yt-dlp/youtube_dl/extractor/space.py

39 lines
1.5 KiB
Python
Raw Normal View History

2014-02-19 01:04:24 +01:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .brightcove import BrightcoveLegacyIE
from ..utils import RegexNotFoundError, ExtractorError
class SpaceIE(InfoExtractor):
2014-01-22 11:25:32 +01:00
_VALID_URL = r'https?://(?:(?:www|m)\.)?space\.com/\d+-(?P<title>[^/\.\?]*?)-video\.html'
_TEST = {
'add_ie': ['BrightcoveLegacy'],
2014-02-19 01:04:24 +01:00
'url': 'http://www.space.com/23373-huge-martian-landforms-detail-revealed-by-european-probe-video.html',
'info_dict': {
'id': '2780937028001',
'ext': 'mp4',
'title': 'Huge Martian Landforms\' Detail Revealed By European Probe | Video',
'description': 'md5:db81cf7f3122f95ed234b631a6ea1e61',
'uploader': 'TechMedia Networks',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
title = mobj.group('title')
webpage = self._download_webpage(url, title)
try:
# Some videos require the playerKey field, which isn't define in
# the BrightcoveExperience object
brightcove_url = self._og_search_video_url(webpage)
except RegexNotFoundError:
# Other videos works fine with the info from the object
brightcove_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
if brightcove_url is None:
2014-11-26 13:06:02 +01:00
raise ExtractorError(
'The webpage does not contain a video', expected=True)
return self.url_result(brightcove_url, BrightcoveLegacyIE.ie_key())