yt-dlp/yt_dlp/extractor/nosvideo.py

73 lines
2.4 KiB
Python
Raw Normal View History

2014-09-01 20:47:14 +00:00
import re
from .common import InfoExtractor
from ..networking import Request
2014-09-01 20:47:14 +00:00
from ..utils import (
2014-09-10 15:10:21 +00:00
ExtractorError,
urlencode_postdata,
xpath_text,
2014-09-01 20:47:14 +00:00
xpath_with_ns,
)
_x = lambda p: xpath_with_ns(p, {'xspf': 'http://xspf.org/ns/0/'})
class NosVideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nosvideo\.com/' + \
r'(?:embed/|\?v=)(?P<id>[A-Za-z0-9]{12})/?'
2014-09-01 20:47:14 +00:00
_PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml'
2014-09-10 15:10:21 +00:00
_FILE_DELETED_REGEX = r'<b>File Not Found</b>'
2014-09-01 20:47:14 +00:00
_TEST = {
2014-09-10 15:19:59 +00:00
'url': 'http://nosvideo.com/?v=mu8fle7g7rpq',
'md5': '6124ed47130d8be3eacae635b071e6b6',
2014-09-01 20:47:14 +00:00
'info_dict': {
2014-09-10 15:19:59 +00:00
'id': 'mu8fle7g7rpq',
2014-09-01 20:47:14 +00:00
'ext': 'mp4',
'title': 'big_buck_bunny_480p_surround-fix.avi.mp4',
'thumbnail': r're:^https?://.*\.jpg$',
2014-09-01 20:47:14 +00:00
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
2014-09-01 20:47:14 +00:00
fields = {
'id': video_id,
'op': 'download1',
'method_free': 'Continue to Video',
}
req = Request(url, urlencode_postdata(fields))
req.headers['Content-type'] = 'application/x-www-form-urlencoded'
2014-09-01 20:47:14 +00:00
webpage = self._download_webpage(req, video_id,
'Downloading download page')
2014-09-10 15:10:21 +00:00
if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
raise ExtractorError('Video %s does not exist' % video_id,
expected=True)
2014-09-01 20:47:14 +00:00
xml_id = self._search_regex(r'php\|([^\|]+)\|', webpage, 'XML ID')
playlist_url = self._PLAYLIST_URL.format(xml_id=xml_id)
playlist = self._download_xml(playlist_url, video_id)
track = playlist.find(_x('.//xspf:track'))
if track is None:
raise ExtractorError(
'XML playlist is missing the \'track\' element',
expected=True)
title = xpath_text(track, _x('./xspf:title'), 'title')
url = xpath_text(track, _x('./xspf:file'), 'URL', fatal=True)
thumbnail = xpath_text(track, _x('./xspf:image'), 'thumbnail')
if title is not None:
title = title.strip()
2014-09-01 20:47:14 +00:00
formats = [{
'format_id': 'sd',
'url': url,
}]
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}