youtube-dl/youtube_dl/extractor/vice.py

51 lines
1.7 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .ooyala import OoyalaIE
from ..utils import ExtractorError
class ViceIE(InfoExtractor):
_VALID_URL = r'https?://(?:.+?\.)?vice\.com/.*?/(?P<name>.+)'
2015-07-19 16:31:38 +00:00
_TESTS = [
{
'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1',
'info_dict': {
'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
'ext': 'mp4',
'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
},
'params': {
# Requires ffmpeg (m3u8 manifest)
'skip_download': True,
},
}, {
'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab',
'info_dict': {
'id': 'N2bzkydjraWDGwnt8jAttCF6Y0PDv4Zj',
'ext': 'mp4',
'title': 'VICE News - Inside the Monkey Lab',
'description': 'md5:1f660d467d3515f29d11e5ef742a4b82',
},
'params': {
# Requires ffmpeg (m3u8 manifest)
'skip_download': True,
},
}
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
name = mobj.group('name')
webpage = self._download_webpage(url, name)
try:
embed_code = self._search_regex(
r'embedCode=([^&\'"]+)', webpage,
'ooyala embed code')
ooyala_url = OoyalaIE._url_for_embed_code(embed_code)
except ExtractorError:
raise ExtractorError('The page doesn\'t contain a video', expected=True)
return self.url_result(ooyala_url, ie='Ooyala')