_URL = r'https?://www\.hark\.com/clips/(.+?)-.+' + _TEST = { + u'url': u'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013', + u'file': u'mmbzyhkgny.mp3', + u'md5': u'6783a58491b47b92c7c1af5a77d4cbee', + u'info_dict': { + u'title': u"Obama: 'Beyond The Afghan Theater, We Only Target Al Qaeda' on May 23, 2013", + u'description': u'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.', + u'duration': 11, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group(1) + json_url = "http://www.hark.com/clips/%s.json" %(video_id) + info_json = self._download_webpage(json_url, video_id) + info = json.loads(info_json) + final_url = info['url'] + + return {'id': video_id, + 'url' : final_url, + 'title': info['name'], + 'ext': determine_ext(final_url), + 'description': info['description'], + 'thumbnail': info['image_original'], + 'duration': info['duration'], + } diff --git a/youtube_dl/extractor/jeuxvideo.py b/youtube_dl/extractor/jeuxvideo.py new file mode 100644 index 000000000..4327bc13d --- /dev/null +++ b/youtube_dl/extractor/jeuxvideo.py @@ -0,0 +1,47 @@ +# coding: utf-8 + +import json +import re +import xml.etree.ElementTree + +from .common import InfoExtractor + +class JeuxVideoIE(InfoExtractor): + _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm' + + _TEST = { + u'url': u'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm', + u'file': u'5182.mp4', + u'md5': u'e0fdb0cd3ce98713ef9c1e1e025779d0', + u'info_dict': { + u'title': u'GC 2013 : Tearaway nous présente ses papiers d\'identité', + u'description': u'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + title = re.match(self._VALID_URL, url).group(1) + webpage = self._download_webpage(url, title) + m_download = re.search(r'<param name="flashvars" value="config=(.*?)" />', webpage) + + xml_link = m_download.group(1) + + id = re.search(r'http://www.jeuxvideo.com/config/\w+/0011/(.*?)/\d+_player\.xml', xml_link).group(1) + + xml_config = self._download_webpage(xml_link, title, + 'Downloading XML config') + config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8')) + info = re.search(r'<format\.json>(.*?)</format\.json>', + xml_config, re.MULTILINE|re.DOTALL).group(1) + info = json.loads(info)['versions'][0] + + video_url = 'http://video720.jeuxvideo.com/' + info['file'] + + return {'id': id, + 'title' : config.find('titre_video').text, + 'ext' : 'mp4', + 'url' : video_url, + 'description': self._og_search_description(webpage), + 'thumbnail': config.find('image').text, + } diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py new file mode 100644 index 000000000..3bc9dae6d --- /dev/null +++ b/youtube_dl/extractor/nbc.py @@ -0,0 +1,33 @@ +import re +import xml.etree.ElementTree + +from .common import InfoExtractor +from ..utils import find_xpath_attr, compat_str + + +class NBCNewsIE(InfoExtractor): + _VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)' + + _TEST = { + u'url': u'http://www.nbcnews.com/video/nbc-news/52753292', + u'file': u'52753292.flv', + u'md5': u'47abaac93c6eaf9ad37ee6c4463a5179', + u'info_dict': { + u'title': u'Crew emerges after four-month Mars food study', + u'description': u'md5:24e632ffac72b35f8b67a12d1b6ddfc1', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + info_xml = self._download_webpage('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id) + info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')).find('video') + + return {'id': video_id, + 'title': info.find('headline').text, + 'ext': 'flv', + 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text, + 'description': compat_str(info.find('caption').text), + 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text, + } diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py new file mode 100644 index 000000000..65462d867 --- /dev/null +++ b/youtube_dl/extractor/pbs.py @@ -0,0 +1,34 @@ +import re +import json + +from .common import InfoExtractor + + +class PBSIE(InfoExtractor): + _VALID_URL = r'https?://video.pbs.org/video/(?P<id>\d+)/?' + + _TEST = { + u'url': u'http://video.pbs.org/video/2365006249/', + u'file': u'2365006249.mp4', + u'md5': 'ce1888486f0908d555a8093cac9a7362', + u'info_dict': { + u'title': u'A More Perfect Union', + u'description': u'md5:ba0c207295339c8d6eced00b7c363c6a', + u'duration': 3190, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id + info_page = self._download_webpage(info_url, video_id) + info =json.loads(info_page) + return {'id': video_id, + 'title': info['title'], + 'url': info['alternate_encoding']['url'], + 'ext': 'mp4', + 'description': info['program'].get('description'), + 'thumbnail': info.get('image_url'), + 'duration': info.get('duration'), + } diff --git a/youtube_dl/extractor/ro220.py b/youtube_dl/extractor/ro220.py new file mode 100644 index 000000000..c32f64d99 --- /dev/null +++ b/youtube_dl/extractor/ro220.py @@ -0,0 +1,42 @@ +import re + +from .common import InfoExtractor +from ..utils import ( + clean_html, + compat_parse_qs, +) + + +class Ro220IE(InfoExtractor): + IE_NAME = '220.ro' + _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?220\.ro/(?P<category>[^/]+)/(?P<shorttitle>[^/]+)/(?P<video_id>[^/]+)' + _TEST = { + u"url": u"http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/", + u'file': u'LYV6doKo7f.mp4', + u'md5': u'03af18b73a07b4088753930db7a34add', + u'info_dict': { + u"title": u"Luati-le Banii sez 4 ep 1", + u"description": u"Iata-ne reveniti dupa o binemeritata vacanta. Va astept si pe Facebook cu pareri si comentarii.", + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('video_id') + + webpage = self._download_webpage(url, video_id) + flashVars_str = self._search_regex( + r'<param name="flashVars" value="([^"]+)"', + webpage, u'flashVars') + flashVars = compat_parse_qs(flashVars_str) + + info = { + '_type': 'video', + 'id': video_id, + 'ext': 'mp4', + 'url': flashVars['videoURL'][0], + 'title': flashVars['title'][0], + 'description': clean_html(flashVars['desc'][0]), + 'thumbnail': flashVars['preview'][0], + } + return info diff --git a/youtube_dl/extractor/rtlnow.py b/youtube_dl/extractor/rtlnow.py new file mode 100644 index 000000000..7bb236c2b --- /dev/null +++ b/youtube_dl/extractor/rtlnow.py @@ -0,0 +1,126 @@ +# encoding: utf-8 +import re + +from .common import InfoExtractor +from ..utils import ( + clean_html, + ExtractorError, +) + +class RTLnowIE(InfoExtractor): + """Information Extractor for RTL NOW, RTL2 NOW, SUPER RTL NOW and VOX NOW""" + _VALID_URL = r'(?:http://)?(?P<url>(?P<base_url>rtl-now\.rtl\.de/|rtl2now\.rtl2\.de/|(?:www\.)?voxnow\.de/|(?:www\.)?superrtlnow\.de/)[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)' + _TESTS = [{ + u'url': u'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1', + u'file': u'90419.flv', + u'info_dict': { + u'upload_date': u'20070416', + u'title': u'Ahornallee - Folge 1 - Der Einzug', + u'description': u'Folge 1 - Der Einzug', + }, + u'params': { + u'skip_download': True, + }, + u'skip': u'Only works from Germany', + }, + { + u'url': u'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5', + u'file': u'69756.flv', + u'info_dict': { + u'upload_date': u'20120519', + u'title': u'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit...', + u'description': u'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.', + u'thumbnail': u'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg', + }, + u'params': { + u'skip_download': True, + }, + u'skip': u'Only works from Germany', + }, + { + u'url': u'www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17', + u'file': u'13883.flv', + u'info_dict': { + u'upload_date': u'20090627', + u'title': u'Voxtours - Südafrika-Reporter II', + u'description': u'Südafrika-Reporter II', + }, + u'params': { + u'skip_download': True, + }, + }, + { + u'url': u'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1', + u'file': u'99205.flv', + u'info_dict': { + u'upload_date': u'20080928', + u'title': u'Medicopter 117 - Angst!', + u'description': u'Angst!', + u'thumbnail': u'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg' + }, + u'params': { + u'skip_download': True, + }, + }] + + def _real_extract(self,url): + mobj = re.match(self._VALID_URL, url) + + webpage_url = u'http://' + mobj.group('url') + video_page_url = u'http://' + mobj.group('base_url') + video_id = mobj.group(u'video_id') + + webpage = self._download_webpage(webpage_url, video_id) + + note_m = re.search(r'''(?sx) + <div[ ]style="margin-left:[ ]20px;[ ]font-size:[ ]13px;">(.*?) + <div[ ]id="playerteaser">''', webpage) + if note_m: + msg = clean_html(note_m.group(1)) + raise ExtractorError(msg) + + video_title = self._html_search_regex(r'<title>(?P<title>[^<]+)</title>', + webpage, u'title') + playerdata_url = self._html_search_regex(r'\'playerdata\': \'(?P<playerdata_url>[^\']+)\'', + webpage, u'playerdata_url') + + playerdata = self._download_webpage(playerdata_url, video_id) + mobj = re.search(r'<title><!