Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/miomio.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import random
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     xpath_text,
   9     int_or_none,
  10     ExtractorError,
  11 )
  12
  13
  14 class MioMioIE(InfoExtractor):
  15     IE_NAME = 'miomio.tv'
  16     _VALID_URL = r'https?://(?:www\.)?miomio\.tv/watch/cc(?P<id>[0-9]+)'
  17     _TESTS = [{
  18         # "type=video" in flashvars
  19         'url': 'http://www.miomio.tv/watch/cc88912/',
  20         'md5': '317a5f7f6b544ce8419b784ca8edae65',
  21         'info_dict': {
  22             'id': '88912',
  23             'ext': 'flv',
  24             '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',
  25             'duration': 5923,
  26         },
  27     }, {
  28         'url': 'http://www.miomio.tv/watch/cc184024/',
  29         'info_dict': {
  30             'id': '43729',
  31             'title': '《动漫同人插画绘制》',
  32         },
  33         'playlist_mincount': 86,
  34         'skip': 'This video takes time too long for retrieving the URL',
  35     }, {
  36         'url': 'http://www.miomio.tv/watch/cc173113/',
  37         'info_dict': {
  38             'id': '173113',
  39             'title': 'The New Macbook 2015 上手试玩与简评'
  40         },
  41         'playlist_mincount': 2,
  42     }]
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46         webpage = self._download_webpage(url, video_id)
  47
  48         title = self._html_search_meta(
  49             'description', webpage, 'title', fatal=True)
  50
  51         mioplayer_path = self._search_regex(
  52             r'src="(/mioplayer/[^"]+)"', webpage, 'ref_path')
  53
  54         xml_config = self._search_regex(
  55             r'flashvars="type=(?:sina|video)&amp;(.+?)&amp;',
  56             webpage, 'xml config')
  57
  58         # skipping the following page causes lags and eventually connection drop-outs
  59         self._request_webpage(
  60             'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/xml.php?id=%s&r=%s' % (id, random.randint(100, 999)),
  61             video_id)
  62
  63         # the following xml contains the actual configuration information on the video file(s)
  64         vid_config = self._download_xml(
  65             'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/sina.php?{0}'.format(xml_config),
  66             video_id)
  67
  68         http_headers = {
  69             'Referer': 'http://www.miomio.tv%s' % mioplayer_path,
  70         }
  71
  72         if not int_or_none(xpath_text(vid_config, 'timelength')):
  73             raise ExtractorError('Unable to load videos!', expected=True)
  74
  75         entries = []
  76         for f in vid_config.findall('./durl'):
  77             segment_url = xpath_text(f, 'url', 'video url')
  78             if not segment_url:
  79                 continue
  80             order = xpath_text(f, 'order', 'order')
  81             segment_id = video_id
  82             segment_title = title
  83             if order:
  84                 segment_id += '-%s' % order
  85                 segment_title += ' part %s' % order
  86             entries.append({
  87                 'id': segment_id,
  88                 'url': segment_url,
  89                 'title': segment_title,
  90                 'duration': int_or_none(xpath_text(f, 'length', 'duration'), 1000),
  91                 'http_headers': http_headers,
  92             })
  93
  94         if len(entries) == 1:
  95             segment = entries[0]
  96             segment['id'] = video_id
  97             segment['title'] = title
  98             return segment
  99
 100         return {
 101             '_type': 'multi_video',
 102             'id': video_id,
 103             'entries': entries,
 104             'title': title,
 105             'http_headers': http_headers,
 106         }