aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/nhl.py
blob: 224f56ac84b77647c2ff5468b41d229786da632e (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
import re
import json
import xml.etree.ElementTree

from .common import InfoExtractor
from ..utils import (
    compat_urlparse,
    compat_urllib_parse,
    determine_ext,
    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']
        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_response = self._download_webpage(path_url, video_id,
            u'Downloading final video url')
        path_doc = xml.etree.ElementTree.fromstring(path_response)
        video_url = path_doc.find('path').text

        join = compat_urlparse.urljoin
        return {
            'id': video_id,
            'title': info['name'],
            'url': video_url,
            'ext': determine_ext(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 = u'nhl.com'
    _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console\?.*?(?<=[?&])id=(?P<id>\d+)'

    _TEST = {
        u'url': u'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',
        u'file': u'453614.mp4',
        u'info_dict': {
            u'title': u'Quick clip: Weise 4-3 goal vs Flames',
            u'description': u'Dale Weise scores his first of the season to put the Canucks up 4-3.',
            u'duration': 18,
            u'upload_date': u'20131006',
        },
    }

    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
        info_json = self._download_webpage(json_url, video_id,
            u'Downloading info json')
        info_json = self._fix_json(info_json)
        info = json.loads(info_json)[0]
        return self._extract_video(info)


class NHLVideocenterIE(NHLBaseInfoExtractor):
    IE_NAME = u'nhl.com:videocenter'
    IE_DESC = u'Download the first 12 videos from a videocenter category'
    _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P<catid>[^&]+))?'

    @classmethod
    def suitable(cls, url):
        if NHLIE.suitable(url):
            return False
        return super(NHLVideocenterIE, cls).suitable(url)

    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, u'category id')
        playlist_title = self._html_search_regex(
            r'tab0"[^>]*?>(.*?)</td>',
            webpage, u'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 '
                                            u'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(i) for i in videos],
        }