\[CDATA\[(?P<description>.+?)\s+- (?:Sendung )?vom (?P<upload_date_d>[0-9]{2})\.(?P<upload_date_m>[0-9]{2})\.(?:(?P<upload_date_Y>[0-9]{4})|(?P<upload_date_y>[0-9]{2})) [0-9]{2}:[0-9]{2} Uhr\]\]></title>', playerdata) + if mobj: + video_description = mobj.group(u'description') + if mobj.group('upload_date_Y'): + video_upload_date = mobj.group('upload_date_Y') + else: + video_upload_date = u'20' + mobj.group('upload_date_y') + video_upload_date += mobj.group('upload_date_m')+mobj.group('upload_date_d') + else: + video_description = None + video_upload_date = None + self._downloader.report_warning(u'Unable to extract description and upload date') + + # Thumbnail: not every video has an thumbnail + mobj = re.search(r'<meta property="og:image" content="(?P<thumbnail>[^"]+)">', webpage) + if mobj: + video_thumbnail = mobj.group(u'thumbnail') + else: + video_thumbnail = None + + mobj = re.search(r'<filename [^>]+><!\[CDATA\[(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>[^\]]+)\]\]></filename>', playerdata) + if mobj is None: + raise ExtractorError(u'Unable to extract media URL') + video_url = mobj.group(u'url') + video_play_path = u'mp4:' + mobj.group(u'play_path') + video_player_url = video_page_url + u'includes/vodplayer.swf' + + return [{ + 'id': video_id, + 'url': video_url, + 'play_path': video_play_path, + 'page_url': video_page_url, + 'player_url': video_player_url, + 'ext': 'flv', + 'title': video_title, + 'description': video_description, + 'upload_date': video_upload_date, + 'thumbnail': video_thumbnail, + }] diff --git a/youtube_dl/extractor/slashdot.py b/youtube_dl/extractor/slashdot.py new file mode 100644 index 000000000..2cba53076 --- /dev/null +++ b/youtube_dl/extractor/slashdot.py @@ -0,0 +1,23 @@ +import re + +from .common import InfoExtractor + + +class SlashdotIE(InfoExtractor): + _VALID_URL = r'https?://tv.slashdot.org/video/\?embed=(?P<id>.*?)(&|$)' + + _TEST = { + u'url': u'http://tv.slashdot.org/video/?embed=JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz', + u'file': u'JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz.mp4', + u'md5': u'd2222e7a4a4c1541b3e0cf732fb26735', + u'info_dict': { + u'title': u' Meet the Stampede Supercomputing Cluster\'s Administrator', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + ooyala_url = self._search_regex(r'<script src="(.*?)"', webpage, 'ooyala url') + return self.url_result(ooyala_url, 'Ooyala') diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 7c9f1c6b6..5f3a5540d 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -4,6 +4,7 @@ import re from .common import InfoExtractor from ..utils import ( compat_str, + compat_urlparse, ExtractorError, unified_strdate, @@ -22,6 +23,7 @@ class SoundcloudIE(InfoExtractor): _VALID_URL = r'''^(?:https?://)? (?:(?:(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)/?(?:[?].*)?$) |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)) + |(?P<widget>w.soundcloud.com/player/?.*?url=.*) ) ''' IE_NAME = u'soundcloud' @@ -79,6 +81,9 @@ class SoundcloudIE(InfoExtractor): if track_id is not None: info_json_url = 'http://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID full_title = track_id + elif mobj.group('widget'): + query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) + return self.url_result(query['url'][0], ie='Soundcloud') else: # extract uploader (which is in the url) uploader = mobj.group(1) diff --git a/youtube_dl/extractor/statigram.py b/youtube_dl/extractor/statigram.py index b8e6b3bf9..1ea4a9f2f 100644 --- a/youtube_dl/extractor/statigram.py +++ b/youtube_dl/extractor/statigram.py @@ -5,13 +5,13 @@ from .common import InfoExtractor class StatigramIE(InfoExtractor): _VALID_URL = r'(?:http://)?(?:www\.)