diff options
Diffstat (limited to 'youtube_dl')
41 files changed, 655 insertions, 232 deletions
diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index 0804dfbe1..04784f602 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -4,12 +4,19 @@ import re import subprocess import sys import time -import traceback if os.name == 'nt': import ctypes -from .utils import * +from .utils import ( + compat_urllib_error, + compat_urllib_request, + ContentTooShortError, + determine_ext, + encodeFilename, + sanitize_open, + timeconvert, +) class FileDownloader(object): @@ -194,7 +201,7 @@ class FileDownloader(object): if old_filename == new_filename: return os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) - except (IOError, OSError) as err: + except (IOError, OSError): self.report_error(u'unable to rename file') def try_utime(self, filename, last_modified_hdr): @@ -227,8 +234,14 @@ class FileDownloader(object): if self.params.get('noprogress', False): return clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'') - eta_str = self.format_eta(eta) - percent_str = self.format_percent(percent) + if eta is not None: + eta_str = self.format_eta(eta) + else: + eta_str = 'Unknown ETA' + if percent is not None: + percent_str = self.format_percent(percent) + else: + percent_str = 'Unknown %' speed_str = self.format_speed(speed) if self.params.get('progress_with_newline', False): self.to_screen(u'[download] %s of %s at %s ETA %s' % @@ -251,7 +264,7 @@ class FileDownloader(object): """Report file has already been fully downloaded.""" try: self.to_screen(u'[download] %s has already been downloaded' % file_name) - except (UnicodeEncodeError) as err: + except UnicodeEncodeError: self.to_screen(u'[download] The file has already been downloaded') def report_unable_to_resume(self): @@ -368,7 +381,8 @@ class FileDownloader(object): self.report_destination(filename) tmpfilename = self.temp_name(filename) - args = ['ffmpeg', '-y', '-i', url, '-f', 'mp4', tmpfilename] + args = ['ffmpeg', '-y', '-i', url, '-f', 'mp4', '-c', 'copy', + '-absf', 'aac_adtstoasc', tmpfilename] # Check for ffmpeg first try: subprocess.call(['ffmpeg', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT) @@ -553,12 +567,11 @@ class FileDownloader(object): # Progress message speed = self.calc_speed(start, time.time(), byte_counter - resume_len) if data_len is None: - self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA') - eta = None + eta = percent = None else: percent = self.calc_percent(byte_counter, data_len) eta = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len) - self.report_progress(percent, data_len_str, speed, eta) + self.report_progress(percent, data_len_str, speed, eta) self._hook_progress({ 'downloaded_bytes': byte_counter, diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 7f73ea360..5253c39e1 100644 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -318,6 +318,12 @@ class YoutubeDL(object): % info_dict) return None + @staticmethod + def add_extra_info(info_dict, extra_info): + '''Set the keys from extra_info in info dict if they are missing''' + for key, value in extra_info.items(): + info_dict.setdefault(key, value) + def extract_info(self, url, download=True, ie_key=None, extra_info={}): ''' Returns a list with a dictionary for each video we find. @@ -344,17 +350,17 @@ class YoutubeDL(object): break if isinstance(ie_result, list): # Backwards compatibility: old IE result format - for result in ie_result: - result.update(extra_info) ie_result = { '_type': 'compat_list', 'entries': ie_result, } - else: - ie_result.update(extra_info) - if 'extractor' not in ie_result: - ie_result['extractor'] = ie.IE_NAME - return self.process_ie_result(ie_result, download=download) + self.add_extra_info(ie_result, + { + 'extractor': ie.IE_NAME, + 'webpage_url': url, + 'extractor_key': ie.ie_key(), + }) + return self.process_ie_result(ie_result, download, extra_info) except ExtractorError as de: # An error we somewhat expected self.report_error(compat_str(de), de.format_traceback()) break @@ -378,7 +384,7 @@ class YoutubeDL(object): result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system if result_type == 'video': - ie_result.update(extra_info) + self.add_extra_info(ie_result, extra_info) return self.process_video_result(ie_result) elif result_type == 'url': # We have to add extra_info to the results because it may be @@ -388,6 +394,7 @@ class YoutubeDL(object): ie_key=ie_result.get('ie_key'), extra_info=extra_info) elif result_type == 'playlist': + self.add_extra_info(ie_result, extra_info) # We process each entry in the playlist playlist = ie_result.get('title', None) or ie_result.get('id', None) self.to_screen(u'[download] Downloading playlist: %s' % playlist) @@ -413,12 +420,10 @@ class YoutubeDL(object): extra = { 'playlist': playlist, 'playlist_index': i + playliststart, + 'extractor': ie_result['extractor'], + 'webpage_url': ie_result['webpage_url'], + 'extractor_key': ie_result['extractor_key'], } - if not 'extractor' in entry: - # We set the extractor, if it's an url it will be set then to - # the new extractor, but if it's already a video we must make - # sure it's present: see issue #877 - entry['extractor'] = ie_result['extractor'] entry_result = self.process_ie_result(entry, download=download, extra_info=extra) @@ -427,10 +432,15 @@ class YoutubeDL(object): return ie_result elif result_type == 'compat_list': def _fixup(r): - r.setdefault('extractor', ie_result['extractor']) + self.add_extra_info(r, + { + 'extractor': ie_result['extractor'], + 'webpage_url': ie_result['webpage_url'], + 'extractor_key': ie_result['extractor_key'], + }) return r ie_result['entries'] = [ - self.process_ie_result(_fixup(r), download=download) + self.process_ie_result(_fixup(r), download, extra_info) for r in ie_result['entries'] ] return ie_result @@ -772,7 +782,7 @@ class YoutubeDL(object): def list_formats(self, info_dict): def line(format): - return (u'%-15s%-10s%-12s%s' % ( + return (u'%-20s%-10s%-12s%s' % ( format['format_id'], format['ext'], self.format_resolution(format), diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 48ffcbf8e..ab7879c5d 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -349,7 +349,7 @@ def parseOpts(overrideArguments=None): 'for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .')) filesystem.add_option('--autonumber-size', dest='autonumber_size', metavar='NUMBER', - help='Specifies the number of digits in %(autonumber)s when it is present in output filename template or --autonumber option is given') + help='Specifies the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given') filesystem.add_option('--restrict-filenames', action='store_true', dest='restrictfilenames', help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index bcf1cce7f..f9caca4ef 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -9,6 +9,7 @@ from .arte import ( ArteTVFutureIE, ) from .auengine import AUEngineIE +from .bambuser import BambuserIE, BambuserChannelIE from .bandcamp import BandcampIE from .bliptv import BlipTVIE, BlipTVUserIE from .bloomberg import BloombergIE @@ -37,8 +38,10 @@ from .defense import DefenseGouvFrIE from .ebaumsworld import EbaumsWorldIE from .ehow import EHowIE from .eighttracks import EightTracksIE +from .eitb import EitbIE from .escapist import EscapistIE from .exfm import ExfmIE +from .extremetube import ExtremeTubeIE from .facebook import FacebookIE from .faz import FazIE from .fktv import ( @@ -81,6 +84,7 @@ from .metacafe import MetacafeIE from .metacritic import MetacriticIE from .mit import TechTVMITIE, MITIE from .mixcloud import MixcloudIE +from .mofosex import MofosexIE from .mtv import MTVIE from .muzu import MuzuTVIE from .myspace import MySpaceIE @@ -112,6 +116,7 @@ from .slideshare import SlideshareIE from .sohu import SohuIE from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE from .southparkstudios import SouthParkStudiosIE +from .space import SpaceIE from .spankwire import SpankwireIE from .spiegel import SpiegelIE from .stanfordoc import StanfordOpenClassroomIE @@ -151,6 +156,7 @@ from .worldstarhiphop import WorldStarHipHopIE from .xhamster import XHamsterIE from .xnxx import XNXXIE from .xvideos import XVideosIE +from .xtube import XTubeIE from .yahoo import YahooIE, YahooSearchIE from .youjizz import YouJizzIE from .youku import YoukuIE @@ -159,6 +165,7 @@ from .youtube import ( YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, + YoutubeSearchDateIE, YoutubeUserIE, YoutubeChannelIE, YoutubeShowIE, diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index e10c74c11..b35a679e3 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -10,6 +10,7 @@ from ..utils import ( unified_strdate, determine_ext, get_element_by_id, + compat_str, ) # There are different sources of video in arte.tv, the extraction process @@ -181,20 +182,30 @@ class ArteTVPlus7IE(InfoExtractor): formats = all_formats else: raise ExtractorError(u'The formats list is empty') - # We order the formats by quality + if re.match(r'[A-Z]Q', formats[0]['quality']) is not None: - sort_key = lambda f: ['HQ', 'MQ', 'EQ', 'SQ'].index(f['quality']) + def sort_key(f): + return ['HQ', 'MQ', 'EQ', 'SQ'].index(f['quality']) else: - sort_key = lambda f: int(f.get('height',-1)) + def sort_key(f): + return ( + # Sort first by quality + int(f.get('height',-1)), + int(f.get('bitrate',-1)), + # The original version with subtitles has lower relevance + re.match(r'VO-ST(F|A)', f.get('versionCode', '')) is None, + # The version with sourds/mal subtitles has also lower relevance + re.match(r'VO?(F|A)-STM\1', f.get('versionCode', '')) is None, + ) formats = sorted(formats, key=sort_key) - # Prefer videos without subtitles in the same language - formats = sorted(formats, key=lambda f: re.match(r'VO(F|A)-STM\1', f.get('versionCode', '')) is None) - # Pick the best quality def _format(format_info): - quality = format_info['quality'] - m_quality = re.match(r'\w*? - (\d*)p', quality) - if m_quality is not None: - quality = m_quality.group(1) + quality = '' + height = format_info.get('height') + if height is not None: + quality = compat_str(height) + bitrate = format_info.get('bitrate') + if bitrate is not None: + quality += '-%d' % bitrate if format_info.get('versionCode') is not None: format_id = u'%s-%s' % (quality, format_info['versionCode']) else: @@ -203,7 +214,7 @@ class ArteTVPlus7IE(InfoExtractor): 'format_id': format_id, 'format_note': format_info.get('versionLibelle'), 'width': format_info.get('width'), - 'height': format_info.get('height'), + 'height': height, } if format_info['mediaType'] == u'rtmp': info['url'] = format_info['streamer'] diff --git a/youtube_dl/extractor/bambuser.py b/youtube_dl/extractor/bambuser.py new file mode 100644 index 000000000..f3b36f473 --- /dev/null +++ b/youtube_dl/extractor/bambuser.py @@ -0,0 +1,80 @@ +import re +import json +import itertools + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_request, +) + + +class BambuserIE(InfoExtractor): + IE_NAME = u'bambuser' + _VALID_URL = r'https?://bambuser\.com/v/(?P<id>\d+)' + _API_KEY = '005f64509e19a868399060af746a00aa' + + _TEST = { + u'url': u'http://bambuser.com/v/4050584', + u'md5': u'fba8f7693e48fd4e8641b3fd5539a641', + u'info_dict': { + u'id': u'4050584', + u'ext': u'flv', + u'title': u'Education engineering days - lightning talks', + u'duration': 3741, + u'uploader': u'pixelversity', + u'uploader_id': u'344706', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + info_url = ('http://player-c.api.bambuser.com/getVideo.json?' + '&api_key=%s&vid=%s' % (self._API_KEY, video_id)) + info_json = self._download_webpage(info_url, video_id) + info = json.loads(info_json)['result'] + + return { + 'id': video_id, + 'title': info['title'], + 'url': info['url'], + 'thumbnail': info.get('preview'), + 'duration': int(info['length']), + 'view_count': int(info['views_total']), + 'uploader': info['username'], + 'uploader_id': info['uid'], + } + + +class BambuserChannelIE(InfoExtractor): + IE_NAME = u'bambuser:channel' + _VALID_URL = r'http://bambuser.com/channel/(?P<user>.*?)(?:/|#|\?|$)' + # The maximum number we can get with each request + _STEP = 50 + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + user = mobj.group('user') + urls = [] + last_id = '' + for i in itertools.count(1): + req_url = ('http://bambuser.com/xhr-api/index.php?username={user}' + '&sort=created&access_mode=0%2C1%2C2&limit={count}' + '&method=broadcast&format=json&vid_older_than={last}' + ).format(user=user, count=self._STEP, last=last_id) + req = compat_urllib_request.Request(req_url) + # Without setting this header, we wouldn't get any result + req.add_header('Referer', 'http://bambuser.com/channel/%s' % user) + info_json = self._download_webpage(req, user, + u'Downloading page %d' % i) + results = json.loads(info_json)['result'] + if len(results) == 0: + break + last_id = results[-1]['vid'] + urls.extend(self.url_result(v['page'], 'Bambuser') for v in results) + + return { + '_type': 'playlist', + 'title': user, + 'entries': urls, + } diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 1392f382a..d8c35465a 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -9,10 +9,13 @@ from ..utils import ( compat_urllib_parse, find_xpath_attr, compat_urlparse, + compat_str, + compat_urllib_request, ExtractorError, ) + class BrightcoveIE(InfoExtractor): _VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*\?(?P<query>.*)' _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s' @@ -23,7 +26,7 @@ class BrightcoveIE(InfoExtractor): # From http://www.8tv.cat/8aldia/videos/xavier-sala-i-martin-aquesta-tarda-a-8-al-dia/ u'url': u'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1654948606001&flashID=myExperience&%40videoPlayer=2371591881001', u'file': u'2371591881001.mp4', - u'md5': u'9e80619e0a94663f0bdc849b4566af19', + u'md5': u'8eccab865181d29ec2958f32a6a754f5', u'note': u'Test Brightcove downloads and detection in GenericIE', u'info_dict': { u'title': u'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”', @@ -41,6 +44,17 @@ class BrightcoveIE(InfoExtractor): u'uploader': u'Oracle', }, }, + { + # From http://mashable.com/2013/10/26/thermoelectric-bracelet-lets-you-control-your-body-temperature/ + u'url': u'http://c.brightcove.com/services/viewer/federated_f9?