diff options
| -rwxr-xr-x | youtube-dl.exe | bin | 3989787 -> 3992216 bytes | |||
| -rw-r--r-- | youtube_dl/InfoExtractors.py | 175 | ||||
| -rw-r--r-- | youtube_dl/__init__.py | 1 |
3 files changed, 148 insertions, 28 deletions
diff --git a/youtube-dl.exe b/youtube-dl.exe Binary files differindex 2aa052ccf..fbed2841a 100755 --- a/youtube-dl.exe +++ b/youtube-dl.exe diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 56003df26..ff5c47726 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -13,6 +13,8 @@ import urllib import urllib2 import email.utils import xml.etree.ElementTree +import random +import math from urlparse import parse_qs try: @@ -95,7 +97,7 @@ class InfoExtractor(object): class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|tube.majestyc.net/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$' + _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|tube\.majestyc\.net/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$' _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' @@ -2956,6 +2958,129 @@ class MTVIE(InfoExtractor): return [info] + +class YoukuIE(InfoExtractor): + + _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html' + IE_NAME = u'Youku' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, file_id): + """Report webpage download.""" + self._downloader.to_screen(u'[Youku] %s: Downloading webpage' % file_id) + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[Youku] %s: Extracting information' % file_id) + + def _gen_sid(self): + nowTime = int(time.time() * 1000) + random1 = random.randint(1000,1998) + random2 = random.randint(1000,9999) + + return "%d%d%d" %(nowTime,random1,random2) + + def _get_file_ID_mix_string(self, seed): + mixed = [] + 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) ) + mixed.append(source[int(index)]) + source.remove(source[int(index)]) + #return ''.join(mixed) + return mixed + + def _get_file_id(self, fileId, seed): + mixed = self._get_file_ID_mix_string(seed) + ids = fileId.split('*') + realId = [] + for ch in ids: + if ch: + realId.append(mixed[int(ch)]) + return ''.join(realId) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group('ID') + + info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id + + request = urllib2.Request(info_url, None, std_headers) + try: + self.report_download_webpage(video_id) + jsondata = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + + self.report_extraction(video_id) + try: + config = json.loads(jsondata) + + video_title = config['data'][0]['title'] + seed = config['data'][0]['seed'] + + format = self._downloader.params.get('format', None) + supported_format = config['data'][0]['streamfileids'].keys() + + if format is None or format == 'best': + if 'hd2' in supported_format: + format = 'hd2' + else: + format = 'flv' + ext = u'flv' + elif format == 'worst': + format = 'mp4' + ext = u'mp4' + else: + format = 'flv' + ext = u'flv' + + + fileid = config['data'][0]['streamfileids'][format] + seg_number = len(config['data'][0]['segs'][format]) + + keys=[] + for i in xrange(seg_number): + keys.append(config['data'][0]['segs'][format][i]['k']) + + #TODO check error + #youku only could be viewed from mainland china + except: + self._downloader.trouble(u'ERROR: unable to extract info section') + return + + files_info=[] + sid = self._gen_sid() + fileid = self._get_file_id(fileid, seed) + + #column 8,9 of fileid represent the segment number + #fileid[7:9] should be changed + for index, key in enumerate(keys): + + temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:]) + download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key) + + info = { + 'id': '%s_part%02d' % (video_id, index), + 'url': download_url, + 'uploader': None, + 'title': video_title, + 'ext': ext, + 'format': u'NA' + } + files_info.append(info) + + return files_info + + class XNXXIE(InfoExtractor): """Information extractor for xnxx.com""" @@ -2973,30 +3098,6 @@ class XNXXIE(InfoExtractor): """Report information extraction""" self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) - def extract_video_url(self, webpage): - "Extract the url for the video from the webpage" - - result = re.search(self.VIDEO_URL_RE, webpage) - if result is None: - self._downloader.trouble(u'ERROR: unable to extract video url') - return urllib.unquote(result.group(1).decode('utf-8')) - - def extract_video_title(self, webpage): - "Extract the title for the video from the webpage" - - result = re.search(self.VIDEO_TITLE_RE, webpage) - if result is None: - self._downloader.trouble(u'ERROR: unable to extract video title') - return result.group(1).decode('utf-8') - - def extract_video_thumbnail(self, webpage): - "Extract the thumbnail for the video from the webpage" - - result = re.search(self.VIDEO_THUMB_RE, webpage) - if result is None: - self._downloader.trouble(u'ERROR: unable to extract video thumbnail') - return result.group(1).decode('utf-8') - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj is None: @@ -3013,14 +3114,32 @@ class XNXXIE(InfoExtractor): self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) return + result = re.search(self.VIDEO_URL_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video url') + return + video_url = urllib.unquote(result.group(1).decode('utf-8')) + + result = re.search(self.VIDEO_TITLE_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = result.group(1).decode('utf-8') + + result = re.search(self.VIDEO_THUMB_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = result.group(1).decode('utf-8') + info = {'id': video_id, - 'url': self.extract_video_url(webpage), + 'url': video_url, 'uploader': None, 'upload_date': None, - 'title': self.extract_video_title(webpage), + 'title': video_title, 'ext': 'flv', 'format': 'flv', - 'thumbnail': self.extract_video_thumbnail(webpage), + 'thumbnail': video_thumbnail, 'description': None, 'player_url': None} diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 0f9d73c46..5ed453bf7 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -351,6 +351,7 @@ def gen_extractors(): MixcloudIE(), StanfordOpenClassroomIE(), MTVIE(), + YoukuIE(), XNXXIE(), GenericIE() |