?statigr\.am/p/([^/]+)' _TEST = { - u'url': u'http://statigr.am/p/484091715184808010_284179915', - u'file': u'484091715184808010_284179915.mp4', - u'md5': u'deda4ff333abe2e118740321e992605b', + u'url': u'http://statigr.am/p/522207370455279102_24101272', + u'file': u'522207370455279102_24101272.mp4', + u'md5': u'6eb93b882a3ded7c378ee1d6884b1814', u'info_dict': { - u"uploader_id": u"videoseconds", - u"title": u"Instagram photo by @videoseconds" - } + u'uploader_id': u'aguynamedpatrick', + u'title': u'Instagram photo by @aguynamedpatrick (Patrick Janelle)', + }, } def _real_extract(self, url): diff --git a/youtube_dl/extractor/trilulilu.py b/youtube_dl/extractor/trilulilu.py new file mode 100644 index 000000000..1c46156c7 --- /dev/null +++ b/youtube_dl/extractor/trilulilu.py @@ -0,0 +1,76 @@ +import json +import re +import xml.etree.ElementTree + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, +) + + +class TriluliluIE(InfoExtractor): + _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?trilulilu\.ro/video-(?P<category>[^/]+)/(?P<video_id>[^/]+)' + _TEST = { + u"url": u"http://www.trilulilu.ro/video-animatie/big-buck-bunny-1", + u'file': u"big-buck-bunny-1.mp4", + u'info_dict': { + u"title": u"Big Buck Bunny", + u"description": u":) pentru copilul din noi", + }, + # Server ignores Range headers (--test) + u"params": { + u"skip_download": True + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('video_id') + + webpage = self._download_webpage(url, video_id) + + title = self._og_search_title(webpage) + thumbnail = self._og_search_thumbnail(webpage) + description = self._og_search_description(webpage) + + log_str = self._search_regex( + r'block_flash_vars[ ]=[ ]({[^}]+})', webpage, u'log info') + log = json.loads(log_str) + + format_url = (u'http://fs%(server)s.trilulilu.ro/%(hash)s/' + u'video-formats2' % log) + format_str = self._download_webpage( + format_url, video_id, + note=u'Downloading formats', + errnote=u'Error while downloading formats') + + format_doc = xml.etree.ElementTree.fromstring(format_str) + + video_url_template = ( + u'http://fs%(server)s.trilulilu.ro/stream.php?type=video' + u'&source=site&hash=%(hash)s&username=%(userid)s&' + u'key=ministhebest&format=%%s&sig=&exp=' % + log) + formats = [ + { + 'format': fnode.text, + 'url': video_url_template % fnode.text, + } + + for fnode in format_doc.findall('./formats/format') + ] + + info = { + '_type': 'video', + 'id': video_id, + 'formats': formats, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + } + + # TODO: Remove when #980 has been merged + info['url'] = formats[-1]['url'] + info['ext'] = formats[-1]['format'].partition('-')[0] + + return info diff --git a/youtube_dl/extractor/unistra.py b/youtube_dl/extractor/unistra.py new file mode 100644 index 000000000..5ba0a9061 --- /dev/null +++ b/youtube_dl/extractor/unistra.py @@ -0,0 +1,32 @@ +import re + +from .common import InfoExtractor + +class UnistraIE(InfoExtractor): + _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', + u'file': u'154.mp4', + u'md5': u'736f605cfdc96724d55bb543ab3ced24', + u'info_dict': { + u'title': u'M!ss Yella', + u'description': u'md5:75e8439a3e2981cd5d4b6db232e8fdfc', + }, + } + + def _real_extract(self, url): + id = re.match(self._VALID_URL, url).group(1) + webpage = self._download_webpage(url, id) + file = re.search(r'file: "(.*?)",', webpage).group(1) + title = self._html_search_regex(r'<title>UTV - (.*?)</', webpage, u'title') + + video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file + + return {'id': id, + 'title': title, + 'ext': 'mp4', + 'url': video_url, + 'description': self._html_search_regex(r'<meta name="Description" content="(.*?)"', webpage, u'description', flags=re.DOTALL), + 'thumbnail': self._search_regex(r'image: "(.*?)"', webpage, u'thumbnail'), + } diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py index 67537eae5..70408c4f0 100644 --- a/youtube_dl/extractor/vevo.py +++ b/youtube_dl/extractor/vevo.py @@ -8,18 +8,18 @@ from ..utils import ( class VevoIE(InfoExtractor): """ - Accecps urls from vevo.com or in the format 'vevo:{id}' + 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>.*)$' + _VALID_URL = r'((http://www.vevo.com/watch/.*?/.*?/)|(vevo:))(?P<id>.*?)(\?