&playerID=1265504713001&publisherID=AQ%7E%7E%2CAAABBzUwv1E%7E%2CxP-xFHVUstiMFlNYfvF4G9yFnNaqCw_9&videoID=2750934548001', + u'info_dict': { + u'id': u'2750934548001', + u'ext': u'mp4', + u'title': u'This Bracelet Acts as a Personal Thermostat', + u'description': u'md5:547b78c64f4112766ccf4e151c20b6a0', + u'uploader': u'Mashable', + }, + }, ] @classmethod @@ -68,24 +82,48 @@ class BrightcoveIE(InfoExtractor): videoPlayer = find_xpath_attr(object_doc, './param', 'name', '@videoPlayer') if videoPlayer is not None: params['@videoPlayer'] = videoPlayer.attrib['value'] + linkBase = find_xpath_attr(object_doc, './param', 'name', 'linkBaseURL') + if linkBase is not None: + params['linkBaseURL'] = linkBase.attrib['value'] data = compat_urllib_parse.urlencode(params) return cls._FEDERATED_URL_TEMPLATE % data + @classmethod + def _extract_brightcove_url(cls, webpage): + """Try to extract the brightcove url from the wepbage, returns None + if it can't be found + """ + m_brightcove = re.search( + r'<object[^>]+?class=([\'"])[^>]*?BrightcoveExperience.*?\1.+?</object>', + webpage, re.DOTALL) + if m_brightcove is not None: + return cls._build_brighcove_url(m_brightcove.group()) + else: + return None + def _real_extract(self, url): + # Change the 'videoId' and others field to '@videoPlayer' + url = re.sub(r'(?<=[?&])(videoI(d|D)|bctid)', '%40videoPlayer', url) + # Change bckey (used by bcove.me urls) to playerKey + url = re.sub(r'(?<=[?&])bckey', 'playerKey', url) mobj = re.match(self._VALID_URL, url) query_str = mobj.group('query') query = compat_urlparse.parse_qs(query_str) videoPlayer = query.get('@videoPlayer') if videoPlayer: - return self._get_video_info(videoPlayer[0], query_str) + return self._get_video_info(videoPlayer[0], query_str, query) else: player_key = query['playerKey'] return self._get_playlist_info(player_key[0]) - def _get_video_info(self, video_id, query): - request_url = self._FEDERATED_URL_TEMPLATE % query - webpage = self._download_webpage(request_url, video_id) + def _get_video_info(self, video_id, query_str, query): + request_url = self._FEDERATED_URL_TEMPLATE % query_str + req = compat_urllib_request.Request(request_url) + linkBase = query.get('linkBaseURL') + if linkBase is not None: + req.add_header('Referer', linkBase[0]) + webpage = self._download_webpage(req, video_id) self.report_extraction(video_id) info = self._search_regex(r'var experienceJSON = ({.*?});', webpage, 'json') @@ -109,7 +147,7 @@ class BrightcoveIE(InfoExtractor): def _extract_video_info(self, video_info): info = { - 'id': video_info['id'], + 'id': compat_str(video_info['id']), 'title': video_info['displayName'], 'description': video_info.get('shortDescription'), 'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'), @@ -119,15 +157,14 @@ class BrightcoveIE(InfoExtractor): renditions = video_info.get('renditions') if renditions: renditions = sorted(renditions, key=lambda r: r['size']) - best_format = renditions[-1] - info.update({ - 'url': best_format['defaultURL'], - 'ext': 'mp4', - }) + info['formats'] = [{ + 'url': rend['defaultURL'], + 'height': rend.get('frameHeight'), + 'width': rend.get('frameWidth'), + } for rend in renditions] elif video_info.get('FLVFullLengthURL') is not None: info.update({ 'url': video_info['FLVFullLengthURL'], - 'ext': 'flv', }) else: raise ExtractorError(u'Unable to extract video url for %s' % info['id']) diff --git a/youtube_dl/extractor/canalc2.py b/youtube_dl/extractor/canalc2.py index e7f4fa9fd..3d8d7f9d2 100644 --- a/youtube_dl/extractor/canalc2.py +++ b/youtube_dl/extractor/canalc2.py @@ -6,7 +6,7 @@ from .common import InfoExtractor class Canalc2IE(InfoExtractor): IE_NAME = 'canalc2.tv' - _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?idVideo=(\d+)&voir=oui' + _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?.*?idVideo=(?P<id>\d+)' _TEST = { u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui', @@ -18,7 +18,9 @@ class Canalc2IE(InfoExtractor): } def _real_extract(self, url): - video_id = re.match(self._VALID_URL, url).group(1) + video_id = re.match(self._VALID_URL, url).group('id') + # We need to set the voir field for getting the file name + url = 'http://www.canalc2.tv/video.asp?idVideo=%s&voir=oui' % video_id webpage = self._download_webpage(url, video_id) file_name = self._search_regex( r"so\.addVariable\('file','(.*?)'\);", diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index 79d879ced..d26f0f434 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -41,7 +41,7 @@ class CinemassacreIE(InfoExtractor): webpage_url = u'http://' + mobj.group('url') webpage = self._download_webpage(webpage_url, None) # Don't know video id yet video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d') - mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/(?:embed|player)\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage) + mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage) if not mobj: raise ExtractorError(u'Can\'t extract embed url and video id') playerdata_url = mobj.group(u'embed_url') diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py index a79f881cd..34adf6dda 100644 --- a/youtube_dl/extractor/cnn.py +++ b/youtube_dl/extractor/cnn.py @@ -6,7 +6,7 @@ from ..utils import determine_ext class CNNIE(InfoExtractor): - _VALID_URL = r'''(?x)https?://(edition\.)?cnn\.com/video/(data/.+?|\?)/ + _VALID_URL = r'''(?x)https?://((edition|www)\.)?cnn\.com/video/(data/.+?|\?)/ (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))''' _TESTS = [{ diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index cef4dce85..fb2d50a09 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -71,6 +71,9 @@ class InfoExtractor(object): ("3D" or "DASH video") * width Width of the video, if known * height Height of the video, if known + webpage_url: The url to the video webpage, if given to youtube-dl it + should allow to get the same result again. (It will be set + by YoutubeDL if it's missing) Unless mentioned otherwise, the fields should be Unicode strings. @@ -319,7 +322,9 @@ class InfoExtractor(object): if name is None: name = 'OpenGraph %s' % prop escaped = self._search_regex(self._og_regex(prop), html, name, flags=re.DOTALL, **kargs) - return unescapeHTML(escaped) + if not escaped is None: + return unescapeHTML(escaped) + return None def _og_search_thumbnail(self, html, **kargs): return self._og_search_property('image', html, u'thumbnail url', fatal=False, **kargs) diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 355b4ed0a..e87690f9d 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -141,9 +141,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): raise ExtractorError(u'Unable to extract video URL') # subtitles - video_subtitles = self.extract_subtitles(video_id) + video_subtitles = self.extract_subtitles(video_id, webpage) if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id) + self._list_available_subtitles(video_id, webpage) return return { @@ -157,7 +157,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): 'age_limit': age_limit, } - def _get_available_subtitles(self, video_id): + def _get_available_subtitles(self, video_id, webpage): try: sub_list = self._download_webpage( 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id, diff --git a/youtube_dl/extractor/depositfiles.py b/youtube_dl/extractor/depositfiles.py index d43348955..2c9fb5f2e 100644 --- a/youtube_dl/extractor/depositfiles.py +++ b/youtube_dl/extractor/depositfiles.py @@ -25,7 +25,7 @@ class DepositFilesIE(InfoExtractor): url = 'http://depositfiles.com/en/files/' + file_id # Retrieve file webpage with 'Free download' button pressed - free_download_indication = { 'gateway_result' : '1' } + free_download_indication = {'gateway_result' : '1'} request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication)) try: