_ Git - youtube-dl/blob - youtube_dl/extractor/myspace.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_str,
   9 )
  10
  11
  12 class MySpaceIE(InfoExtractor):
  13     _VALID_URL = r'https?://myspace\.com/([^/]+)/(?P<mediatype>video/[^/]+/|music/song/.*?)(?P<id>\d+)'
  14
  15     _TESTS = [
  16         {
  17             'url': 'https://myspace.com/coldplay/video/viva-la-vida/100008689',
  18             'info_dict': {
  19                 'id': '100008689',
  20                 'ext': 'flv',
  21                 'title': 'Viva La Vida',
  22                 'description': 'The official Viva La Vida video, directed by Hype Williams',
  23                 'uploader': 'Coldplay',
  24                 'uploader_id': 'coldplay',
  25             },
  26             'params': {
  27                 # rtmp download
  28                 'skip_download': True,
  29             },
  30         },
  31         # song
  32         {
  33             'url': 'https://myspace.com/spiderbags/music/song/darkness-in-my-heart-39008454-27041242',
  34             'info_dict': {
  35                 'id': '39008454',
  36                 'ext': 'flv',
  37                 'title': 'Darkness In My Heart',
  38                 'uploader_id': 'spiderbags',
  39             },
  40             'params': {
  41                 # rtmp download
  42                 'skip_download': True,
  43             },
  44         },
  45     ]
  46
  47     def _real_extract(self, url):
  48         mobj = re.match(self._VALID_URL, url)
  49         video_id = mobj.group('id')
  50         webpage = self._download_webpage(url, video_id)
  51         player_url = self._search_regex(
  52             r'playerSwf":"([^"?]*)', webpage, 'player URL')
  53
  54         if mobj.group('mediatype').startswith('music/song'):
  55             # songs don't store any useful info in the 'context' variable
  56             def search_data(name):
  57                 return self._search_regex(
  58                     r'data-%s="(.*?)"' % name, webpage, name)
  59             streamUrl = search_data('stream-url')
  60             info = {
  61                 'id': video_id,
  62                 'title': self._og_search_title(webpage),
  63                 'uploader_id': search_data('artist-username'),
  64                 'thumbnail': self._og_search_thumbnail(webpage),
  65             }
  66         else:
  67             context = json.loads(self._search_regex(
  68                 r'context = ({.*?});', webpage, 'context'))
  69             video = context['video']
  70             streamUrl = video['streamUrl']
  71             info = {
  72                 'id': compat_str(video['mediaId']),
  73                 'title': video['title'],
  74                 'description': video['description'],
  75                 'thumbnail': video['imageUrl'],
  76                 'uploader': video['artistName'],
  77                 'uploader_id': video['artistUsername'],
  78             }
  79
  80         rtmp_url, play_path = streamUrl.split(';', 1)
  81         info.update({
  82             'url': rtmp_url,
  83             'play_path': play_path,
  84             'player_url': player_url,
  85             'ext': 'flv',
  86         })
  87         return info