[teamcoco] Fix extracting preload data again

This commit is contained in:
Yen Chi Hsuan 2015-05-07 02:08:47 +08:00
parent ad0c0ad3b4
commit ac6c358c2a
1 changed files with 21 additions and 3 deletions

View File

@ -2,6 +2,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import base64 import base64
import binascii
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -9,6 +10,7 @@ from ..utils import (
ExtractorError, ExtractorError,
qualities, qualities,
) )
from ..compat import compat_ord
class TeamcocoIE(InfoExtractor): class TeamcocoIE(InfoExtractor):
@ -66,7 +68,7 @@ class TeamcocoIE(InfoExtractor):
video_id = self._html_search_regex( video_id = self._html_search_regex(
self._VIDEO_ID_REGEXES, webpage, 'video id') self._VIDEO_ID_REGEXES, webpage, 'video id')
preload = None data = preload = None
preloads = re.findall(r'"preload":\s*"([^"]+)"', webpage) preloads = re.findall(r'"preload":\s*"([^"]+)"', webpage)
if preloads: if preloads:
preload = max([(len(p), p) for p in preloads])[1] preload = max([(len(p), p) for p in preloads])[1]
@ -80,9 +82,25 @@ class TeamcocoIE(InfoExtractor):
], webpage.replace('","', ''), 'preload data', default=None) ], webpage.replace('","', ''), 'preload data', default=None)
if not preload: if not preload:
preload_codes = self._html_search_regex(
r'(function.+)setTimeout\(function\(\)\{playlist',
webpage, 'preload codes')
base64_fragments = re.findall(r'"([a-zA-z0-9+/=]+)"', preload_codes)
base64_fragments.remove('init')
for i in range(len(base64_fragments)):
cur_sequence = (''.join(base64_fragments[i:] + base64_fragments[:i])).encode('ascii')
try:
raw_data = base64.b64decode(cur_sequence)
except (TypeError, binascii.Error):
continue
if compat_ord(raw_data[0]) == compat_ord('{'):
data = self._parse_json(raw_data.decode('utf-8'), video_id, fatal=False)
if not preload and not data:
raise ExtractorError( raise ExtractorError(
'Preload information could not be extracted', expected=True) 'Preload information could not be extracted', expected=True)
if not data:
data = self._parse_json( data = self._parse_json(
base64.b64decode(preload.encode('ascii')).decode('utf-8'), video_id) base64.b64decode(preload.encode('ascii')).decode('utf-8'), video_id)