self.report_download_webpage(file_id) diff --git a/youtube_dl/extractor/eitb.py b/youtube_dl/extractor/eitb.py new file mode 100644 index 000000000..4ba323148 --- /dev/null +++ b/youtube_dl/extractor/eitb.py @@ -0,0 +1,37 @@ +# encoding: utf-8 +import re + +from .common import InfoExtractor +from .brightcove import BrightcoveIE +from ..utils import ExtractorError + + +class EitbIE(InfoExtractor): + IE_NAME = u'eitb.tv' + _VALID_URL = r'https?://www\.eitb\.tv/(eu/bideoa|es/video)/[^/]+/(?P<playlist_id>\d+)/(?P<chapter_id>\d+)' + + _TEST = { + u'add_ie': ['Brightcove'], + u'url': u'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/', + u'md5': u'edf4436247185adee3ea18ce64c47998', + u'info_dict': { + u'id': u'2743577154001', + u'ext': u'mp4', + u'title': u'60 minutos (Lasa y Zabala, 30 años)', + # All videos from eitb has this description in the brightcove info + u'description': u'.', + u'uploader': u'Euskal Telebista', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + chapter_id = mobj.group('chapter_id') + webpage = self._download_webpage(url, chapter_id) + bc_url = BrightcoveIE._extract_brightcove_url(webpage) + if bc_url is None: + raise ExtractorError(u'Could not extract the Brightcove url') + # The BrightcoveExperience object doesn't contain the video id, we set + # it manually + bc_url += '&%40videoPlayer={0}'.format(chapter_id) + return self.url_result(bc_url, BrightcoveIE.ie_key()) diff --git a/youtube_dl/extractor/exfm.py b/youtube_dl/extractor/exfm.py index c74556579..a51d79b08 100644 --- a/youtube_dl/extractor/exfm.py +++ b/youtube_dl/extractor/exfm.py @@ -21,6 +21,7 @@ class ExfmIE(InfoExtractor): u'description': u'Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive', }, u'note': u'Soundcloud song', + u'skip': u'The site is down too often', }, { u'url': u'http://ex.fm/song/wddt8', @@ -30,6 +31,7 @@ class ExfmIE(InfoExtractor): u'title': u'Safe and Sound', u'uploader': u'Capital Cities', }, + u'skip': u'The site is down too often', }, ] diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py new file mode 100644 index 000000000..1c20e4364 --- /dev/null +++ b/youtube_dl/extractor/extremetube.py @@ -0,0 +1,50 @@ +import os +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse_urlparse, + compat_urllib_request, + compat_urllib_parse, +) + +class ExtremeTubeIE(InfoExtractor): + _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)' + _TEST = { + u'url': u'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431', + u'file': u'652431.mp4', + u'md5': u'1fb9228f5e3332ec8c057d6ac36f33e0', + u'info_dict': { + u"title": u"Music Video 14 british euro brit european cumshots swallow", + u"uploader": u"unknown", + u"age_limit": 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('videoid') + url = 'http://www.' + mobj.group('url') + + req = compat_urllib_request.Request(url) + req.add_header('Cookie', 'age_verified=1') + webpage = self._download_webpage(req, video_id) + + video_title = self._html_search_regex(r'<h1 [^>]*?title="([^"]+)"[^>]*>\1<', webpage, u'title') + uploader = self._html_search_regex(r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, u'uploader', fatal=False) + video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&', webpage, u'video_url')) + path = compat_urllib_parse_urlparse(video_url).path + extension = os.path.splitext(path)[1][1:] + format = path.split('/')[5].split('_')[:2] + format = "-".join(format) + + return { + 'id': video_id, + 'title': video_title, + 'uploader': uploader, + 'url': video_url, + 'ext': extension, + 'format': format, + 'format_id': format, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 2c8fcf5ae..c7552fddb 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -33,6 +33,7 @@ class GenericIE(InfoExtractor): }, # embedded vimeo video { + u'add_ie': ['Vimeo'], u'url': u'http://skillsmatter.com/podcast/home/move-semanticsperfect-forwarding-and-rvalue-references', u'file': u'22444065.mp4', u'md5': u'2903896e23df39722c33f015af0666e2', @@ -44,6 +45,7 @@ class GenericIE(InfoExtractor): }, # bandcamp page with custom domain { + u'add_ie': ['Bandcamp'], u'url': u'http://bronyrock.com/track/the-pony-mash', u'file': u'3235767654.mp3', u'info_dict': { @@ -52,6 +54,23 @@ class GenericIE(InfoExtractor): }, u'skip': u'There is a limit of 200 free downloads / month for the test song', }, + # embedded brightcove video + # it also tests brightcove videos that need to set the 'Referer' in the + # http requests + { + u'add_ie': ['Brightcove'], + u'url': u'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/', + u'info_dict': { + u'id': u'2765128793001', + u'ext': u'mp4', + u'title': u'Le cours de bourse : l’analyse technique', + u'description': u'md5:7e9ad046e968cb2d1114004aba466fd9', + u'uploader': u'BFM BUSINESS', + }, + u'params': { + u'skip_download': True, + }, + }, ] def report_download_webpage(self, video_id): @@ -144,10 +163,9 @@ class GenericIE(InfoExtractor): self.report_extraction(video_id) # Look for BrightCove: - m_brightcove = re.search(r'<object[^>]+?class=([\'"])[^>]*?BrightcoveExperience.*?\1.+?</object>', webpage, re.DOTALL) - if m_brightcove is not None: + bc_url = BrightcoveIE._extract_brightcove_url(webpage) + if bc_url is not None: self.to_screen(u'Brightcove video detected.') - bc_url = BrightcoveIE._build_brighcove_url(m_brightcove.group()) return self.url_result(bc_url, 'Brightcove') # Look for embedded Vimeo player @@ -160,9 +178,9 @@ class GenericIE(InfoExtractor): # Look for embedded YouTube player mobj = re.search( - r'<iframe[^>]+?src="(https?://(?:www\.)?youtube.com/embed/.+?)"', webpage) + r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?youtube.com/embed/.+?)\1', webpage) if mobj: - surl = unescapeHTML(mobj.group(1)) + surl = unescapeHTML(mobj.group(u'url')) return self.url_result(surl, 'Youtube') # Look for Bandcamp pages with custom domain diff --git a/youtube_dl/extractor/hypem.py b/youtube_dl/extractor/hypem.py index ab2b59103..9bd06e7c7 100644 --- a/youtube_dl/extractor/hypem.py +++ b/youtube_dl/extractor/hypem.py @@ -30,7 +30,7 @@ class HypemIE(InfoExtractor): raise ExtractorError(u'Invalid URL: %s' % url) track_id = mobj.group(1) - data = { 'ax': 1, 'ts': time.time() } + data = {'ax': 1, 'ts': time.time()} data_encoded = compat_urllib_parse.urlencode(data) complete_url = url + "?" + data_encoded request = compat_urllib_request.Request(complete_url) @@ -68,4 +68,4 @@ class HypemIE(InfoExtractor): 'ext': "mp3", 'title': title, 'artist': artist, - }]
