# coding: utf-8
from __future__ import unicode_literals
-import hmac
-from hashlib import sha1
-from base64 import b64encode
-from time import time
+import re
from .common import InfoExtractor
from ..utils import (
+ dict_get,
ExtractorError,
- determine_ext,
- int_or_none
+ float_or_none,
+ int_or_none,
+ remove_start,
)
-from ..compat import compat_urllib_parse
+from ..compat import compat_urllib_parse_urlencode
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<id>[0-9]+)'
- _TEST = {
+ _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P<id>[0-9]+)'
+ _TESTS = [{
'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 LIVE] Girl's Day's Broadcast",
+ 'creator': "Girl's Day",
+ 'view_count': int,
},
- }
+ }, {
+ 'url': 'http://www.vlive.tv/video/16937',
+ 'info_dict': {
+ 'id': '16937',
+ 'ext': 'mp4',
+ 'title': '[V LIVE] 첸백시 걍방',
+ 'creator': 'EXO',
+ 'view_count': int,
+ 'subtitles': 'mincount:12',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }]
def _real_extract(self, url):
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)
+
+ video_params = self._search_regex(
+ r'\bvlive\.video\.init\(([^)]+)\)',
+ webpage, 'video params')
+ status, _, _, live_params, long_video_id, key = re.split(
+ r'"\s*,\s*"', video_params)[2:8]
+ status = remove_start(status, 'PRODUCT_')
- 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')
+ if status == 'LIVE_ON_AIR' or status == 'BIG_EVENT_ON_AIR':
+ live_params = self._parse_json('"%s"' % live_params, video_id)
+ live_params = self._parse_json(live_params, video_id)
+ return self._live(video_id, webpage, live_params)
+ elif status == 'VOD_ON_AIR' or status == 'BIG_EVENT_INTRO':
+ if long_video_id and key:
+ return self._replay(video_id, webpage, long_video_id, key)
+ else:
+ status = 'COMING_SOON'
- key = self._search_regex(
- r'vlive\.tv\.video\.ajax\.request\.handler\.init\("[0-9]+",\s?"[^"]*",\s?"[^"]+",\s?"([^"]+)",\s?"[^"]*",\s?"[^"]*"\)', webpage, 'key')
+ if status == 'LIVE_END':
+ raise ExtractorError('Uploading for replay. Please wait...',
+ expected=True)
+ elif status == 'COMING_SOON':
+ raise ExtractorError('Coming soon!', expected=True)
+ elif status == 'CANCELED':
+ raise ExtractorError('We are sorry, '
+ 'but the live broadcast has been canceled.',
+ expected=True)
+ else:
+ raise ExtractorError('Unknown status %s' % status)
+ def _get_common_fields(self, webpage):
title = self._og_search_title(webpage)
- thumbnail = self._og_search_thumbnail(webpage)
creator = self._html_search_regex(
- r'<div class="info_area">\s*<strong[^>]+class="name">([^<>]+)</strong>', 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')
+ r'<div[^>]+class="info_area"[^>]*>\s*<a\s+[^>]*>([^<]+)',
+ webpage, 'creator', fatal=False)
+ thumbnail = self._og_search_thumbnail(webpage)
+ return {
+ 'title': title,
+ 'creator': creator,
+ 'thumbnail': thumbnail,
+ }
+ def _live(self, video_id, webpage, live_params):
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')),
- })
+ for vid in live_params.get('resolutions', []):
+ formats.extend(self._extract_m3u8_formats(
+ vid['cdnUrl'], video_id, 'mp4',
+ m3u8_id=vid.get('name'),
+ fatal=False, live=True))
+ self._sort_formats(formats)
+
+ return dict(self._get_common_fields(webpage),
+ id=video_id,
+ formats=formats,
+ is_live=True)
+
+ def _replay(self, video_id, webpage, long_video_id, key):
+ 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 = [{
+ '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)
+ 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, ('locale', 'language', '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,
- 'formats': formats,
- 'subtitles': subtitles,
- }
+ return dict(self._get_common_fields(webpage),
+ id=video_id,
+ formats=formats,
+ view_count=view_count,
+ subtitles=subtitles)
projects / youtube-dl / blobdiff