X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fafreecatv.py;h=75b36699363609876c755d4c120ec195aa81ec3a;hb=073d5bf583e8ff8ae71efca5fc6fae0743ac8961;hp=9f9399edc3b1403b2c9775e994ca56f410f126d9;hpb=833b644fffae4d4cb0807591006e34ef963d9bc0;p=youtube-dl diff --git a/youtube_dl/extractor/afreecatv.py b/youtube_dl/extractor/afreecatv.py index 9f9399edc..75b366993 100644 --- a/youtube_dl/extractor/afreecatv.py +++ b/youtube_dl/extractor/afreecatv.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..compat import ( compat_urllib_parse_urlparse, @@ -9,30 +11,81 @@ from ..compat import ( from ..utils import ( ExtractorError, int_or_none, + update_url_query, + xpath_element, xpath_text, ) class AfreecaTVIE(InfoExtractor): IE_DESC = 'afreecatv.com' - _VALID_URL = r'''(?x)^ - https?://(?:(live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)? - (?: - /app/(?:index|read_ucc_bbs)\.cgi| - /player/[Pp]layer\.(?:swf|html)) - \?.*?\bnTitleNo=(?P\d+)''' - _TEST = { + _VALID_URL = r'''(?x) + https?:// + (?: + (?:(?:live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)? + (?: + /app/(?:index|read_ucc_bbs)\.cgi| + /player/[Pp]layer\.(?:swf|html) + )\?.*?\bnTitleNo=| + vod\.afreecatv\.com/PLAYER/STATION/ + ) + (?P\d+) + ''' + _TESTS = [{ 'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=', 'md5': 'f72c89fe7ecc14c1b5ce506c4996046e', 'info_dict': { 'id': '36164052', 'ext': 'mp4', 'title': '데일리 에이프릴 요정들의 시상식!', - 'thumbnail': 're:^https?://videoimg.afreecatv.com/.*$', + 'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$', 'uploader': 'dailyapril', 'uploader_id': 'dailyapril', + 'upload_date': '20160503', } - } + }, { + 'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867', + 'info_dict': { + 'id': '36153164', + 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'", + 'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$', + 'uploader': 'dailyapril', + 'uploader_id': 'dailyapril', + }, + 'playlist_count': 2, + 'playlist': [{ + 'md5': 'd8b7c174568da61d774ef0203159bf97', + 'info_dict': { + 'id': '36153164_1', + 'ext': 'mp4', + 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'", + 'upload_date': '20160502', + }, + }, { + 'md5': '58f2ce7f6044e34439ab2d50612ab02b', + 'info_dict': { + 'id': '36153164_2', + 'ext': 'mp4', + 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'", + 'upload_date': '20160502', + }, + }], + }, { + 'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652', + 'only_matching': True, + }, { + 'url': 'http://vod.afreecatv.com/PLAYER/STATION/15055030', + 'only_matching': True, + }] + + @staticmethod + def parse_video_key(key): + video_key = {} + m = re.match(r'^(?P\d{8})_\w+_(?P\d+)$', key) + if m: + video_key['upload_date'] = m.group('upload_date') + video_key['part'] = m.group('part') + return video_key def _real_extract(self, url): video_id = self._match_id(url) @@ -40,11 +93,14 @@ class AfreecaTVIE(InfoExtractor): info_url = compat_urlparse.urlunparse(parsed_url._replace( netloc='afbbs.afreecatv.com:8080', path='/api/video/get_video_info.php')) - video_xml = self._download_xml(info_url, video_id) - if xpath_text(video_xml, './track/flag', default='FAIL') != 'SUCCEED': + video_xml = self._download_xml( + update_url_query(info_url, {'nTitleNo': video_id}), video_id) + + if xpath_element(video_xml, './track/video/file') is None: raise ExtractorError('Specified AfreecaTV video does not exist', expected=True) + title = xpath_text(video_xml, './track/title', 'title') uploader = xpath_text(video_xml, './track/nickname', 'uploader') uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id') @@ -53,12 +109,16 @@ class AfreecaTVIE(InfoExtractor): thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail') entries = [] - for video_file in video_xml.findall('./track/video/file'): + for i, video_file in enumerate(video_xml.findall('./track/video/file')): + video_key = self.parse_video_key(video_file.get('key', '')) + if not video_key: + continue entries.append({ - 'id': video_file.get('key'), + 'id': '%s_%s' % (video_id, video_key.get('part', i + 1)), 'title': title, + 'upload_date': video_key.get('upload_date'), 'duration': int_or_none(video_file.get('duration')), - 'formats': [{'url': video_file.text}] + 'url': video_file.text, }) info = { @@ -74,7 +134,8 @@ class AfreecaTVIE(InfoExtractor): info['_type'] = 'multi_video' info['entries'] = entries elif len(entries) == 1: - info['formats'] = entries[0]['formats'] + info['url'] = entries[0]['url'] + info['upload_date'] = entries[0].get('upload_date') else: raise ExtractorError( 'No files found for the specified AfreecaTV video, either'