1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-02 23:02:57 +01:00
youtube-dl/youtube_dl/extractor/helsinki.py

44 lines
1.3 KiB
Python
Raw Normal View History

# -*- coding: utf-8 -*-
from __future__ import unicode_literals
from .common import InfoExtractor
2014-12-12 13:03:16 +01:00
from ..utils import js_to_json
class HelsinkiIE(InfoExtractor):
2014-02-17 11:32:30 +01:00
IE_DESC = 'helsinki.fi'
_VALID_URL = r'https?://video\.helsinki\.fi/Arkisto/flash\.php\?id=(?P<id>\d+)'
_TEST = {
'url': 'http://video.helsinki.fi/Arkisto/flash.php?id=20258',
'info_dict': {
'id': '20258',
'ext': 'mp4',
'title': 'Tietotekniikkafoorumi-iltapäivä',
2014-02-17 11:32:30 +01:00
'description': 'md5:f5c904224d43c133225130fe156a5ee0',
},
'params': {
'skip_download': True, # RTMP
}
}
def _real_extract(self, url):
2014-12-12 13:03:16 +01:00
video_id = self._match_id(url)
2014-02-17 11:32:30 +01:00
webpage = self._download_webpage(url, video_id)
2014-12-12 13:03:16 +01:00
params = self._parse_json(self._html_search_regex(
r'(?s)jwplayer\("player"\).setup\((\{.*?\})\);',
webpage, 'player code'), video_id, transform_source=js_to_json)
formats = [{
'url': s['file'],
'ext': 'mp4',
} for s in params['sources']]
2014-02-17 11:32:30 +01:00
self._sort_formats(formats)
return {
2014-02-17 11:32:30 +01:00
'id': video_id,
'title': self._og_search_title(webpage).replace('Video: ', ''),
'description': self._og_search_description(webpage),
2014-02-17 11:32:30 +01:00
'formats': formats,
}