X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Faparat.py;h=025e29aa46fe5db97c323fa95d947470f1f2023a;hb=853a71b628bbf1626c301dc66f496464ad796b2e;hp=74860882628017c5ab7a44f22bd9b05286ad556e;hpb=9480d1a56674f95f135562d2133cbf12f6a96bbc;p=youtube-dl diff --git a/youtube_dl/extractor/aparat.py b/youtube_dl/extractor/aparat.py index 748608826..025e29aa4 100644 --- a/youtube_dl/extractor/aparat.py +++ b/youtube_dl/extractor/aparat.py @@ -1,9 +1,6 @@ -#coding: utf-8 - +# coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( ExtractorError, @@ -16,39 +13,40 @@ class AparatIE(InfoExtractor): _TEST = { 'url': 'http://www.aparat.com/v/wP8On', - 'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1', + 'md5': '131aca2e14fe7c4dcb3c4877ba300c89', 'info_dict': { 'id': 'wP8On', 'ext': 'mp4', 'title': 'تیم گلکسی 11 - زومیت', + 'age_limit': 0, }, # 'skip': 'Extremely unreliable', } def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('id') + video_id = self._match_id(url) # Note: There is an easier-to-parse configuration at # http://www.aparat.com/video/video/config/videohash/%video_id # but the URL in there does not work - embed_url = ('http://www.aparat.com/video/video/embed/videohash/' + - video_id + '/vt/frame') + embed_url = 'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id webpage = self._download_webpage(embed_url, video_id) - video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage) - for i, video_url in enumerate(video_urls): + file_list = self._parse_json(self._search_regex( + r'fileList\s*=\s*JSON\.parse\(\'([^\']+)\'\)', webpage, 'file list'), video_id) + for i, item in enumerate(file_list[0]): + video_url = item['file'] req = HEADRequest(video_url) res = self._request_webpage( - req, video_id, note=u'Testing video URL %d' % i, errnote=False) + req, video_id, note='Testing video URL %d' % i, errnote=False) if res: break else: - raise ExtractorError(u'No working video URLs found') + raise ExtractorError('No working video URLs found') - title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, u'title') + title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title') thumbnail = self._search_regex( - r'\s+image:\s*"([^"]+)"', webpage, u'thumbnail', fatal=False) + r'image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False) return { 'id': video_id, @@ -56,4 +54,5 @@ class AparatIE(InfoExtractor): 'url': video_url, 'ext': 'mp4', 'thumbnail': thumbnail, + 'age_limit': self._family_friendly_search(webpage), }