From 52f5889f77e04420634d70145d689660ea6bfe24 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 7 Feb 2016 06:17:40 +0600 Subject: [PATCH] [vlive] Improve and extract more metadata (Closes #8446) --- youtube_dl/extractor/vlive.py | 80 +++++++++++++++++++---------------- 1 file changed, 43 insertions(+), 37 deletions(-) diff --git a/youtube_dl/extractor/vlive.py b/youtube_dl/extractor/vlive.py index 3e1f8ef07..9e2aa58bd 100644 --- a/youtube_dl/extractor/vlive.py +++ b/youtube_dl/extractor/vlive.py @@ -1,32 +1,27 @@ # coding: utf-8 from __future__ import unicode_literals -import hmac -from hashlib import sha1 -from base64 import b64encode -from time import time - from .common import InfoExtractor from ..utils import ( - ExtractorError, - determine_ext, - int_or_none + dict_get, + float_or_none, + int_or_none, ) from ..compat import compat_urllib_parse class VLiveIE(InfoExtractor): IE_NAME = 'vlive' - # vlive.tv/video/ links redirect to www.vlive.tv/video/ - _VALID_URL = r'https?://(?:(www|m)\.)?vlive\.tv/video/(?P[0-9]+)' + _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P[0-9]+)' _TEST = { 'url': 'http://www.vlive.tv/video/1326', 'md5': 'cc7314812855ce56de70a06a27314983', 'info_dict': { 'id': '1326', 'ext': 'mp4', - 'title': '[V] Girl\'s Day\'s Broadcast', - 'creator': 'Girl\'s Day', + 'title': "[V] Girl's Day's Broadcast", + 'creator': "Girl's Day", + 'view_count': int, }, } @@ -34,49 +29,60 @@ class VLiveIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage( - 'http://www.vlive.tv/video/%s' % video_id, - video_id, note='Download video page') + 'http://www.vlive.tv/video/%s' % video_id, video_id) long_video_id = self._search_regex( - r'vlive\.tv\.video\.ajax\.request\.handler\.init\("[0-9]+",\s?"[^"]*",\s?"([^"]+)",\s?"[^"]+",\s?"[^"]*",\s?"[^"]*"\)', webpage, 'long_video_id') + r'vlive\.tv\.video\.ajax\.request\.handler\.init\(\s*"[0-9]+"\s*,\s*"[^"]*"\s*,\s*"([^"]+)"', + webpage, 'long video id') key = self._search_regex( - r'vlive\.tv\.video\.ajax\.request\.handler\.init\("[0-9]+",\s?"[^"]*",\s?"[^"]+",\s?"([^"]+)",\s?"[^"]*",\s?"[^"]*"\)', webpage, 'key') + r'vlive\.tv\.video\.ajax\.request\.handler\.init\(\s*"[0-9]+"\s*,\s*"[^"]*"\s*,\s*"[^"]+"\s*,\s*"([^"]+)"', + webpage, 'key') title = self._og_search_title(webpage) - thumbnail = self._og_search_thumbnail(webpage) - creator = self._html_search_regex( - r'
\s*]+class="name">([^<>]+)', webpage, 'creator',fatal=False) - # doct = document type (xml or json), cpt = caption type (vtt or ttml) - url = "http://global.apis.naver.com/rmcnmv/rmcnmv/vod_play_videoInfo.json?videoId=%s&key=%s&ptc=http&doct=json&cpt=vtt" % (long_video_id, key) - - playinfo = self._download_json(url, video_id, 'Downloading video json') + playinfo = self._download_json( + 'http://global.apis.naver.com/rmcnmv/rmcnmv/vod_play_videoInfo.json?%s' + % compat_urllib_parse.urlencode({ + 'videoId': long_video_id, + 'key': key, + 'ptc': 'http', + 'doct': 'json', # document type (xml or json) + 'cpt': 'vtt', # captions type (vtt or ttml) + }), video_id) - formats = [] - for vid in playinfo.get('videos', {}).get('list', []): - formats.append({ - 'url': vid['source'], - 'ext': 'mp4', - 'abr': vid.get('bitrate', {}).get('audio'), - 'vbr': vid.get('bitrate', {}).get('video'), - 'format_id': vid.get('encodingOption', {}).get('name'), - 'height': int_or_none(vid.get('encodingOption', {}).get('height')), - 'width': int_or_none(vid.get('encodingOption', {}).get('width')), - }) + formats = [{ + 'url': vid['source'], + 'format_id': vid.get('encodingOption', {}).get('name'), + 'abr': float_or_none(vid.get('bitrate', {}).get('audio')), + 'vbr': float_or_none(vid.get('bitrate', {}).get('video')), + 'width': int_or_none(vid.get('encodingOption', {}).get('width')), + 'height': int_or_none(vid.get('encodingOption', {}).get('height')), + 'filesize': int_or_none(vid.get('size')), + } for vid in playinfo.get('videos', {}).get('list', []) if vid.get('source')] self._sort_formats(formats) + thumbnail = self._og_search_thumbnail(webpage) + creator = self._html_search_regex( + r']+class="info_area"[^>]*>\s*]+class="name"[^>]*>([^<]+)', + webpage, 'creator', fatal=False) + + view_count = int_or_none(playinfo.get('meta', {}).get('count')) + subtitles = {} for caption in playinfo.get('captions', {}).get('list', []): - subtitles[caption['language']] = [ - {'ext': determine_ext(caption['source'], default_ext='vtt'), - 'url': caption['source']}] + lang = dict_get(caption, ('language', 'locale', 'country', 'label')) + if lang and caption.get('source'): + subtitles[lang] = [{ + 'ext': 'vtt', + 'url': caption['source']}] return { 'id': video_id, 'title': title, 'creator': creator, 'thumbnail': thumbnail, + 'view_count': view_count, 'formats': formats, 'subtitles': subtitles, }