[nowness] Add support
[youtube-dl] / youtube_dl / extractor / nowness.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .brightcove import BrightcoveIE
6 from .common import InfoExtractor
7 from ..utils import (
8     ExtractorError,
9 )
10
11
12 class NownessIE(InfoExtractor):
13     _VALID_URL = r'https?://(?:www\.)?nowness\.com/[^?#]*?/(?P<id>[0-9]+)/(?P<slug>[^/]+?)(?:$|[?#])'
14
15     _TEST = {
16         'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation',
17         'file': '2520295746001.mp4',
18         'md5': '0ece2f70a7bd252c7b00f3070182d418',
19         'info_dict': {
20             'description': 'Candor: The Art of Gesticulation',
21             'uploader': 'Nowness',
22             'title': 'Candor: The Art of Gesticulation',
23         }
24     }
25
26     def _real_extract(self, url):
27         mobj = re.match(self._VALID_URL, url)
28         video_id = mobj.group('slug')
29
30         webpage = self._download_webpage(url, video_id)
31         player_url = self._search_regex(
32             r'"([^"]+/content/issue-[0-9.]+.js)"', webpage, 'player URL')
33         real_id = self._search_regex(
34             r'\sdata-videoId="([0-9]+)"', webpage, 'internal video ID')
35
36         player_code = self._download_webpage(
37             player_url, video_id,
38             note='Downloading player JavaScript',
39             errnote='Player download failed')
40         player_code = player_code.replace("'+d+'", real_id)
41
42         bc_url = BrightcoveIE._extract_brightcove_url(player_code)
43         if bc_url is None:
44             raise ExtractorError('Could not find player definition')
45         return {
46             '_type': 'url',
47             'url': bc_url,
48             'ie_key': 'Brightcove',
49         }