aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/screenwavemedia.py
blob: e1604b5c0c3514bfe39fb5278a33e5d65f10106c (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
138
139
# encoding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    int_or_none,
    unified_strdate,
    js_to_json,
)


class ScreenwaveMediaIE(InfoExtractor):
    _VALID_URL = r'http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=(?P<id>.+)'

    _TESTS = [{
        'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)

        playerdata = self._download_webpage(
            'http://player.screenwavemedia.com/player.php?id=%s' % video_id,
            video_id, 'Downloading player webpage')

        vidtitle = self._search_regex(
            r'\'vidtitle\'\s*:\s*"([^"]+)"', playerdata, 'vidtitle').replace('\\/', '/')

        playerconfig = self._download_webpage(
            'http://player.screenwavemedia.com/player.js',
            video_id, 'Downloading playerconfig webpage')

        videoserver = self._search_regex(r'SWMServer\s*=\s*"([\d\.]+)"', playerdata, 'videoserver')

        sources = self._parse_json(
            js_to_json(
                re.sub(
                    r'(?s)/\*.*?\*/', '',
                    self._search_regex(
                        r"sources\s*:\s*(\[[^\]]+?\])", playerconfig,
                        'sources',
                    ).replace(
                        "' + thisObj.options.videoserver + '",
                        videoserver
                    ).replace(
                        "' + playerVidId + '",
                        video_id
                    )
                )
            ),
            video_id, fatal=False
        )

        # Fallback to hardcoded sources if JS changes again
        if not sources:
            sources = [{
                'file': 'http://%s/vod/%s_%s.mp4' % (videoserver, video_id, format_id),
                'type': 'mp4',
                'label': format_label,
            } for format_id, format_label in (
                ('low', '144p Low'), ('med', '160p Med'), ('high', '360p High'), ('hd1', '720p HD1'))]
            sources.append({
                'file': 'http://%s/vod/smil:%s.smil/playlist.m3u8' % (videoserver, video_id),
                'type': 'hls',
            })

        formats = []
        for source in sources:
            if source['type'] == 'hls':
                formats.extend(self._extract_m3u8_formats(source['file'], video_id))
            else:
                file_ = source.get('file')
                if not file_:
                    continue
                format_label = source.get('label')
                format_id = self._search_regex(
                    r'_(.+?)\.[^.]+$', file_, 'format id', default=None)
                height = int_or_none(self._search_regex(
                    r'^(\d+)[pP]', format_label, 'height', default=None))
                formats.append({
                    'url': source['file'],
                    'format_id': format_id,
                    'format': format_label,
                    'ext': source.get('type'),
                    'height': height,
                })
        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': vidtitle,
            'formats': formats,
        }


class TeamFourIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?'
    _TEST = {
        'url': 'http://teamfourstar.com/video/a-moment-with-tfs-episode-4/',
        'info_dict': {
            'id': 'TeamFourStar-5292a02f20bfa',
            'ext': 'mp4',
            'upload_date': '20130401',
            'description': 'Check out this and more on our website: http://teamfourstar.com\nTFS Store: http://sharkrobot.com/team-four-star\nFollow on Twitter: http://twitter.com/teamfourstar\nLike on FB: http://facebook.com/teamfourstar',
            'title': 'A Moment With TFS Episode 4',
        }
    }

    def _real_extract(self, url):
        display_id = self._match_id(url)
        webpage = self._download_webpage(url, display_id)

        playerdata_url = self._search_regex(
            r'src="(http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
            webpage, 'player data URL')

        video_title = self._html_search_regex(
            r'<div class="heroheadingtitle">(?P<title>.+?)</div>',
            webpage, 'title')
        video_date = unified_strdate(self._html_search_regex(
            r'<div class="heroheadingdate">(?P<date>.+?)</div>',
            webpage, 'date', fatal=False))
        video_description = self._html_search_regex(
            r'(?s)<div class="postcontent">(?P<description>.+?)</div>',
            webpage, 'description', fatal=False)
        video_thumbnail = self._og_search_thumbnail(webpage)

        return {
            '_type': 'url_transparent',
            'display_id': display_id,
            'title': video_title,
            'description': video_description,
            'upload_date': video_date,
            'thumbnail': video_thumbnail,
            'url': playerdata_url,
        }