aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/nhl.py
blob: 719eb51a468d72ef6939d5a4bf2f49570c24b15d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
from __future__ import unicode_literals

import re
import json

from .common import InfoExtractor
from ..utils import (
    compat_urlparse,
    compat_urllib_parse,
    unified_strdate,
)


class NHLBaseInfoExtractor(InfoExtractor):
    @staticmethod
    def _fix_json(json_string):
        return json_string.replace('\\\'', '\'')

    def _extract_video(self, info):
        video_id = info['id']
        self.report_extraction(video_id)

        initial_video_url = info['publishPoint']
        if info['formats'] == '1':
            data = compat_urllib_parse.urlencode({
                'type': 'fvod',
                'path': initial_video_url.replace('.mp4', '_sd.mp4'),
            })
            path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data
            path_doc = self._download_xml(
                path_url, video_id, 'Downloading final video url')
            video_url = path_doc.find('path').text
        else:
            video_url = initial_video_url

        join = compat_urlparse.urljoin
        return {
            'id': video_id,
            'title': info['name'],
            'url': video_url,
            'description': info['description'],
            'duration': int(info['duration']),
            'thumbnail': join(join(video_url, '/u/'), info['bigImage']),
            'upload_date': unified_strdate(info['releaseDate'].split('.')[0]),
        }


class NHLIE(NHLBaseInfoExtractor):
    IE_NAME = 'nhl.com'
    _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console(?:\?(?:.*?[?&])?)id=(?P<id>[0-9a-z-]+)'

    _TESTS = [{
        'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',
        'md5': 'db704a4ea09e8d3988c85e36cc892d09',
        'info_dict': {
            'id': '453614',
            'ext': 'mp4',
            'title': 'Quick clip: Weise 4-3 goal vs Flames',
            'description': 'Dale Weise scores his first of the season to put the Canucks up 4-3.',
            'duration': 18,
            'upload_date': '20131006',
        },
    }, {
        'url': 'http://video.nhl.com/videocenter/console?id=2014020024-628-h',
        'md5': 'd22e82bc592f52d37d24b03531ee9696',
        'info_dict': {
            'id': '2014020024-628-h',
            'ext': 'mp4',
            'title': 'Alex Galchenyuk Goal on Ray Emery (14:40/3rd)',
            'description': 'Home broadcast - Montreal Canadiens at Philadelphia Flyers - October 11, 2014',
            'duration': 0,
            'upload_date': '20141011',
        },
    }, {
        'url': 'http://video.flames.nhl.com/videocenter/console?id=630616',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')
        json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id
        data = self._download_json(
            json_url, video_id, transform_source=self._fix_json)
        return self._extract_video(data[0])


class NHLVideocenterIE(NHLBaseInfoExtractor):
    IE_NAME = 'nhl.com:videocenter'
    IE_DESC = 'NHL videocenter category'
    _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$'
    _TEST = {
        'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999',
        'info_dict': {
            'id': '999',
            'title': 'Highlights',
        },
        'playlist_count': 12,
    }

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        team = mobj.group('team')
        webpage = self._download_webpage(url, team)
        cat_id = self._search_regex(
            [r'var defaultCatId = "(.+?)";',
             r'{statusIndex:0,index:0,.*?id:(.*?),'],
            webpage, 'category id')
        playlist_title = self._html_search_regex(
            r'tab0"[^>]*?>(.*?)</td>',
            webpage, 'playlist title', flags=re.DOTALL).lower().capitalize()

        data = compat_urllib_parse.urlencode({
            'cid': cat_id,
            # This is the default value
            'count': 12,
            'ptrs': 3,
            'format': 'json',
        })
        path = '/videocenter/servlets/browse?' + data
        request_url = compat_urlparse.urljoin(url, path)
        response = self._download_webpage(request_url, playlist_title)
        response = self._fix_json(response)
        if not response.strip():
            self._downloader.report_warning(u'Got an empty reponse, trying '
                                            'adding the "newvideos" parameter')
            response = self._download_webpage(request_url + '&newvideos=true',
                                              playlist_title)
            response = self._fix_json(response)
        videos = json.loads(response)

        return {
            '_type': 'playlist',
            'title': playlist_title,
            'id': cat_id,
            'entries': [self._extract_video(v) for v in videos],
        }