youtube_dl/extractor/springboardplatform.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     int_or_none,
  10     xpath_attr,
  11     xpath_text,
  12     xpath_element,
  13     unescapeHTML,
  14     unified_timestamp,
  15 )
  16
  17
  18 class SpringboardPlatformIE(InfoExtractor):
  19     _VALID_URL = r'''(?x)
  20                     https?://
  21                         cms\.springboardplatform\.com/
  22                         (?:
  23                             (?:previews|embed_iframe)/(?P<index>\d+)/video/(?P<id>\d+)|
  24                             xml_feeds_advanced/index/(?P<index_2>\d+)/rss3/(?P<id_2>\d+)
  25                         )
  26                     '''
  27     _TESTS = [{
  28         'url': 'http://cms.springboardplatform.com/previews/159/video/981017/0/0/1',
  29         'md5': '5c3cb7b5c55740d482561099e920f192',
  30         'info_dict': {
  31             'id': '981017',
  32             'ext': 'mp4',
  33             'title': 'Redman "BUD like YOU" "Usher Good Kisser" REMIX',
  34             'description': 'Redman "BUD like YOU" "Usher Good Kisser" REMIX',
  35             'thumbnail': r're:^https?://.*\.jpg$',
  36             'timestamp': 1409132328,
  37             'upload_date': '20140827',
  38             'duration': 193,
  39         },
  40     }, {
  41         'url': 'http://cms.springboardplatform.com/embed_iframe/159/video/981017/rab007/rapbasement.com/1/1',
  42         'only_matching': True,
  43     }, {
  44         'url': 'http://cms.springboardplatform.com/embed_iframe/20/video/1731611/ki055/kidzworld.com/10',
  45         'only_matching': True,
  46     }, {
  47         'url': 'http://cms.springboardplatform.com/xml_feeds_advanced/index/159/rss3/981017/0/0/1/',
  48         'only_matching': True,
  49     }]
  50
  51     @staticmethod
  52     def _extract_urls(webpage):
  53         return [
  54             mobj.group('url')
  55             for mobj in re.finditer(
  56                 r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//cms\.springboardplatform\.com/embed_iframe/\d+/video/\d+.*?)\1',
  57                 webpage)]
  58
  59     def _real_extract(self, url):
  60         mobj = re.match(self._VALID_URL, url)
  61         video_id = mobj.group('id') or mobj.group('id_2')
  62         index = mobj.group('index') or mobj.group('index_2')
  63
  64         video = self._download_xml(
  65             'http://cms.springboardplatform.com/xml_feeds_advanced/index/%s/rss3/%s'
  66             % (index, video_id), video_id)
  67
  68         item = xpath_element(video, './/item', 'item', fatal=True)
  69
  70         content = xpath_element(
  71             item, './{http://search.yahoo.com/mrss/}content', 'content',
  72             fatal=True)
  73         title = unescapeHTML(xpath_text(item, './title', 'title', fatal=True))
  74
  75         video_url = content.attrib['url']
  76
  77         if 'error_video.mp4' in video_url:
  78             raise ExtractorError(
  79                 'Video %s no longer exists' % video_id, expected=True)
  80
  81         duration = int_or_none(content.get('duration'))
  82         tbr = int_or_none(content.get('bitrate'))
  83         filesize = int_or_none(content.get('fileSize'))
  84         width = int_or_none(content.get('width'))
  85         height = int_or_none(content.get('height'))
  86
  87         description = unescapeHTML(xpath_text(
  88             item, './description', 'description'))
  89         thumbnail = xpath_attr(
  90             item, './{http://search.yahoo.com/mrss/}thumbnail', 'url',
  91             'thumbnail')
  92
  93         timestamp = unified_timestamp(xpath_text(
  94             item, './{http://cms.springboardplatform.com/namespaces.html}created',
  95             'timestamp'))
  96
  97         formats = [{
  98             'url': video_url,
  99             'format_id': 'http',
 100             'tbr': tbr,
 101             'filesize': filesize,
 102             'width': width,
 103             'height': height,
 104         }]
 105
 106         m3u8_format = formats[0].copy()
 107         m3u8_format.update({
 108             'url': re.sub(r'(https?://)cdn\.', r'\1hls.', video_url) + '.m3u8',
 109             'ext': 'mp4',
 110             'format_id': 'hls',
 111             'protocol': 'm3u8_native',
 112         })
 113         formats.append(m3u8_format)
 114
 115         self._sort_formats(formats)
 116
 117         return {
 118             'id': video_id,
 119             'title': title,
 120             'description': description,
 121             'thumbnail': thumbnail,
 122             'timestamp': timestamp,
 123             'duration': duration,
 124             'formats': formats,
 125         }