yt-dlp/youtube_dl/extractor/clipfish.py

55 lines
1.7 KiB
Python
Raw Normal View History

2014-03-24 21:30:32 +00:00
from __future__ import unicode_literals
2013-11-24 06:51:44 +00:00
from .common import InfoExtractor
2014-03-24 21:30:32 +00:00
from ..utils import (
ExtractorError,
2015-07-24 11:00:20 +00:00
int_or_none,
js_to_json,
determine_ext,
2014-03-24 21:30:32 +00:00
)
2013-11-24 06:51:44 +00:00
class ClipfishIE(InfoExtractor):
2014-03-24 21:30:32 +00:00
IE_NAME = 'clipfish'
2013-11-24 06:51:44 +00:00
_VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/'
_TEST = {
2014-03-24 21:30:32 +00:00
'url': 'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
2015-07-24 11:00:20 +00:00
'md5': '79bc922f3e8a9097b3d68a93780fd475',
2014-03-24 21:30:32 +00:00
'info_dict': {
'id': '3966754',
'ext': 'mp4',
'title': 'FIFA 14 - E3 2013 Trailer',
'duration': 82,
2015-07-24 11:00:20 +00:00
}
2013-11-24 06:51:44 +00:00
}
def _real_extract(self, url):
2015-07-24 11:00:20 +00:00
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_info = self._parse_json(
js_to_json(self._html_search_regex('var videoObject = ({[^}]+?})', webpage, 'videoObject')),
video_id
)
info_url = self._parse_json(
js_to_json(self._html_search_regex('var globalFlashvars = ({[^}]+?})', webpage, 'globalFlashvars')),
video_id
)['data']
2013-11-24 06:51:44 +00:00
doc = self._download_xml(
2014-11-26 12:06:02 +00:00
info_url, video_id, note='Downloading info page')
2013-11-24 06:51:44 +00:00
title = doc.find('title').text
video_url = doc.find('filename').text
thumbnail = doc.find('imageurl').text
2015-07-24 11:00:20 +00:00
duration = int_or_none(video_info['length'])
formats = [{'url': video_info['videourl']},{'url': video_url}]
self._sort_formats(formats)
2013-11-24 06:51:44 +00:00
return {
'id': video_id,
'title': title,
2015-07-24 11:00:20 +00:00
'formats': formats,
2013-11-24 06:51:44 +00:00
'thumbnail': thumbnail,
'duration': duration,
}