You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
yt-dlc/youtube_dl/extractor/myspace.py

111 lines
4.0 KiB
Python

from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..compat import (
compat_str,
)
from ..utils import ExtractorError
class MySpaceIE(InfoExtractor):
_VALID_URL = r'https?://myspace\.com/([^/]+)/(?P<mediatype>video/[^/]+/|music/song/.*?)(?P<id>\d+)'
_TESTS = [
{
'url': 'https://myspace.com/coldplay/video/viva-la-vida/100008689',
'info_dict': {
'id': '100008689',
'ext': 'flv',
'title': 'Viva La Vida',
'description': 'The official Viva La Vida video, directed by Hype Williams',
'uploader': 'Coldplay',
'uploader_id': 'coldplay',
},
'params': {
# rtmp download
'skip_download': True,
},
},
# song
{
'url': 'https://myspace.com/spiderbags/music/song/darkness-in-my-heart-39008454-27041242',
'info_dict': {
'id': '39008454',
'ext': 'flv',
'title': 'Darkness In My Heart',
'uploader_id': 'spiderbags',
},
'params': {
# rtmp download
'skip_download': True,
},
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
player_url = self._search_regex(
r'playerSwf":"([^"?]*)', webpage, 'player URL')
if mobj.group('mediatype').startswith('music/song'):
# songs don't store any useful info in the 'context' variable
song_data = self._search_regex(
r'''<button.*data-song-id=(["\'])%s\1.*''' % video_id,
webpage, 'song_data', default=None, group=0)
if song_data is None:
self.to_screen(
'%s: No downloadable song on this page' % video_id)
return
def search_data(name):
return self._search_regex(
r'''data-%s=([\'"])(.*?)\1''' % name,
song_data, name, default='', group=2)
streamUrl = search_data('stream-url')
if not streamUrl:
vevo_id = search_data('vevo-id')
youtube_id = search_data('youtube-id')
if vevo_id:
self.to_screen('Vevo video detected: %s' % vevo_id)
return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
elif youtube_id:
self.to_screen('Youtube video detected: %s' % youtube_id)
return self.url_result(youtube_id, ie='Youtube')
else:
raise ExtractorError(
'Found song but don\'t know how to download it')
info = {
'id': video_id,
'title': self._og_search_title(webpage),
'uploader': search_data('artist-name'),
'uploader_id': search_data('artist-username'),
'playlist': search_data('album-title'),
'thumbnail': self._og_search_thumbnail(webpage),
}
else:
context = json.loads(self._search_regex(
r'context = ({.*?});', webpage, 'context'))
video = context['video']
streamUrl = video['streamUrl']
info = {
'id': compat_str(video['mediaId']),
'title': video['title'],
'description': video['description'],
'thumbnail': video['imageUrl'],
'uploader': video['artistName'],
'uploader_id': video['artistUsername'],
}
rtmp_url, play_path = streamUrl.split(';', 1)
info.update({
'url': rtmp_url,
'play_path': play_path,
'player_url': player_url,
'ext': 'flv',
})
return info