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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     float_or_none,
   8     get_element_by_attribute,
   9     parse_iso8601,
  10     remove_end,
  11 )
  12
  13
  14 class XuiteIE(InfoExtractor):
  15     IE_DESC = '隨意窩Xuite影音'
  16     _REGEX_BASE64 = r'(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?'
  17     _VALID_URL = r'https?://vlog\.xuite\.net/(?:play|embed)/(?P<id>%s)' % _REGEX_BASE64
  18     _TESTS = [{
  19         # Audio
  20         'url': 'http://vlog.xuite.net/play/RGkzc1ZULTM4NjA5MTQuZmx2',
  21         'md5': 'e79284c87b371424885448d11f6398c8',
  22         'info_dict': {
  23             'id': '3860914',
  24             'ext': 'mp3',
  25             'title': '孤單南半球-歐德陽',
  26             'description': '孤單南半球-歐德陽',
  27             'thumbnail': r're:^https?://.*\.jpg$',
  28             'duration': 247.246,
  29             'timestamp': 1314932940,
  30             'upload_date': '20110902',
  31             'uploader': '阿能',
  32             'uploader_id': '15973816',
  33             'categories': ['個人短片'],
  34         },
  35     }, {
  36         # Video with only one format
  37         'url': 'http://vlog.xuite.net/play/WUxxR2xCLTI1OTI1MDk5LmZsdg==',
  38         'md5': '21f7b39c009b5a4615b4463df6eb7a46',
  39         'info_dict': {
  40             'id': '25925099',
  41             'ext': 'mp4',
  42             'title': 'BigBuckBunny_320x180',
  43             'thumbnail': r're:^https?://.*\.jpg$',
  44             'duration': 596.458,
  45             'timestamp': 1454242500,
  46             'upload_date': '20160131',
  47             'uploader': '屁姥',
  48             'uploader_id': '12158353',
  49             'categories': ['個人短片'],
  50             'description': 'http://download.blender.org/peach/bigbuckbunny_movies/BigBuckBunny_320x180.mp4',
  51         },
  52     }, {
  53         # Video with two formats
  54         'url': 'http://vlog.xuite.net/play/bWo1N1pLLTIxMzAxMTcwLmZsdg==',
  55         'md5': '1166e0f461efe55b62e26a2d2a68e6de',
  56         'info_dict': {
  57             'id': '21301170',
  58             'ext': 'mp4',
  59             'title': '暗殺教室 02',
  60             'description': '字幕:【極影字幕社】',
  61             'thumbnail': r're:^https?://.*\.jpg$',
  62             'duration': 1384.907,
  63             'timestamp': 1421481240,
  64             'upload_date': '20150117',
  65             'uploader': '我只是想認真點',
  66             'uploader_id': '242127761',
  67             'categories': ['電玩動漫'],
  68         },
  69         'skip': 'Video removed',
  70     }, {
  71         # Video with encoded media id
  72         # from http://forgetfulbc.blogspot.com/2016/06/date.html
  73         'url': 'http://vlog.xuite.net/embed/cE1xbENoLTI3NDQ3MzM2LmZsdg==?ar=0&as=0',
  74         'info_dict': {
  75             'id': '27447336',
  76             'ext': 'mp4',
  77             'title': '男女平權只是口號？專家解釋約會時男生是否該幫女生付錢 (中字)',
  78             'description': 'md5:1223810fa123b179083a3aed53574706',
  79             'timestamp': 1466160960,
  80             'upload_date': '20160617',
  81             'uploader': 'B.C. & Lowy',
  82             'uploader_id': '232279340',
  83         },
  84     }, {
  85         'url': 'http://vlog.xuite.net/play/S1dDUjdyLTMyOTc3NjcuZmx2/%E5%AD%AB%E7%87%95%E5%A7%BF-%E7%9C%BC%E6%B7%9A%E6%88%90%E8%A9%A9',
  86         'only_matching': True,
  87     }]
  88
  89     def _real_extract(self, url):
  90         # /play/ URLs provide embedded video URL and more metadata
  91         url = url.replace('/embed/', '/play/')
  92         video_id = self._match_id(url)
  93
  94         webpage = self._download_webpage(url, video_id)
  95
  96         error_msg = self._search_regex(
  97             r'<div id="error-message-content">([^<]+)',
  98             webpage, 'error message', default=None)
  99         if error_msg:
 100             raise ExtractorError(
 101                 '%s returned error: %s' % (self.IE_NAME, error_msg),
 102                 expected=True)
 103
 104         media_info = self._parse_json(self._search_regex(
 105             r'var\s+mediaInfo\s*=\s*({.*});', webpage, 'media info'), video_id)
 106
 107         video_id = media_info['MEDIA_ID']
 108
 109         formats = []
 110         for key in ('html5Url', 'html5HQUrl'):
 111             video_url = media_info.get(key)
 112             if not video_url:
 113                 continue
 114             format_id = self._search_regex(
 115                 r'\bq=(.+?)\b', video_url, 'format id', default=None)
 116             formats.append({
 117                 'url': video_url,
 118                 'ext': 'mp4' if format_id.isnumeric() else format_id,
 119                 'format_id': format_id,
 120                 'height': int(format_id) if format_id.isnumeric() else None,
 121             })
 122         self._sort_formats(formats)
 123
 124         timestamp = media_info.get('PUBLISH_DATETIME')
 125         if timestamp:
 126             timestamp = parse_iso8601(timestamp + ' +0800', ' ')
 127
 128         category = media_info.get('catName')
 129         categories = [category] if category else []
 130
 131         uploader = media_info.get('NICKNAME')
 132         uploader_url = None
 133
 134         author_div = get_element_by_attribute('itemprop', 'author', webpage)
 135         if author_div:
 136             uploader = uploader or self._html_search_meta('name', author_div)
 137             uploader_url = self._html_search_regex(
 138                 r'<link[^>]+itemprop="url"[^>]+href="([^"]+)"', author_div,
 139                 'uploader URL', fatal=False)
 140
 141         return {
 142             'id': video_id,
 143             'title': media_info['TITLE'],
 144             'description': remove_end(media_info.get('metaDesc'), ' (Xuite 影音)'),
 145             'thumbnail': media_info.get('ogImageUrl'),
 146             'timestamp': timestamp,
 147             'uploader': uploader,
 148             'uploader_id': media_info.get('MEMBER_ID'),
 149             'uploader_url': uploader_url,
 150             'duration': float_or_none(media_info.get('MEDIA_DURATION'), 1000000),
 151             'categories': categories,
 152             'formats': formats,
 153         }