\ No newline at end of file + }] diff --git a/youtube_dl/extractor/kankan.py b/youtube_dl/extractor/kankan.py index 445d46501..50916f4a6 100644 --- a/youtube_dl/extractor/kankan.py +++ b/youtube_dl/extractor/kankan.py @@ -1,8 +1,10 @@ import re +import hashlib from .common import InfoExtractor from ..utils import determine_ext +_md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest() class KankanIE(InfoExtractor): _VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P<id>\d+)\.shtml' @@ -30,7 +32,10 @@ class KankanIE(InfoExtractor): video_id, u'Downloading video url info') ip = self._search_regex(r'ip:"(.+?)"', video_info_page, u'video url ip') path = self._search_regex(r'path:"(.+?)"', video_info_page, u'video url path') - video_url = 'http://%s%s' % (ip, path) + param1 = self._search_regex(r'param1:(\d+)', video_info_page, u'param1') + param2 = self._search_regex(r'param2:(\d+)', video_info_page, u'param2') + key = _md5('xl_mp43651' + param1 + param2) + video_url = 'http://%s%s?key=%s&key1=%s' % (ip, path, key, param2) return {'id': video_id, 'title': title, diff --git a/youtube_dl/extractor/keezmovies.py b/youtube_dl/extractor/keezmovies.py index 5e05900da..29658a7d6 100644 --- a/youtube_dl/extractor/keezmovies.py +++ b/youtube_dl/extractor/keezmovies.py @@ -12,7 +12,7 @@ from ..aes import ( ) class KeezMoviesIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>keezmovies\.com/video/.+?(?P<videoid>[0-9]+))' + _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>keezmovies\.com/video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)' _TEST = { u'url': u'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711', u'file': u'1214711.mp4', @@ -43,10 +43,10 @@ class KeezMoviesIE(InfoExtractor): if webpage.find('encrypted=true')!=-1: password = self._html_search_regex(r'video_title=(.+?)&', webpage, u'password') video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8') - path = compat_urllib_parse_urlparse( video_url ).path - extension = os.path.splitext( path )[1][1:] + path = compat_urllib_parse_urlparse(video_url).path + extension = os.path.splitext(path)[1][1:] format = path.split('/')[4].split('_')[:2] - format = "-".join( format ) + format = "-".join(format) age_limit = self._rta_search(webpage) diff --git a/youtube_dl/extractor/mofosex.py b/youtube_dl/extractor/mofosex.py new file mode 100644 index 000000000..b9430b09b --- /dev/null +++ b/youtube_dl/extractor/mofosex.py @@ -0,0 +1,49 @@ +import os +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse_urlparse, + compat_urllib_request, + compat_urllib_parse, +) + +class MofosexIE(InfoExtractor): + _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>mofosex\.com/videos/(?P<videoid>[0-9]+)/.*?\.html)' + _TEST = { + u'url': u'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html', + u'file': u'5018.mp4', + u'md5': u'1b2eb47ac33cc75d4a80e3026b613c5a', + u'info_dict': { + u"title": u"Japanese Teen Music Video", + u"age_limit": 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('videoid') + url = 'http://www.' + mobj.group('url') + + req = compat_urllib_request.Request(url) + req.add_header('Cookie', 'age_verified=1') + webpage = self._download_webpage(req, video_id) + + video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, u'title') + video_url = compat_urllib_parse.unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, u'video_url')) + path = compat_urllib_parse_urlparse(video_url).path + extension = os.path.splitext(path)[1][1:] + format = path.split('/')[5].split('_')[:2] + format = "-".join(format) + + age_limit = self._rta_search(webpage) + + return { + 'id': video_id, + 'title': video_title, + 'url': video_url, + 'ext': extension, + 'format': format, + 'format_id': format, + 'age_limit': age_limit, + } diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index e96d3952c..24a79ae13 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -26,6 +26,7 @@ class MTVIE(InfoExtractor): }, }, { + 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', diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 5e2454f1b..75cf4bb9f 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -47,10 +47,10 @@ class PornHubIE(InfoExtractor): formats = [] for video_url in video_urls: - path = compat_urllib_parse_urlparse( video_url ).path - extension = os.path.splitext( path )[1][1:] + path = compat_urllib_parse_urlparse(video_url).path + extension = os.path.splitext(path)[1][1:] format = path.split('/')[5].split('_')[:2] - format = "-".join( format ) + format = "-".join(format) formats.append({ 'url': video_url, 'ext': extension, diff --git a/youtube_dl/extractor/slashdot.py b/youtube_dl/extractor/slashdot.py index 2cba53076..f5003c7f9 100644 --- a/youtube_dl/extractor/slashdot.py +++ b/youtube_dl/extractor/slashdot.py @@ -7,6 +7,7 @@ class SlashdotIE(InfoExtractor): _VALID_URL = r'https?://tv.slashdot.org/video/\?embed=(?P<id>.*?)(&|$)' _TEST = { + u'add_ie': ['Ooyala'], u'url': u'http://tv.slashdot.org/video/?embed=JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz', u'file': u'JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz.mp4', u'md5': u'd2222e7a4a4c1541b3e0cf732fb26735', diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 29cd5617c..4717fbb77 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -29,17 +29,34 @@ class SoundcloudIE(InfoExtractor): ) ''' IE_NAME = u'soundcloud' - _TEST = { - u'url': u'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy', - u'file': u'62986583.mp3', - u'md5': u'ebef0a451b909710ed1d7787dddbf0d7', - u'info_dict': { - u"upload_date": u"20121011", - u"description": u"No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd", - u"uploader": u"E.T. ExTerrestrial Music", - u"title": u"Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1" - } - } + _TESTS = [ + { + u'url': u'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy', + u'file': u'62986583.mp3', + u'md5': u'ebef0a451b909710ed1d7787dddbf0d7', + u'info_dict': { + u"upload_date": u"20121011", + u"description": u"No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd", + u"uploader": u"E.T. ExTerrestrial Music", + u"title": u"Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1" + } + }, + # not streamable song + { + u'url': u'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep', + u'info_dict': { + u'id': u'47127627', + u'ext': u'mp3', + u'title': u'Goldrushed', + u'uploader': u'The Royal Concept', + u'upload_date': u'20120521', + }, + u'params': { + # rtmp + u'skip_download': True, + }, + }, + ] _CLIENT_ID = 'b45b1aa10f1ac2941910a7f0d10f8e28' @@ -56,16 +73,16 @@ class SoundcloudIE(InfoExtractor): return 'http://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID def _extract_info_dict(self, info, full_title=None, quiet=False): - video_id = info['id'] - name = full_title or video_id + track_id = compat_str(info['id']) + name = full_title or track_id if quiet == False: self.report_extraction(name) thumbnail = info['artwork_url'] if thumbnail is not None: thumbnail = thumbnail.replace('-large', '-t500x500') - return { - 'id': info['id'], + result = { + 'id': track_id, 'url': info['stream_url'] + '?client_id=' + self._CLIENT_ID, 'uploader': info['user']['username'], 'upload_date': unified_strdate(info['created_at']), @@ -74,6 +91,21 @@ class SoundcloudIE(InfoExtractor): 'description': info['description'], 'thumbnail': thumbnail, } + if info.get('downloadable', False): + result['url'] = 'https://api.soundcloud.com/tracks/{0}/download?client_id={1}'.format(track_id, self._CLIENT_ID) + if not info.get('streamable', False): + # We have to get the rtmp url + stream_json = self._download_webpage( + 'http://api.soundcloud.com/i1/tracks/{0}/streams?client_id={1}'.format(track_id, self._CLIENT_ID), + track_id, u'Downloading track url') + rtmp_url = json.loads(stream_json)['rtmp_mp3_128_url'] + # The url doesn't have an rtmp app, we have to extract the playpath + url, path = rtmp_url.split('mp3:', 1) + result.update({ + 'url': url, + 'play_path': 'mp3:' + path, + }) + return result def _real_extract(self, url): mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE) @@ -106,70 +138,8 @@ class SoundcloudIE(InfoExtractor): class SoundcloudSetIE(SoundcloudIE): _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)(?:[?].