|$)' _TEST = { u'url': u'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280', u'file': u'GB1101300280.mp4', u'md5': u'06bea460acb744eab74a9d7dcb4bfd61', u'info_dict': { - u"upload_date": u"20130624", - u"uploader": u"Hurts", - u"title": u"Somebody To Die For" + u"upload_date": u"20130624", + u"uploader": u"Hurts", + u"title": u"Somebody to Die For" } } diff --git a/youtube_dl/extractor/videofyme.py b/youtube_dl/extractor/videofyme.py index 04106672b..94f64ffa5 100644 --- a/youtube_dl/extractor/videofyme.py +++ b/youtube_dl/extractor/videofyme.py @@ -14,7 +14,7 @@ class VideofyMeIE(InfoExtractor): _TEST = { u'url': u'http://www.videofy.me/thisisvideofyme/1100701', u'file': u'1100701.mp4', - u'md5': u'2046dd5758541d630bfa93e741e2fd79', + u'md5': u'c77d700bdc16ae2e9f3c26019bd96143', u'info_dict': { u'title': u'This is VideofyMe', u'description': None, @@ -32,9 +32,8 @@ class VideofyMeIE(InfoExtractor): config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8')) video = config.find('video') sources = video.find('sources') - url_node = find_xpath_attr(sources, 'source', 'id', 'HQ on') - if url_node is None: - url_node = find_xpath_attr(sources, 'source', 'id', 'HQ off') + url_node = next(node for node in [find_xpath_attr(sources, 'source', 'id', 'HQ %s' % key) + for key in ['on', 'av', 'off']] if node is not None) video_url = url_node.find('url').text return {'id': video_id, diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index cc9c8d018..512e06e2a 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -20,18 +20,31 @@ class VimeoIE(InfoExtractor): _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)(?:[?].*)?$' _NETRC_MACHINE = 'vimeo' IE_NAME = u'vimeo' - _TEST = { - u'url': u'http://vimeo.com/56015672', - u'file': u'56015672.mp4', - u'md5': u'8879b6cc097e987f02484baf890129e5', - u'info_dict': { - u"upload_date": u"20121220", - u"description": u"This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", - u"uploader_id": u"user7108434", - u"uploader": u"Filippo Valsorda", - u"title": u"youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550" - } - } + _TESTS = [ + { + u'url': u'http://vimeo.com/56015672', + u'file': u'56015672.mp4', + u'md5': u'8879b6cc097e987f02484baf890129e5', + u'info_dict': { + u"upload_date": u"20121220", + u"description": u"This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", + u"uploader_id": u"user7108434", + u"uploader": u"Filippo Valsorda", + u"title": u"youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", + }, + }, + { + u'url': u'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876', + u'file': u'68093876.mp4', + u'md5': u'3b5ca6aa22b60dfeeadf50b72e44ed82', + u'note': u'Vimeo Pro video (#1197)', + u'info_dict': { + u'uploader_id': u'openstreetmapus', + u'uploader': u'OpenStreetMap US', + u'title': u'Andy Allan - Putting the Carto into OpenStreetMap Cartography', + }, + }, + ] def _login(self): (username, password) = self._get_login_info() @@ -83,7 +96,9 @@ class VimeoIE(InfoExtractor): video_id = mobj.group('id') if not mobj.group('proto'): url = 'https://' + url - if mobj.group('direct_link') or mobj.group('pro'): + elif mobj.group('pro'): + url = 'http://player.vimeo.com/video/' + video_id + elif mobj.group('direct_link'): url = 'https://vimeo.com/' + video_id # Retrieve video webpage to extract further information diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 0f1feeffd..88b8b6be0 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -3,7 +3,8 @@ import re from .common import InfoExtractor from ..utils import ( compat_urllib_parse, - + unescapeHTML, + determine_ext, ExtractorError, ) @@ -36,15 +37,16 @@ class XHamsterIE(InfoExtractor): video_url = compat_urllib_parse.unquote(mobj.group('file')) else: video_url = mobj.group('server')+'/key='+mobj.group('file') - video_extension = video_url.split('.')[-1] video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, u'title') - # Can't see the description anywhere in the UI - # video_description = self._html_search_regex(r'<span>Description: </span>(?P<description>[^<]+)', - # webpage, u'description', fatal=False) - # if video_description: video_description = unescapeHTML(video_description) + # Only a few videos have an description + mobj = re.search('<span>Description: </span>(?P<description>[^<]+)', webpage) + if mobj: + video_description = unescapeHTML(mobj.group('description')) + else: + video_description = None mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage) if mobj: @@ -62,9 +64,9 @@ class XHamsterIE(InfoExtractor): return [{ 'id': video_id, 'url': video_url, - 'ext': video_extension, + 'ext': determine_ext(video_url), 'title': video_title, - # 'description': video_description, + 'description': video_description, 'upload_date': video_upload_date, 'uploader_id': video_uploader_id, 'thumbnail': video_thumbnail diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 4d3bce879..af01c9da0 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -141,7 +141,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): (?: # the various things that can precede the ID: (?:(?:v|embed|e)/) # v/ or embed/ or e/ |(?: # or the v= param in all its forms - (?:watch|movie(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) + (?:(?:watch|movie)(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) (?:\?