2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..compat import compat_urlparse
16 class MioMioIE(InfoExtractor):
18 _VALID_URL = r'https?://(?:www\.)?miomio\.tv/watch/cc(?P<id>[0-9]+)'
20 # "type=video" in flashvars
21 'url': 'http://www.miomio.tv/watch/cc88912/',
25 'title': '【SKY】字幕 铠武昭和VS平成 假面骑士大战FEAT战队 魔星字幕组 字幕',
29 # The server provides broken file
30 'skip_download': True,
33 'url': 'http://www.miomio.tv/watch/cc184024/',
36 'title': '《动漫同人插画绘制》',
38 'playlist_mincount': 86,
39 'skip': 'Unable to load videos',
41 'url': 'http://www.miomio.tv/watch/cc173113/',
44 'title': 'The New Macbook 2015 上手试玩与简评'
46 'playlist_mincount': 2,
47 'skip': 'Unable to load videos',
50 'url': 'http://www.miomio.tv/watch/cc273295/',
55 'title': 'アウト×デラックス 20160526',
58 # intermittent HTTP 500
59 'skip_download': True,
63 def _extract_mioplayer(self, webpage, video_id, title, http_headers):
64 xml_config = self._search_regex(
65 r'flashvars="type=(?:sina|video)&(.+?)&',
66 webpage, 'xml config')
68 # skipping the following page causes lags and eventually connection drop-outs
69 self._request_webpage(
70 'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/xml.php?id=%s&r=%s' % (id, random.randint(100, 999)),
73 vid_config_request = sanitized_Request(
74 'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/sina.php?{0}'.format(xml_config),
77 # the following xml contains the actual configuration information on the video file(s)
78 vid_config = self._download_xml(vid_config_request, video_id)
80 if not int_or_none(xpath_text(vid_config, 'timelength')):
81 raise ExtractorError('Unable to load videos!', expected=True)
84 for f in vid_config.findall('./durl'):
85 segment_url = xpath_text(f, 'url', 'video url')
88 order = xpath_text(f, 'order', 'order')
92 segment_id += '-%s' % order
93 segment_title += ' part %s' % order
97 'title': segment_title,
98 'duration': int_or_none(xpath_text(f, 'length', 'duration'), 1000),
99 'http_headers': http_headers,
104 def _real_extract(self, url):
105 video_id = self._match_id(url)
106 webpage = self._download_webpage(url, video_id)
108 title = self._html_search_meta(
109 'description', webpage, 'title', fatal=True)
111 mioplayer_path = self._search_regex(
112 r'src="(/mioplayer(?:_h5)?/[^"]+)"', webpage, 'ref_path')
114 if '_h5' in mioplayer_path:
115 player_url = compat_urlparse.urljoin(url, mioplayer_path)
116 player_webpage = self._download_webpage(
117 player_url, video_id,
118 note='Downloading player webpage', headers={'Referer': url})
119 entries = self._parse_html5_media_entries(player_url, player_webpage)
120 http_headers = {'Referer': player_url}
122 http_headers = {'Referer': 'http://www.miomio.tv%s' % mioplayer_path}
123 entries = self._extract_mioplayer(webpage, video_id, title, http_headers)
125 if len(entries) == 1:
127 segment['id'] = video_id
128 segment['title'] = title
129 segment['http_headers'] = http_headers
133 '_type': 'multi_video',
137 'http_headers': http_headers,