*)?$' IE_NAME = u'soundcloud:set' - _TEST = { - u"url":"https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep", - u"playlist": [ - { - u"file":"30510138.mp3", - u"md5":"f9136bf103901728f29e419d2c70f55d", - u"info_dict": { - u"upload_date": u"20111213", - u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com", - u"uploader": u"The Royal Concept", - u"title": u"D-D-Dance" - } - }, - { - u"file":"47127625.mp3", - u"md5":"09b6758a018470570f8fd423c9453dd8", - u"info_dict": { - u"upload_date": u"20120521", - u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com", - u"uploader": u"The Royal Concept", - u"title": u"The Royal Concept - Gimme Twice" - } - }, - { - u"file":"47127627.mp3", - u"md5":"154abd4e418cea19c3b901f1e1306d9c", - u"info_dict": { - u"upload_date": u"20120521", - u"uploader": u"The Royal Concept", - u"title": u"Goldrushed" - } - }, - { - u"file":"47127629.mp3", - u"md5":"2f5471edc79ad3f33a683153e96a79c1", - u"info_dict": { - u"upload_date": u"20120521", - u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com", - u"uploader": u"The Royal Concept", - u"title": u"In the End" - } - }, - { - u"file":"47127631.mp3", - u"md5":"f9ba87aa940af7213f98949254f1c6e2", - u"info_dict": { - u"upload_date": u"20120521", - u"description": u"The Royal Concept from Stockholm\r\nFilip / David / Povel / Magnus\r\nwww.theroyalconceptband.com", - u"uploader": u"The Royal Concept", - u"title": u"Knocked Up" - } - }, - { - u"file":"75206121.mp3", - u"md5":"f9d1fe9406717e302980c30de4af9353", - u"info_dict": { - u"upload_date": u"20130116", - u"description": u"The unreleased track World on Fire premiered on the CW's hit show Arrow (8pm/7pm central). \r\nAs a gift to our fans we would like to offer you a free download of the track! ", - u"uploader": u"The Royal Concept", - u"title": u"World On Fire" - } - } - ] - } + # it's in tests/test_playlists.py + _TESTS = [] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -208,7 +178,7 @@ class SoundcloudUserIE(SoundcloudIE): IE_NAME = u'soundcloud:user' # it's in tests/test_playlists.py - _TEST = None + _TESTS = [] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/space.py b/youtube_dl/extractor/space.py new file mode 100644 index 000000000..0d32a0688 --- /dev/null +++ b/youtube_dl/extractor/space.py @@ -0,0 +1,35 @@ +import re + +from .common import InfoExtractor +from .brightcove import BrightcoveIE +from ..utils import RegexNotFoundError, ExtractorError + + +class SpaceIE(InfoExtractor): + _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', + u'info_dict': { + u'id': u'2780937028001', + u'ext': u'mp4', + u'title': u'Huge Martian Landforms\' Detail Revealed By European Probe | Video', + u'description': u'md5:db81cf7f3122f95ed234b631a6ea1e61', + u'uploader': u'TechMedia Networks', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + title = mobj.group('title') + webpage = self._download_webpage(url, title) + try: + # Some videos require the playerKey field, which isn't define in + # the BrightcoveExperience object + brightcove_url = self._og_search_video_url(webpage) + except RegexNotFoundError: + # Other videos works fine with the info from the object + brightcove_url = BrightcoveIE._extract_brightcove_url(webpage) + if brightcove_url is None: + raise ExtractorError(u'The webpage does not contain a video', expected=True) + return self.url_result(brightcove_url, BrightcoveIE.ie_key()) diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py index 32df0a7fb..97f9c268a 100644 --- a/youtube_dl/extractor/spankwire.py +++ b/youtube_dl/extractor/spankwire.py @@ -49,10 +49,10 @@ class SpankwireIE(InfoExtractor): formats = [] for video_url in video_urls: - path = compat_urllib_parse_urlparse( video_url ).path - extension = os.path.splitext( path )[1][1:] + path = compat_urllib_parse_urlparse(video_url).path + extension = os.path.splitext(path)[1][1:] format = path.split('/')[4].split('_')[:2] - format = "-".join( format ) + format = "-".join(format) formats.append({ 'url': video_url, 'ext': extension, diff --git a/youtube_dl/extractor/subtitles.py b/youtube_dl/extractor/subtitles.py index 90de7de3a..4b4c5235d 100644 --- a/youtube_dl/extractor/subtitles.py +++ b/youtube_dl/extractor/subtitles.py @@ -12,9 +12,9 @@ class SubtitlesInfoExtractor(InfoExtractor): return any([self._downloader.params.get('writesubtitles', False), self._downloader.params.get('writeautomaticsub')]) - def _list_available_subtitles(self, video_id, webpage=None): + def _list_available_subtitles(self, video_id, webpage): """ outputs the available subtitles for the video """ - sub_lang_list = self._get_available_subtitles(video_id) + sub_lang_list = self._get_available_subtitles(video_id, webpage) auto_captions_list = self._get_available_automatic_caption(video_id, webpage) sub_lang = ",".join(list(sub_lang_list.keys())) self.to_screen(u'%s: Available subtitles for video: %s' % @@ -23,7 +23,7 @@ class SubtitlesInfoExtractor(InfoExtractor): self.to_screen(u'%s: Available automatic captions for video: %s' % (video_id, auto_lang)) - def extract_subtitles(self, video_id, video_webpage=None): + def extract_subtitles(self, video_id, webpage): """ returns {sub_lang: sub} ,{} if subtitles not found or None if the subtitles aren't requested. @@ -32,9 +32,9 @@ class SubtitlesInfoExtractor(InfoExtractor): return None available_subs_list = {} if self._downloader.params.get('writeautomaticsub', False): - available_subs_list.update(self._get_available_automatic_caption(video_id, video_webpage)) + available_subs_list.update(self._get_available_automatic_caption(video_id, webpage)) if self._downloader.params.get('writesubtitles', False): - available_subs_list.update(self._get_available_subtitles(video_id)) + available_subs_list.update(self._get_available_subtitles(video_id, webpage)) if not available_subs_list: # error, it didn't get the available subtitles return {} @@ -74,7 +74,7 @@ class SubtitlesInfoExtractor(InfoExtractor): return return sub - def _get_available_subtitles(self, video_id): + def _get_available_subtitles(self, video_id, webpage): """ returns {sub_lang: url} or {} if not available Must be redefined by the subclasses diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py index c910110ca..bc48620f0 100644 --- a/youtube_dl/extractor/teamcoco.py +++ b/youtube_dl/extractor/teamcoco.py @@ -1,4 +1,5 @@ import re +import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( @@ -11,7 +12,7 @@ class TeamcocoIE(InfoExtractor): _TEST = { u'url': u'http://teamcoco.com/video/louis-ck-interview-george-w-bush', u'file': u'19705.mp4', - u'md5': u'27b6f7527da5acf534b15f21b032656e', + u'md5': u'cde9ba0fa3506f5f017ce11ead928f9a', u'info_dict': { u"description": u"Louis C.K. got starstruck by George W. Bush, so what? Part one.", u"title": u"Louis C.K. Interview Pt. 1 11/3/11" @@ -31,16 +32,40 @@ class TeamcocoIE(InfoExtractor): self.report_extraction(video_id) data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id - data = self._download_webpage(data_url, video_id, 'Downloading data webpage') + data_xml = self._download_webpage(data_url, video_id, 'Downloading data webpage') + data = xml.etree.ElementTree.fromstring(data_xml.encode('utf-8')) - video_url = self._html_search_regex(r'<file [^>]*type="high".*?>(.*?)