|\#!?) # the params delimiter ? or # or #! (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx) v= @@ -155,11 +155,22 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # Listed in order of quality _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13', '95', '94', '93', '92', '132', '151', + # 3D '85', '84', '102', '83', '101', '82', '100', + # Dash video + '138', '137', '248', '136', '247', '135', '246', + '245', '244', '134', '243', '133', '242', '160', + # Dash audio + '141', '172', '140', '171', '139', ] _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13', '95', '94', '93', '92', '132', '151', '85', '102', '84', '101', '83', '100', '82', + # Dash video + '138', '248', '137', '247', '136', '246', '245', + '244', '135', '243', '134', '242', '133', '160', + # Dash audio + '172', '141', '171', '140', '139', ] _video_extensions = { '13': '3gp', @@ -181,7 +192,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): '100': 'webm', '101': 'webm', '102': 'webm', - + # videos that use m3u8 '92': 'mp4', '93': 'mp4', @@ -190,6 +201,29 @@ class YoutubeIE(YoutubeBaseInfoExtractor): '96': 'mp4', '132': 'mp4', '151': 'mp4', + + # Dash mp4 + '133': 'mp4', + '134': 'mp4', + '135': 'mp4', + '136': 'mp4', + '137': 'mp4', + '138': 'mp4', + '139': 'mp4', + '140': 'mp4', + '141': 'mp4', + '160': 'mp4', + + # Dash webm + '171': 'webm', + '172': 'webm', + '242': 'webm', + '243': 'webm', + '244': 'webm', + '245': 'webm', + '246': 'webm', + '247': 'webm', + '248': 'webm', } _video_dimensions = { '5': '240x400', @@ -217,11 +251,58 @@ class YoutubeIE(YoutubeBaseInfoExtractor): '96': '1080p', '100': '360p', '101': '480p', - '102': '720p', + '102': '720p', '132': '240p', '151': '72p', + '133': '240p', + '134': '360p', + '135': '480p', + '136': '720p', + '137': '1080p', + '138': '>1080p', + '139': '48k', + '140': '128k', + '141': '256k', + '160': '192p', + '171': '128k', + '172': '256k', + '242': '240p', + '243': '360p', + '244': '480p', + '245': '480p', + '246': '480p', + '247': '720p', + '248': '1080p', + } + _special_itags = { + '82': '3D', + '83': '3D', + '84': '3D', + '85': '3D', + '100': '3D', + '101': '3D', + '102': '3D', + '133': 'DASH Video', + '134': 'DASH Video', + '135': 'DASH Video', + '136': 'DASH Video', + '137': 'DASH Video', + '138': 'DASH Video', + '139': 'DASH Audio', + '140': 'DASH Audio', + '141': 'DASH Audio', + '160': 'DASH Video', + '171': 'DASH Audio', + '172': 'DASH Audio', + '242': 'DASH Video', + '243': 'DASH Video', + '244': 'DASH Video', + '245': 'DASH Video', + '246': 'DASH Video', + '247': 'DASH Video', + '248': 'DASH Video', } - _3d_itags = ['85', '84', '102', '83', '101', '82', '100'] + IE_NAME = u'youtube' _TESTS = [ { @@ -255,7 +336,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): u"upload_date": u"20120506", u"title": u"Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]", u"description": u"md5:b085c9804f5ab69f4adea963a2dceb3c", - u"uploader": u"IconaPop", + u"uploader": u"Icona Pop", u"uploader_id": u"IconaPop" } }, @@ -335,22 +416,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor): return s[25] + s[3:25] + s[0] + s[26:42] + s[79] + s[43:79] + s[91] + s[80:83] elif len(s) == 90: return s[25] + s[3:25] + s[2] + s[26:40] + s[77] + s[41:77] + s[89] + s[78:81] + elif len(s) == 89: + return s[84:78:-1] + s[87] + s[77:60:-1] + s[0] + s[59:3:-1] elif len(s) == 88: return s[48] + s[81:67:-1] + s[82] + s[66:62:-1] + s[85] + s[61:48:-1] + s[67] + s[47:12:-1] + s[3] + s[11:3:-1] + s[2] + s[12] elif len(s) == 87: - return s[4:23] + s[86] + s[24:85] + return s[6:27] + s[4] + s[28:39] + s[27] + s[40:59] + s[2] + s[60:] elif len(s) == 86: - return s[83:85] + s[26] + s[79:46:-1] + s[85] + s[45:36:-1] + s[30] + s[35:30:-1] + s[46] + s[29:26:-1] + s[82] + s[25:1:-1] + return s[5:40] + s[3] + s[41:48] + s[0] + s[49:86] elif len(s) == 85: - return s[2:8] + s[0] + s[9:21] + s[65] + s[22:65] + s[84] + s[66:82] + s[21] + return