_ 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             song_data = self._search_regex(
  57                 r'''<button.*data-song-id=(["\'])%s\1.*''' % video_id,
  58                 webpage, 'song_data', default=None, group=0)
  59             if song_data is None:
  60                 self.to_screen(
  61                     '%s: No downloadable song on this page' % video_id)
  62                 return
  63             def search_data(name):
  64                 return self._search_regex(
  65                     r'''data-%s=([\'"])(.*?)\1''' % name,
  66                     song_data, name, default='', group=2)
  67             streamUrl = search_data('stream-url')
  68             info = {
  69                 'id': video_id,
  70                 'title': self._og_search_title(webpage),
  71                 'uploader': search_data('artist-name'),
  72                 'uploader_id': search_data('artist-username'),
  73                 'playlist': search_data('album-title'),
  74                 'thumbnail': self._og_search_thumbnail(webpage),
  75             }
  76         else:
  77             context = json.loads(self._search_regex(
  78                 r'context = ({.*?});', webpage, 'context'))
  79             video = context['video']
  80             streamUrl = video['streamUrl']
  81             info = {
  82                 'id': compat_str(video['mediaId']),
  83                 'title': video['title'],
  84                 'description': video['description'],
  85                 'thumbnail': video['imageUrl'],
  86                 'uploader': video['artistName'],
  87                 'uploader_id': video['artistUsername'],
  88             }
  89
  90         rtmp_url, play_path = streamUrl.split(';', 1)
  91         info.update({
  92             'url': rtmp_url,
  93             'play_path': play_path,
  94             'player_url': player_url,
  95             'ext': 'flv',
  96         })
  97         return info