[youku] Modernize somewhat

This commit is contained in:
Philipp Hagemeister 2014-09-25 09:58:09 +02:00
parent fec02bcc90
commit 8a32b82e46

View File

@ -1,5 +1,7 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals
import json import json
import math import math
import random import random
@ -13,18 +15,25 @@
class YoukuIE(InfoExtractor): class YoukuIE(InfoExtractor):
_VALID_URL = r'(?:(?:http://)?(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|youku:)(?P<ID>[A-Za-z0-9]+)(?:\.html|/v\.swf|)' _VALID_URL = r'''(?x)
_TEST = { (?:
u"url": u"http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html", http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
u"file": u"XNDgyMDQ2NTQw_part00.flv", youku:)
u"md5": u"ffe3f2e435663dc2d1eea34faeff5b5b", (?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
u"params": {u"test": False}, '''
u"info_dict": { _TEST = {
u"title": u"youtube-dl test video \"'/\\ä↭𝕐" 'url': 'http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html',
'md5': 'ffe3f2e435663dc2d1eea34faeff5b5b',
'params': {
'test': False
},
'info_dict': {
'id': 'XNDgyMDQ2NTQw_part00',
'ext': 'flv',
'title': 'youtube-dl test video "\'/\\ä↭𝕐'
} }
} }
def _gen_sid(self): def _gen_sid(self):
nowTime = int(time.time() * 1000) nowTime = int(time.time() * 1000)
random1 = random.randint(1000,1998) random1 = random.randint(1000,1998)
@ -55,49 +64,42 @@ def _get_file_id(self, fileId, seed):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None: video_id = mobj.group('id')
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('ID')
info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
jsondata = self._download_webpage(info_url, video_id) config = self._download_json(info_url, video_id)
self.report_extraction(video_id) error_code = config['data'][0].get('error_code')
try: if error_code:
config = json.loads(jsondata) # -8 means blocked outside China.
error_code = config['data'][0].get('error_code') error = config['data'][0].get('error') # Chinese and English, separated by newline.
if error_code: raise ExtractorError(error or 'Server reported error %i' % error_code,
# -8 means blocked outside China. expected=True)
error = config['data'][0].get('error') # Chinese and English, separated by newline.
raise ExtractorError(error or u'Server reported error %i' % error_code,
expected=True)
video_title = config['data'][0]['title'] video_title = config['data'][0]['title']
seed = config['data'][0]['seed'] seed = config['data'][0]['seed']
format = self._downloader.params.get('format', None) format = self._downloader.params.get('format', None)
supported_format = list(config['data'][0]['streamfileids'].keys()) supported_format = list(config['data'][0]['streamfileids'].keys())
if format is None or format == 'best': # TODO proper format selection
if 'hd2' in supported_format: if format is None or format == 'best':
format = 'hd2' if 'hd2' in supported_format:
else: format = 'hd2'
format = 'flv'
ext = u'flv'
elif format == 'worst':
format = 'mp4'
ext = u'mp4'
else: else:
format = 'flv' format = 'flv'
ext = u'flv' ext = 'flv'
elif format == 'worst':
format = 'mp4'
ext = 'mp4'
else:
format = 'flv'
ext = 'flv'
fileid = config['data'][0]['streamfileids'][format]
fileid = config['data'][0]['streamfileids'][format] keys = [s['k'] for s in config['data'][0]['segs'][format]]
keys = [s['k'] for s in config['data'][0]['segs'][format]] # segs is usually a dictionary, but an empty *list* if an error occured.
# segs is usually a dictionary, but an empty *list* if an error occured.
except (UnicodeDecodeError, ValueError, KeyError):
raise ExtractorError(u'Unable to extract info section')
files_info=[] files_info=[]
sid = self._gen_sid() sid = self._gen_sid()
@ -106,9 +108,8 @@ def _real_extract(self, url):
#column 8,9 of fileid represent the segment number #column 8,9 of fileid represent the segment number
#fileid[7:9] should be changed #fileid[7:9] should be changed
for index, key in enumerate(keys): for index, key in enumerate(keys):
temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:]) 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) download_url = 'http://k.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
info = { info = {
'id': '%s_part%02d' % (video_id, index), 'id': '%s_part%02d' % (video_id, index),