aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/bliptv.py
blob: 2370c24b06eb9b9547fbc822a413405b2223ae42 (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
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from .subtitles import SubtitlesInfoExtractor
from ..utils import (
    compat_urllib_request,
    unescapeHTML,
    parse_iso8601,
    compat_urlparse,
    clean_html,
    compat_str,
)


class BlipTVIE(SubtitlesInfoExtractor):
    _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P<id>\d+)|((?:play/|api\.swf#)(?P<lookup_id>[\da-zA-Z+_]+)))'

    _TESTS = [
        {
            'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
            'md5': 'c6934ad0b6acf2bd920720ec888eb812',
            'info_dict': {
                'id': '5779306',
                'ext': 'mov',
                'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3',
                'description': 'md5:9bc31f227219cde65e47eeec8d2dc596',
                'timestamp': 1323138843,
                'upload_date': '20111206',
                'uploader': 'cbr',
                'uploader_id': '679425',
                'duration': 81,
            }
        },
        {
            # https://github.com/rg3/youtube-dl/pull/2274
            'note': 'Video with subtitles',
            'url': 'http://blip.tv/play/h6Uag5OEVgI.html',
            'md5': '309f9d25b820b086ca163ffac8031806',
            'info_dict': {
                'id': '6586561',
                'ext': 'mp4',
                'title': 'Red vs. Blue Season 11 Episode 1',
                'description': 'One-Zero-One',
                'timestamp': 1371261608,
                'upload_date': '20130615',
                'uploader': 'redvsblue',
                'uploader_id': '792887',
                'duration': 279,
            }
        },
        {
            # https://bugzilla.redhat.com/show_bug.cgi?id=967465
            'url': 'http://a.blip.tv/api.swf#h6Uag5KbVwI',
            'md5': '314e87b1ebe7a48fcbfdd51b791ce5a6',
            'info_dict': {
                'id': '6573122',
                'ext': 'mov',
                'upload_date': '20130520',
                'description': 'Two hapless space marines argue over what to do when they realize they have an astronomically huge problem on their hands.',
                'title': 'Red vs. Blue Season 11 Trailer',
                'timestamp': 1369029609,
                'uploader': 'redvsblue',
                'uploader_id': '792887',
            }
        }
    ]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        lookup_id = mobj.group('lookup_id')

        # See https://github.com/rg3/youtube-dl/issues/857 and
        # https://github.com/rg3/youtube-dl/issues/4197
        if lookup_id:
            info_page = self._download_webpage(
                'http://blip.tv/play/%s.x?p=1' % lookup_id, lookup_id, 'Resolving lookup id')
            video_id = self._search_regex(r'config\.id\s*=\s*"([0-9]+)', info_page, 'video_id')
        else:
            video_id = mobj.group('id')

        rss = self._download_xml('http://blip.tv/rss/flash/%s' % video_id, video_id, 'Downloading video RSS')

        def blip(s):
            return '{http://blip.tv/dtd/blip/1.0}%s' % s

        def media(s):
            return '{http://search.yahoo.com/mrss/}%s' % s

        def itunes(s):
            return '{http://www.itunes.com/dtds/podcast-1.0.dtd}%s' % s

        item = rss.find('channel/item')

        video_id = item.find(blip('item_id')).text
        title = item.find('./title').text
        description = clean_html(compat_str(item.find(blip('puredescription')).text))
        timestamp = parse_iso8601(item.find(blip('datestamp')).text)
        uploader = item.find(blip('user')).text
        uploader_id = item.find(blip('userid')).text
        duration = int(item.find(blip('runtime')).text)
        media_thumbnail = item.find(media('thumbnail'))
        thumbnail = media_thumbnail.get('url') if media_thumbnail is not None else item.find(itunes('image')).text
        categories = [category.text for category in item.findall('category')]

        formats = []
        subtitles = {}

        media_group = item.find(media('group'))
        for media_content in media_group.findall(media('content')):
            url = media_content.get('url')
            role = media_content.get(blip('role'))
            msg = self._download_webpage(
                url + '?showplayer=20140425131715&referrer=http://blip.tv&mask=7&skin=flashvars&view=url',
                video_id, 'Resolving URL for %s' % role)
            real_url = compat_urlparse.parse_qs(msg)['message'][0]

            media_type = media_content.get('type')
            if media_type == 'text/srt' or url.endswith('.srt'):
                LANGS = {
                    'english': 'en',
                }
                lang = role.rpartition('-')[-1].strip().lower()
                langcode = LANGS.get(lang, lang)
                subtitles[langcode] = url
            elif media_type.startswith('video/'):
                formats.append({
                    'url': real_url,
                    'format_id': role,
                    'format_note': media_type,
                    'vcodec': media_content.get(blip('vcodec')),
                    'acodec': media_content.get(blip('acodec')),
                    'filesize': media_content.get('filesize'),
                    'width': int(media_content.get('width')),
                    'height': int(media_content.get('height')),
                })
        self._sort_formats(formats)

        # subtitles
        video_subtitles = self.extract_subtitles(video_id, subtitles)
        if self._downloader.params.get('listsubtitles', False):
            self._list_available_subtitles(video_id, subtitles)
            return

        return {
            'id': video_id,
            'title': title,
            'description': description,
            'timestamp': timestamp,
            'uploader': uploader,
            'uploader_id': uploader_id,
            'duration': duration,
            'thumbnail': thumbnail,
            'categories': categories,
            'formats': formats,
            'subtitles': video_subtitles,
        }

    def _download_subtitle_url(self, sub_lang, url):
        # For some weird reason, blip.tv serves a video instead of subtitles
        # when we request with a common UA
        req = compat_urllib_request.Request(url)
        req.add_header('Youtubedl-user-agent', 'youtube-dl')
        return self._download_webpage(req, None, note=False)


class BlipTVUserIE(InfoExtractor):
    _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)(?!api\.swf)([^/]+)/*$'
    _PAGE_SIZE = 12
    IE_NAME = 'blip.tv:user'

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        username = mobj.group(1)

        page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'

        page = self._download_webpage(url, username, 'Downloading user page')
        mobj = re.search(r'data-users-id="([^"]+)"', page)
        page_base = page_base % mobj.group(1)

        # Download video ids using BlipTV Ajax calls. Result size per
        # query is limited (currently to 12 videos) so we need to query
        # page by page until there are no video ids - it means we got
        # all of them.

        video_ids = []
        pagenum = 1

        while True:
            url = page_base + "&page=" + str(pagenum)
            page = self._download_webpage(
                url, username, 'Downloading video ids from page %d' % pagenum)

            # Extract video identifiers
            ids_in_page = []

            for mobj in re.finditer(r'href="/([^"]+)"', page):
                if mobj.group(1) not in ids_in_page:
                    ids_in_page.append(unescapeHTML(mobj.group(1)))

            video_ids.extend(ids_in_page)

            # A little optimization - if current page is not
            # "full", ie. does not contain PAGE_SIZE video ids then
            # we can assume that this page is the last one - there
            # are no more ids on further pages - no need to query
            # again.

            if len(ids_in_page) < self._PAGE_SIZE:
                break

            pagenum += 1

        urls = ['http://blip.tv/%s' % video_id for video_id in video_ids]
        url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls]
        return [self.playlist_result(url_entries, playlist_title=username)]