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

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import base64
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_urllib_parse_unquote
   8 from ..utils import (
   9     ExtractorError,
  10     parse_iso8601,
  11     parse_duration,
  12 )
  13
  14
  15 class XuiteIE(InfoExtractor):
  16     IE_DESC = '隨意窩Xuite影音'
  17     _REGEX_BASE64 = r'(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?'
  18     _VALID_URL = r'https?://vlog\.xuite\.net/(?:play|embed)/(?P<id>%s)' % _REGEX_BASE64
  19     _TESTS = [{
  20         # Audio
  21         'url': 'http://vlog.xuite.net/play/RGkzc1ZULTM4NjA5MTQuZmx2',
  22         'md5': 'e79284c87b371424885448d11f6398c8',
  23         'info_dict': {
  24             'id': '3860914',
  25             'ext': 'mp3',
  26             'title': '孤單南半球-歐德陽',
  27             'thumbnail': 're:^https?://.*\.jpg$',
  28             'duration': 247.246,
  29             'timestamp': 1314932940,
  30             'upload_date': '20110902',
  31             'uploader': '阿能',
  32             'uploader_id': '15973816',
  33             'categories': ['個人短片'],
  34         },
  35     }, {
  36         # Video with only one format
  37         'url': 'http://vlog.xuite.net/play/WUxxR2xCLTI1OTI1MDk5LmZsdg==',
  38         'md5': '21f7b39c009b5a4615b4463df6eb7a46',
  39         'info_dict': {
  40             'id': '25925099',
  41             'ext': 'mp4',
  42             'title': 'BigBuckBunny_320x180',
  43             'thumbnail': 're:^https?://.*\.jpg$',
  44             'duration': 596.458,
  45             'timestamp': 1454242500,
  46             'upload_date': '20160131',
  47             'uploader': 'yan12125',
  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': '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         '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',
  72         'only_matching': True,
  73     }]
  74
  75     @staticmethod
  76     def base64_decode_utf8(data):
  77         return base64.b64decode(data.encode('utf-8')).decode('utf-8')
  78
  79     @staticmethod
  80     def base64_encode_utf8(data):
  81         return base64.b64encode(data.encode('utf-8')).decode('utf-8')
  82
  83     def _extract_flv_config(self, media_id):
  84         base64_media_id = self.base64_encode_utf8(media_id)
  85         flv_config = self._download_xml(
  86             'http://vlog.xuite.net/flash/player?media=%s' % base64_media_id,
  87             'flv config')
  88         prop_dict = {}
  89         for prop in flv_config.findall('./property'):
  90             prop_id = self.base64_decode_utf8(prop.attrib['id'])
  91             # CDATA may be empty in flv config
  92             if not prop.text:
  93                 continue
  94             encoded_content = self.base64_decode_utf8(prop.text)
  95             prop_dict[prop_id] = compat_urllib_parse_unquote(encoded_content)
  96         return prop_dict
  97
  98     def _real_extract(self, url):
  99         video_id = self._match_id(url)
 100
 101         webpage = self._download_webpage(url, video_id)
 102
 103         error_msg = self._search_regex(
 104             r'<div id="error-message-content">([^<]+)',
 105             webpage, 'error message', default=None)
 106         if error_msg:
 107             raise ExtractorError(
 108                 '%s returned error: %s' % (self.IE_NAME, error_msg),
 109                 expected=True)
 110
 111         video_id = self._html_search_regex(
 112             r'data-mediaid="(\d+)"', webpage, 'media id')
 113         flv_config = self._extract_flv_config(video_id)
 114
 115         FORMATS = {
 116             'audio': 'mp3',
 117             'video': 'mp4',
 118         }
 119
 120         formats = []
 121         for format_tag in ('src', 'hq_src'):
 122             video_url = flv_config.get(format_tag)
 123             if not video_url:
 124                 continue
 125             format_id = self._search_regex(
 126                 r'\bq=(.+?)\b', video_url, 'format id', default=format_tag)
 127             formats.append({
 128                 'url': video_url,
 129                 'ext': FORMATS.get(flv_config['type'], 'mp4'),
 130                 'format_id': format_id,
 131                 'height': int(format_id) if format_id.isnumeric() else None,
 132             })
 133         self._sort_formats(formats)
 134
 135         timestamp = flv_config.get('publish_datetime')
 136         if timestamp:
 137             timestamp = parse_iso8601(timestamp + ' +0800', ' ')
 138
 139         category = flv_config.get('category')
 140         categories = [category] if category else []
 141
 142         return {
 143             'id': video_id,
 144             'title': flv_config['title'],
 145             'description': flv_config.get('description'),
 146             'thumbnail': flv_config.get('thumb'),
 147             'timestamp': timestamp,
 148             'uploader': flv_config.get('author_name'),
 149             'uploader_id': flv_config.get('author_id'),
 150             'duration': parse_duration(flv_config.get('duration')),
 151             'categories': categories,
 152             'formats': formats,
 153         }