diff options
author | Unknown <blackjack4494@web.de> | 2020-09-02 23:33:41 +0200 |
---|---|---|
committer | Unknown <blackjack4494@web.de> | 2020-09-02 23:33:41 +0200 |
commit | 3ca3f77f9ce9dd504dc6af4ef605c245c31ff860 (patch) | |
tree | 6bd9c9352327148a78b8c46227c8d526f1447b03 /youtube_dl/extractor/nosvideo.py | |
parent | 4cd6add62b54721eeb3bf76bd9c0b4d676dc4d68 (diff) |
[skip travis] adding automerge support
basically copying content of youtube_dl folder to youtube_dlc and excluding the youtube_dl folder when compiling
Diffstat (limited to 'youtube_dl/extractor/nosvideo.py')
-rw-r--r-- | youtube_dl/extractor/nosvideo.py | 75 |
1 files changed, 75 insertions, 0 deletions
diff --git a/youtube_dl/extractor/nosvideo.py b/youtube_dl/extractor/nosvideo.py new file mode 100644 index 000000000..53c500c35 --- /dev/null +++ b/youtube_dl/extractor/nosvideo.py @@ -0,0 +1,75 @@ +# 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, + } |