1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-22 22:52:53 +08:00
youtube-dl/youtube_dl/extractor/clipfish.py

69 lines
2.1 KiB
Python
Raw Normal View History

2014-03-25 05:30:32 +08:00
from __future__ import unicode_literals
import re
2013-11-24 14:51:44 +08:00
from .common import InfoExtractor
2014-03-25 05:30:32 +08:00
from ..utils import (
determine_ext,
2015-07-24 19:00:20 +08:00
int_or_none,
js_to_json,
parse_iso8601,
remove_end,
2014-03-25 05:30:32 +08:00
)
2013-11-24 14:51:44 +08:00
class ClipfishIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?clipfish\.de/(?:[^/]+/)+video/(?P<id>[0-9]+)'
2013-11-24 14:51:44 +08:00
_TEST = {
2014-03-25 05:30:32 +08:00
'url': 'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
2015-07-24 19:00:20 +08:00
'md5': '79bc922f3e8a9097b3d68a93780fd475',
2014-03-25 05:30:32 +08:00
'info_dict': {
'id': '3966754',
'ext': 'mp4',
'title': 'FIFA 14 - E3 2013 Trailer',
'timestamp': 1370938118,
'upload_date': '20130611',
2014-03-25 05:30:32 +08:00
'duration': 82,
2015-07-24 19:00:20 +08:00
}
2013-11-24 14:51:44 +08:00
}
def _real_extract(self, url):
2015-07-24 19:00:20 +08:00
video_id = self._match_id(url)
2015-07-24 19:00:20 +08:00
webpage = self._download_webpage(url, video_id)
2015-07-24 19:00:20 +08:00
video_info = self._parse_json(
js_to_json(self._html_search_regex(
'(?s)videoObject\s*=\s*({.+?});', webpage, 'video object')),
video_id)
formats = []
for video_url in re.findall(r'var\s+videourl\s*=\s*"([^"]+)"', webpage):
ext = determine_ext(video_url)
if ext == 'm3u8':
formats.append({
'url': video_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'),
'ext': 'mp4',
'format_id': 'hls',
})
else:
formats.append({
'url': video_url,
'format_id': ext,
})
2015-07-24 19:00:20 +08:00
self._sort_formats(formats)
2013-11-24 14:51:44 +08:00
title = remove_end(self._og_search_title(webpage), ' - Video')
thumbnail = self._og_search_thumbnail(webpage)
duration = int_or_none(video_info.get('length'))
timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage, 'upload date'))
2013-11-24 14:51:44 +08:00
return {
'id': video_id,
'title': title,
2015-07-24 19:00:20 +08:00
'formats': formats,
2013-11-24 14:51:44 +08:00
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
2013-11-24 14:51:44 +08:00
}