</file>', - data, u'video URL') - return [{ + qualities = ['500k', '480p', '1000k', '720p', '1080p'] + formats = [] + for file in data.findall('files/file'): + if file.attrib.get('playmode') == 'all': + # it just duplicates one of the entries + break + file_url = file.text + m_format = re.search(r'(\d+(k|p))\.mp4', file_url) + if m_format is not None: + format_id = m_format.group(1) + else: + format_id = file.attrib['bitrate'] + formats.append({ + 'url': file_url, + 'ext': 'mp4', + 'format_id': format_id, + }) + def sort_key(f): + try: + return qualities.index(f['format_id']) + except ValueError: + return -1 + formats.sort(key=sort_key) + if not formats: + raise RegexNotFoundError(u'Unable to extract video URL') + + return { 'id': video_id, - 'url': video_url, - 'ext': 'mp4', + 'formats': formats, 'title': self._og_search_title(webpage), 'thumbnail': self._og_search_thumbnail(webpage), 'description': self._og_search_description(webpage), - }] + } diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index dfa1176a3..76cfdfb90 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -1,10 +1,14 @@ import json import re -from .common import InfoExtractor +from .subtitles import SubtitlesInfoExtractor +from ..utils import ( + compat_str, + RegexNotFoundError, +) -class TEDIE(InfoExtractor): +class TEDIE(SubtitlesInfoExtractor): _VALID_URL=r'''http://www\.ted\.com/ ( ((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist @@ -32,7 +36,7 @@ class TEDIE(InfoExtractor): def _real_extract(self, url): m=re.match(self._VALID_URL, url, re.VERBOSE) if m.group('type_talk'): - return [self._talk_info(url)] + return self._talk_info(url) else : playlist_id=m.group('playlist_id') name=m.group('name') @@ -82,11 +86,21 @@ class TEDIE(InfoExtractor): 'url': stream['file'], 'format': stream['id'] } for stream in info['htmlStreams']] + + video_id = info['id'] + + # subtitles + video_subtitles = self.extract_subtitles(video_id, webpage) + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id, webpage) + return + info = { - 'id': info['id'], + 'id': video_id, 'title': title, 'thumbnail': thumbnail, 'description': desc, + 'subtitles': video_subtitles, 'formats': formats, } @@ -94,3 +108,17 @@ class TEDIE(InfoExtractor): info.update(info['formats'][-1]) return info + + def _get_available_subtitles(self, video_id, webpage): + try: + options = self._search_regex(r'(?:<select name="subtitles_language_select" id="subtitles_language_select">)(.*?)(?:</select>)', webpage, 'subtitles_language_select', flags=re.DOTALL) + languages = re.findall(r'(?:<option value=")(\S+)"', options) + if languages: + sub_lang_list = {} + for l in languages: + url = 'http://www.ted.com/talks/subtitles/id/%s/lang/%s/format/srt' % (video_id, l) + sub_lang_list[l] = url + return sub_lang_list + except RegexNotFoundError as err: + self._downloader.report_warning(u'video doesn\'t have subtitles') + return {} diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py index aea9d9a24..d4b7603c7 100644 --- a/youtube_dl/extractor/tube8.py +++ b/youtube_dl/extractor/tube8.py @@ -46,10 +46,10 @@ class Tube8IE(InfoExtractor): if webpage.find('"encrypted":true')!=-1: password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password') video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8') - path = compat_urllib_parse_urlparse( video_url ).path - extension = os.path.splitext( path )[1][1:] + path = compat_urllib_parse_urlparse(video_url).path + extension = os.path.splitext(path)[1][1:] format = path.split('/')[4].split('_')[:2] - format = "-".join( format ) + format = "-".join(format) return { 'id': video_id, diff --git a/youtube_dl/extractor/viddler.py b/youtube_dl/extractor/viddler.py index 12c84a985..826804af3 100644 --- a/youtube_dl/extractor/viddler.py +++ b/youtube_dl/extractor/viddler.py @@ -8,7 +8,7 @@ from ..utils import ( class ViddlerIE(InfoExtractor): - _VALID_URL = r'(?P<domain>https?://(?:www\.)?viddler.com)/(?:v|embed|player)/(?P<id>[0-9]+)' + _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', diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index c7d864a2b..d465bf20b 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|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?(?:#.*)?$' + _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|(?P<player>player))\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?(?:#.*)?$' _NETRC_MACHINE = 'vimeo' IE_NAME = u'vimeo' _TESTS = [ @@ -128,11 +128,9 @@ class VimeoIE(InfoExtractor): raise ExtractorError(u'Invalid URL: %s' % url) video_id = mobj.group('id') - if not mobj.group('proto'): - url = 'https://' + url - elif mobj.group('pro'): + if mobj.group('pro') or mobj.group('player'): url = 'http://player.vimeo.com/video/' + video_id - elif mobj.group('direct_link'): + else: url = 'https://vimeo.com/' + video_id # Retrieve video webpage to extract further information @@ -205,7 +203,7 @@ class VimeoIE(InfoExtractor): # Vimeo specific: extract video codec and quality information # First consider quality, then codecs, then take everything codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')] - files = { 'hd': [], 'sd': [], 'other': []} + files = {'hd': [], 'sd': [], 'other': []} config_files = config["video"].get("files") or config["request"].get("files") for codec_name, codec_extension in codecs: for quality in config_files.get(codec_name, []): @@ -234,7 +232,7 @@ class VimeoIE(InfoExtractor): if len(formats) == 0: raise ExtractorError(u'No known codec found') - return [{ + return { 'id': video_id, 'uploader': video_uploader, 'uploader_id': video_uploader_id, @@ -243,7 +241,8 @@ class VimeoIE(InfoExtractor): 'thumbnail': video_thumbnail, 'description': video_description, 'formats': formats, - }] + 'webpage_url': url, + } class VimeoChannelIE(InfoExtractor): diff --git a/youtube_dl/extractor/weibo.py b/youtube_dl/extractor/weibo.py index 0757495bd..fa784ab99 100644 --- a/youtube_dl/extractor/weibo.py +++ b/youtube_dl/extractor/weibo.py @@ -13,6 +13,7 @@ class WeiboIE(InfoExtractor): _VALID_URL = r'https?://video\.weibo\.com/v/weishipin/t_(?P<id>.+?)\.htm' _TEST = { + u'add_ie': ['Sina'], u'url': u'http://video.weibo.com/v/weishipin/t_zjUw2kZ.htm', u'file': u'98322879.flv', u'info_dict': { diff --git a/youtube_dl/extractor/xnxx.py b/youtube_dl/extractor/xnxx.py index 8a0eb1afd..1177a4b14 100644 --- a/youtube_dl/extractor/xnxx.py +++ b/youtube_dl/extractor/xnxx.py @@ -9,7 +9,7 @@ from ..utils import ( class XNXXIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?video\.xnxx\.com/video([0-9]+)/(.*)' + _VALID_URL = r'^(?:https?://)?(?:video|www)\.xnxx\.com/video([0-9]+)/(.*)' VIDEO_URL_RE = r'flv_url=(.*?)&' VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM' VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&' diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py new file mode 100644 index 000000000..03ad88bed --- /dev/null +++ b/youtube_dl/extractor/xtube.py @@ -0,0 +1,55 @@ +import os +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse_urlparse, + compat_urllib_request, + compat_urllib_parse, +) + +class XTubeIE(InfoExtractor): + _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<videoid>[^/?