s[83:34:-1] + s[0] + s[33:27:-1] + s[3] + s[26:19:-1] + s[34] + s[18:3:-1] + s[27] elif len(s) == 84: - return s[83:36:-1] + s[2] + s[35:26:-1] + s[3] + s[25:3:-1] + s[26] + return s[5:40] + s[3] + s[41:48] + s[0] + s[49:84] elif len(s) == 83: - return s[:15] + s[80] + s[16:80] + s[15] + return s[81:64:-1] + s[82] + s[63:52:-1] + s[45] + s[51:45:-1] + s[1] + s[44:1:-1] + s[0] elif len(s) == 82: - return s[36] + s[79:67:-1] + s[81] + s[66:40:-1] + s[33] + s[39:36:-1] + s[40] + s[35] + s[0] + s[67] + s[32:0:-1] + s[34] + return s[1:19] + s[0] + s[20:68] + s[19] + s[69:82] elif len(s) == 81: return s[56] + s[79:56:-1] + s[41] + s[55:41:-1] + s[80] + s[40:34:-1] + s[0] + s[33:29:-1] + s[34] + s[28:9:-1] + s[29] + s[8:0:-1] + s[9] + elif len(s) == 80: + return s[1:19] + s[0] + s[20:68] + s[19] + s[69:80] elif len(s) == 79: return s[54] + s[77:54:-1] + s[39] + s[53:39:-1] + s[78] + s[38:34:-1] + s[0] + s[33:29:-1] + s[34] + s[28:9:-1] + s[29] + s[8:0:-1] + s[9] @@ -373,11 +458,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor): try: sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - return (u'unable to download video subtitles: %s' % compat_str(err), None) + self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err)) + return {} sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list) sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list) if not sub_lang_list: - return (u'video doesn\'t have subtitles', None) + self._downloader.report_warning(u'video doesn\'t have subtitles') + return {} return sub_lang_list def _list_available_subtitles(self, video_id): @@ -386,8 +473,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _request_subtitle(self, sub_lang, sub_name, video_id, format): """ - Return tuple: - (error_message, sub_lang, sub) + Return the subtitle as a string or None if they are not found """ self.report_video_subtitles_request(video_id, sub_lang, format) params = compat_urllib_parse.urlencode({ @@ -400,21 +486,24 @@ class YoutubeIE(YoutubeBaseInfoExtractor): try: sub = compat_urllib_request.urlopen(url).read().decode('utf-8') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - return (u'unable to download video subtitles: %s' % compat_str(err), None, None) + self._downloader.report_warning(u'unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err))) + return if not sub: - return (u'Did not fetch video subtitles', None, None) - return (None, sub_lang, sub) + self._downloader.report_warning(u'Did not fetch video subtitles') + return + return sub def _request_automatic_caption(self, video_id, webpage): """We need the webpage for getting the captions url, pass it as an argument to speed up the process.""" - sub_lang = self._downloader.params.get('subtitleslang') or 'en' + sub_lang = (self._downloader.params.get('subtitleslangs') or ['en'])[0] sub_format = self._downloader.params.get('subtitlesformat') self.to_screen(u'%s: Looking for automatic captions' % video_id) mobj = re.search(r';ytplayer.config = ({.*?});', webpage) err_msg = u'Couldn\'t find automatic captions for "%s"' % sub_lang if mobj is None: - return [(err_msg, None, None)] + self._downloader.report_warning(err_msg) + return {} player_config = json.loads(mobj.group(1)) try: args = player_config[u'args'] @@ -429,40 +518,43 @@ class YoutubeIE(YoutubeBaseInfoExtractor): }) subtitles_url = caption_url + '&' + params sub = self._download_webpage(subtitles_url, video_id, u'Downloading automatic captions') - return [(None, sub_lang, sub)] - except KeyError: - return [(err_msg, None, None)] - - def _extract_subtitle(self, video_id): + return {sub_lang: sub} + # An extractor error can be raise by the download process if there are + # no automatic captions but there are subtitles + except (KeyError, ExtractorError): + self._downloader.report_warning(err_msg) + return {} + + def _extract_subtitles(self, video_id): """ - Return a list with a tuple: - [(error_message, sub_lang, sub)] + Return a dictionary: {language: subtitles} or {} if the subtitles + couldn't be found """ - sub_lang_list = self._get_available_subtitles(video_id) + available_subs_list = self._get_available_subtitles(video_id) sub_format = self._downloader.params.get('subtitlesformat') - if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles - return [(sub_lang_list[0], None, None)] - if self._downloader.params.get('subtitleslang', False): - sub_lang = self._downloader.params.get('subtitleslang') - elif 'en' in sub_lang_list: - sub_lang = 'en' + if not available_subs_list: #There was some error, it didn't get the available subtitles + return {} + if self._downloader.params.get('allsubtitles', False): + sub_lang_list = available_subs_list else: - sub_lang = list(sub_lang_list.keys())[0] - if not sub_lang in sub_lang_list: - return [(u'no closed captions found in the specified language "%s"' % sub_lang, None, None)] - - subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format) - return [subtitle] - - def _extract_all_subtitles(self, video_id): - sub_lang_list = self._get_available_subtitles(video_id) - sub_format = self._downloader.params.get('subtitlesformat') - if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles - return [(sub_lang_list[0], None, None)] - subtitles = [] + if self._downloader.params.get('subtitleslangs', False): + reqested_langs = self._downloader.params.get('subtitleslangs') + elif 'en' in available_subs_list: + reqested_langs = ['en'] + else: + reqested_langs = [list(available_subs_list.keys())[0]] + + sub_lang_list = {} + for sub_lang in reqested_langs: + if not sub_lang in available_subs_list: + self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang) + continue + sub_lang_list[sub_lang] = available_subs_list[sub_lang] + subtitles = {} for sub_lang in sub_lang_list: subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format) - subtitles.append(subtitle) + if subtitle: + subtitles[sub_lang] = subtitle return subtitles def _print_formats(self, formats): @@ -470,7 +562,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): for x in formats: print('%s\t:\t%s\t[%s]%s' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'), - ' (3D)' if x in self._3d_itags else '')) + ' ('+self._special_itags[x]+')' if x in self._special_itags else '')) def _extract_id(self, url): mobj = re.match(self._VALID_URL, url, re.VERBOSE) @@ -653,25 +745,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # subtitles video_subtitles = None - if self._downloader.params.get('writesubtitles', False): - video_subtitles = self._extract_subtitle(video_id) - if video_subtitles: - (sub_error, sub_lang, sub) = video_subtitles[0] - if sub_error: - self._downloader.report_warning(sub_error) - - if self._downloader.params.get('writeautomaticsub', False): + if self._downloader.params.get('writesubtitles', False) or self._downloader.params.get('allsubtitles', False): + video_subtitles = self._extract_subtitles(video_id) + elif self._downloader.params.get('writeautomaticsub', False): video_subtitles = self._request_automatic_caption(video_id, video_webpage) - (sub_error, sub_lang, sub) = video_subtitles[0] - if sub_error: - self._downloader.report_warning(sub_error) - - if self._downloader.params.get('allsubtitles', False): - video_subtitles = self._extract_all_subtitles(video_id) - for video_subtitle in video_subtitles: - (sub_error, sub_lang, sub) = video_subtitle - if sub_error: - self._downloader.report_warning(sub_error) if self._downloader.params.get('listsubtitles', False): self._list_available_subtitles(video_id) @@ -697,6 +774,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if m_s is not None: self.to_screen(u'%s: Encrypted signatures detected.' % video_id) video_info['url_encoded_fmt_stream_map'] = [args['url_encoded_fmt_stream_map']] + m_s = re.search(r'[&,]s=', args.get('adaptive_fmts', u'')) + if m_s is not None: + if 'url_encoded_fmt_stream_map' in video_info: + video_info['url_encoded_fmt_stream_map'][0] += ',' + args['adaptive_fmts'] + else: + video_info['url_encoded_fmt_stream_map'] = [args['adaptive_fmts']] + elif 'adaptive_fmts' in video_info: + if 'url_encoded_fmt_stream_map' in video_info: + video_info['url_encoded_fmt_stream_map'][0] += ',' + video_info['adaptive_fmts'][0] + else: + video_info['url_encoded_fmt_stream_map'] = video_info['adaptive_fmts'] except ValueError: pass @@ -756,7 +844,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): video_format = '{0} - {1}{2}'.format(format_param if format_param else video_extension, self._video_dimensions.get(format_param, '???'), - ' (3D)' if format_param in self._3d_itags else '') + ' ('+self._special_itags[format_param]+')' if format_param in self._special_itags else '') results.append({ 'id': video_id, |