From 57cf9b7f0689ed7b643ce863427c3211e407e5bf Mon Sep 17 00:00:00 2001 From: Peter Rowlands Date: Thu, 5 May 2016 03:11:04 +0900 Subject: [PATCH] [afreecatv] Add new extractor for afreecatv.com VODs --- youtube_dl/extractor/afreecatv.py | 84 ++++++++++++++++++++++++++++++ youtube_dl/extractor/extractors.py | 1 + 2 files changed, 85 insertions(+) create mode 100644 youtube_dl/extractor/afreecatv.py diff --git a/youtube_dl/extractor/afreecatv.py b/youtube_dl/extractor/afreecatv.py new file mode 100644 index 0000000000..d57546e49b --- /dev/null +++ b/youtube_dl/extractor/afreecatv.py @@ -0,0 +1,84 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse_urlparse, + compat_urlparse, +) +from ..utils import ( + ExtractorError, + int_or_none, +) + + +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 = { + '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/.*$', + 'uploader': 'dailyapril', + 'uploader_id': 'dailyapril', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + parsed_url = compat_urllib_parse_urlparse(url) + 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) + + track = video_xml.find('track') + if track.find('flag').text != 'SUCCEED': + raise ExtractorError('Specified AfreecaTV video does not exist', + expected=True) + title = track.find('title').text + uploader = track.find('nickname').text + uploader_id = track.find('bj_id').text + duration = int_or_none(track.find('duration').text) + thumbnail = track.find('titleImage').text + + entries = [] + for video in track.findall('video'): + for video_file in video.findall('file'): + entries.append({ + 'id': video_file.get('key'), + 'title': title, + 'duration': int_or_none(video_file.get('duration')), + 'formats': [{'url': video_file.text}] + }) + + info = { + 'id': video_id, + 'title': title, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'duration': duration, + 'thumbnail': thumbnail, + } + + if len(entries) > 1: + info['_type'] = 'multi_video' + info['entries'] = entries + elif len(entries) == 1: + info['formats'] = entries[0]['formats'] + else: + raise ExtractorError( + 'No files found for the specified AfreecaTV video, either' + ' the URL is incorrect or the video has been made private.', + expected=True) + + return info diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index ef44313643..f85d75933f 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -16,6 +16,7 @@ from .adobetv import ( AdobeTVVideoIE, ) from .adultswim import AdultSwimIE +from .afreecatv import AfreecaTVIE from .aenetworks import AENetworksIE from .aftonbladet import AftonbladetIE from .airmozilla import AirMozillaIE