&]+))' + _TEST = { + u'url': u'http://www.xtube.com/watch.php?v=kVTUy_G222_', + u'file': u'kVTUy_G222_.mp4', + u'md5': u'092fbdd3cbe292c920ef6fc6a8a9cdab', + u'info_dict': { + u"title": u"strange erotica", + u"description": u"surreal gay themed erotica...almost an ET kind of thing", + u"uploader": u"greenshowers", + u"age_limit": 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('videoid') + url = 'http://www.' + mobj.group('url') + + req = compat_urllib_request.Request(url) + req.add_header('Cookie', 'age_verified=1') + webpage = self._download_webpage(req, video_id) + + video_title = self._html_search_regex(r'<div class="p_5px[^>]*>([^<]+)', webpage, u'title') + video_uploader = self._html_search_regex(r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, u'uploader', fatal=False) + video_description = self._html_search_regex(r'<p class="video_description">([^<]+)', webpage, u'description', default=None) + video_url= self._html_search_regex(r'var videoMp4 = "([^"]+)', webpage, u'video_url').replace('\\/', '/') + path = compat_urllib_parse_urlparse(video_url).path + extension = os.path.splitext(path)[1][1:] + format = path.split('/')[5].split('_')[:2] + format[0] += 'p' + format[1] += 'k' + format = "-".join(format) + + return { + 'id': video_id, + 'title': video_title, + 'uploader': video_uploader, + 'description': video_description, + 'url': video_url, + 'ext': extension, + 'format': format, + 'format_id': format, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index 464b498f5..34e6afb20 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -132,7 +132,7 @@ class YahooSearchIE(SearchInfoExtractor): mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r) e = self.url_result('http://' + mobj.group('url'), 'Yahoo') res['entries'].append(e) - if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1 )): + if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1)): break return res diff --git a/youtube_dl/extractor/youku.py b/youtube_dl/extractor/youku.py index 9d88c17f5..a8fd40c83 100644 --- a/youtube_dl/extractor/youku.py +++ b/youtube_dl/extractor/youku.py @@ -18,7 +18,7 @@ class YoukuIE(InfoExtractor): u"url": u"http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html", u"file": u"XNDgyMDQ2NTQw_part00.flv", u"md5": u"ffe3f2e435663dc2d1eea34faeff5b5b", - u"params": { u"test": False }, + u"params": {u"test": False}, u"info_dict": { u"title": u"youtube-dl test video \"'/\\ä↭𝕐" } @@ -37,8 +37,8 @@ class YoukuIE(InfoExtractor): source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890") seed = float(seed) for i in range(len(source)): - seed = (seed * 211 + 30031 ) % 65536 - index = math.floor(seed / 65536 * len(source) ) + seed = (seed * 211 + 30031) % 65536 + index = math.floor(seed / 65536 * len(source)) mixed.append(source[int(index)]) source.remove(source[int(index)]) #return ''.join(mixed) diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index e46a9b4d6..bd0f2cae0 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -81,14 +81,14 @@ class YouPornIE(InfoExtractor): # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0 # A path looks like this: # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4 - video_url = unescapeHTML( link ) - path = compat_urllib_parse_urlparse( video_url ).path - extension = os.path.splitext( path )[1][1:] + video_url = unescapeHTML(link) + path = compat_urllib_parse_urlparse(video_url).path + extension = os.path.splitext(path)[1][1:] format = path.split('/')[4].split('_')[:2] # size = format[0] # bitrate = format[1] - format = "-".join( format ) + format = "-".join(format) # title = u'%s-%s-%s' % (video_title, size, bitrate) formats.append({ diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index dc601de52..c992cba97 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -340,18 +340,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): } }, { - u"url": u"http://www.youtube.com/watch?v=1ltcDfZMA3U", - u"file": u"1ltcDfZMA3U.mp4", - u"note": u"Test VEVO video (#897)", - u"info_dict": { - u"upload_date": u"20070518", - u"title": u"Maps - It Will Find You", - u"description": u"Music video by Maps performing It Will Find You.", - u"uploader": u"MuteUSA", - u"uploader_id": u"MuteUSA" - } - }, - { u"url": u"http://www.youtube.com/watch?v=UxxajLWwzqY", u"file": u"UxxajLWwzqY.mp4", u"note": u"Test generic use_cipher_signature video (#897)", @@ -1094,7 +1082,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): else: raise ExtractorError(u'Unable to decrypt signature, key length %d not supported; retrying might work' % (len(s))) - def _get_available_subtitles(self, video_id): + def _get_available_subtitles(self, video_id, webpage): try: sub_list = self._download_webpage( 'http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, @@ -1497,7 +1485,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'subtitles': video_subtitles, 'duration': video_duration, 'age_limit': 18 if age_gate else 0, - 'annotations': video_annotations + 'annotations': video_annotations, + 'webpage_url': 'https://www.youtube.com/watch?v=%s' % video_id, }) return results @@ -1583,7 +1572,6 @@ class YoutubePlaylistIE(InfoExtractor): class YoutubeChannelIE(InfoExtractor): IE_DESC = u'YouTube.com channels' _VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)" - _TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en' _MORE_PAGES_INDICATOR = 'yt-uix-load-more' _MORE_PAGES_URL = 'http://www.youtube.com/c4_browse_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s' IE_NAME = u'youtube:channel' @@ -1604,30 +1592,20 @@ class YoutubeChannelIE(InfoExtractor): # Download channel page channel_id = mobj.group(1) video_ids = [] - pagenum = 1 - - url = self._TEMPLATE_URL % (channel_id, pagenum) - page = self._download_webpage(url, channel_id, - u'Downloading page #%s' % pagenum) - # Extract video identifiers - ids_in_page = self.extract_videos_from_page(page) - video_ids.extend(ids_in_page) + # Download all channel pages using the json-based channel_ajax query + for pagenum in itertools.count(1): + url = self._MORE_PAGES_URL % (pagenum, channel_id) + page = self._download_webpage(url, channel_id, + u'Downloading page #%s' % pagenum) - # Download any subsequent channel pages using the json-based channel_ajax query - if self._MORE_PAGES_INDICATOR in page: - for pagenum in itertools.count(1): - url = self._MORE_PAGES_URL % (pagenum, channel_id) - page = self._download_webpage(url, channel_id, - u'Downloading page #%s' % pagenum) + page = json.loads(page) - page = json.loads(page) - - ids_in_page = self.extract_videos_from_page(page['content_html']) - video_ids.extend(ids_in_page) + ids_in_page = self.extract_videos_from_page(page['content_html']) + video_ids.extend(ids_in_page) - if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']: - break + if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']: + break self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids))) @@ -1743,6 +1721,10 @@ class YoutubeSearchIE(SearchInfoExtractor): videos = [self.url_result('http://www.youtube.com/watch?v=%s' % id, 'Youtube') for id in video_ids] return self.playlist_result(videos, query) +class YoutubeSearchDateIE(YoutubeSearchIE): + _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' class YoutubeShowIE(InfoExtractor): IE_DESC = u'YouTube.com (multi-season) shows' diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 75a46a2d5..84bf0f35c 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,2 +1,2 @@ -__version__ = '2013.11.02' +__version__ = '2013.11.07' |