1
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-04 13:45:17 +01:00
yt-dlp/yt_dlp/extractor/nosvideo.py
Pccode66 7a5c1cfe93
Completely change project name to yt-dlp (#85)
* All modules and binary names are changed
* All documentation references changed
* yt-dlp no longer loads youtube-dlc config files
* All URLs changed to point to organization account

Co-authored-by: Pccode66
Co-authored-by: pukkandan
2021-02-25 00:15:56 +05:30

76 lines
2.4 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
sanitized_Request,
urlencode_postdata,
xpath_text,
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})/?'
_PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml'
_FILE_DELETED_REGEX = r'<b>File Not Found</b>'
_TEST = {
'url': 'http://nosvideo.com/?v=mu8fle7g7rpq',
'md5': '6124ed47130d8be3eacae635b071e6b6',
'info_dict': {
'id': 'mu8fle7g7rpq',
'ext': 'mp4',
'title': 'big_buck_bunny_480p_surround-fix.avi.mp4',
'thumbnail': r're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
fields = {
'id': video_id,
'op': 'download1',
'method_free': 'Continue to Video',
}
req = sanitized_Request(url, urlencode_postdata(fields))
req.add_header('Content-type', 'application/x-www-form-urlencoded')
webpage = self._download_webpage(req, video_id,
'Downloading download page')
if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
raise ExtractorError('Video %s does not exist' % video_id,
expected=True)
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()
formats = [{
'format_id': 'sd',
'url': url,
}]
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}