From 9c286cfa004d18da196a6961ffda30bb9bf57515 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 23 Jun 2013 22:01:02 +0200 Subject: [PATCH] Move Youku IE into its own file --- youtube_dl/InfoExtractors.py | 93 +----------------------------- youtube_dl/extractor/youku.py | 104 ++++++++++++++++++++++++++++++++++ 2 files changed, 105 insertions(+), 92 deletions(-) create mode 100644 youtube_dl/extractor/youku.py diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 1b7e5649d..31f5254cf 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -45,6 +45,7 @@ from .extractor.ted import TEDIE from .extractor.vimeo import VimeoIE from .extractor.xvideos import XVideosIE from .extractor.yahoo import YahooIE, YahooSearchIE +from .extractor.youku import YoukuIE from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE from .extractor.zdf import ZDFIE @@ -54,98 +55,6 @@ from .extractor.zdf import ZDFIE -class YoukuIE(InfoExtractor): - _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P[A-Za-z0-9]+)\.html' - - 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: - raise ExtractorError(u'Invalid URL: %s' % url) - video_id = mobj.group('ID') - - info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id - - jsondata = self._download_webpage(info_url, video_id) - - 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 = list(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] - keys = [s['k'] for s in config['data'][0]['segs'][format]] - except (UnicodeDecodeError, ValueError, KeyError): - raise ExtractorError(u'Unable to extract info section') - - 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, - 'upload_date': None, - 'title': video_title, - 'ext': ext, - } - files_info.append(info) - - return files_info class XNXXIE(InfoExtractor): diff --git a/youtube_dl/extractor/youku.py b/youtube_dl/extractor/youku.py new file mode 100644 index 000000000..ed43f42be --- /dev/null +++ b/youtube_dl/extractor/youku.py @@ -0,0 +1,104 @@ +import json +import math +import random +import re +import time + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, +) + + +class YoukuIE(InfoExtractor): + _VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P[A-Za-z0-9]+)\.html' + + 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: + raise ExtractorError(u'Invalid URL: %s' % url) + video_id = mobj.group('ID') + + info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id + + jsondata = self._download_webpage(info_url, video_id) + + 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 = list(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] + keys = [s['k'] for s in config['data'][0]['segs'][format]] + except (UnicodeDecodeError, ValueError, KeyError): + raise ExtractorError(u'Unable to extract info section') + + 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, + 'upload_date': None, + 'title': video_title, + 'ext': ext, + } + files_info.append(info) + + return files_info