aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/ted.py
blob: a8d8e8b29668f5db59f27565c21ee9064190498b (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
from __future__ import unicode_literals

import json
import re

from .subtitles import SubtitlesInfoExtractor

from ..utils import (
    compat_str,
)


class TEDIE(SubtitlesInfoExtractor):
    _VALID_URL = r'''(?x)
        (?P<proto>https?://)
        (?P<type>www|embed)(?P<urlmain>\.ted\.com/
        (
            (?P<type_playlist>playlists(?:/\d+)?) # We have a playlist
            |
            ((?P<type_talk>talks)) # We have a simple talk
            |
            (?P<type_watch>watch)/[^/]+/[^/]+
        )
        (/lang/(.*?))? # The url may contain the language
        /(?P<name>[\w-]+) # Here goes the name and then ".html"
        .*)$
        '''
    _TESTS = [{
        'url': 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html',
        'md5': '4ea1dada91e4174b53dac2bb8ace429d',
        'info_dict': {
            'id': '102',
            'ext': 'mp4',
            'title': 'The illusion of consciousness',
            'description': ('Philosopher Dan Dennett makes a compelling '
                'argument that not only don\'t we understand our own '
                'consciousness, but that half the time our brains are '
                'actively fooling us.'),
            'uploader': 'Dan Dennett',
        }
    }, {
        'url': 'http://www.ted.com/watch/ted-institute/ted-bcg/vishal-sikka-the-beauty-and-power-of-algorithms',
        'md5': '226f4fb9c62380d11b7995efa4c87994',
        'info_dict': {
            'id': 'vishal-sikka-the-beauty-and-power-of-algorithms',
            'ext': 'mp4',
            'title': 'Vishal Sikka: The beauty and power of algorithms',
            'thumbnail': 're:^https?://.+\.jpg',
            'description': 'Adaptive, intelligent, and consistent, algorithms are emerging as the ultimate app for everything from matching consumers to products to assessing medical diagnoses. Vishal Sikka shares his appreciation for the algorithm, charting both its inherent beauty and its growing power.',
        }
    }]

    _FORMATS_PREFERENCE = {
        'low': 1,
        'medium': 2,
        'high': 3,
    }

    def _extract_info(self, webpage):
        info_json = self._search_regex(r'q\("\w+.init",({.+})\)</script>',
            webpage, 'info json')
        return json.loads(info_json)

    def _real_extract(self, url):
        m = re.match(self._VALID_URL, url, re.VERBOSE)
        if m.group('type') == 'embed':
            desktop_url = m.group('proto') + 'www' + m.group('urlmain')
            return self.url_result(desktop_url, 'TED')
        name = m.group('name')
        if m.group('type_talk'):
            return self._talk_info(url, name)
        elif m.group('type_watch'):
            return self._watch_info(url, name)
        else:
            return self._playlist_videos_info(url, name)

    def _playlist_videos_info(self, url, name):
        '''Returns the videos of the playlist'''

        webpage = self._download_webpage(url, name,
            'Downloading playlist webpage')
        info = self._extract_info(webpage)
        playlist_info = info['playlist']

        playlist_entries = [
            self.url_result(u'http://www.ted.com/talks/' + talk['slug'], self.ie_key())
            for talk in info['talks']
        ]
        return self.playlist_result(
            playlist_entries,
            playlist_id=compat_str(playlist_info['id']),
            playlist_title=playlist_info['title'])

    def _talk_info(self, url, video_name):
        webpage = self._download_webpage(url, video_name)
        self.report_extraction(video_name)

        talk_info = self._extract_info(webpage)['talks'][0]

        formats = [{
            'ext': 'mp4',
            'url': format_url,
            'format_id': format_id,
            'format': format_id,
            'preference': self._FORMATS_PREFERENCE.get(format_id, -1),
        } for (format_id, format_url) in talk_info['nativeDownloads'].items()]
        self._sort_formats(formats)

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

        thumbnail = talk_info['thumb']
        if not thumbnail.startswith('http'):
            thumbnail = 'http://' + thumbnail
        return {
            'id': video_id,
            'title': talk_info['title'],
            'uploader': talk_info['speaker'],
            'thumbnail': thumbnail,
            'description': self._og_search_description(webpage),
            'subtitles': video_subtitles,
            'formats': formats,
        }

    def _get_available_subtitles(self, video_id, talk_info):
        languages = [lang['languageCode'] for lang in talk_info.get('languages', [])]
        if languages:
            sub_lang_list = {}
            for l in languages:
                url = 'http://www.ted.com/talks/subtitles/id/%s/lang/%s/format/srt' % (video_id, l)
                sub_lang_list[l] = url
            return sub_lang_list
        else:
            self._downloader.report_warning(u'video doesn\'t have subtitles')
            return {}

    def _watch_info(self, url, name):
        webpage = self._download_webpage(url, name)

        config_json = self._html_search_regex(
            r"data-config='([^']+)", webpage, 'config')
        config = json.loads(config_json)
        video_url = config['video']['url']
        thumbnail = config.get('image', {}).get('url')

        title = self._html_search_regex(
            r"(?s)<h1(?:\s+class='[^']+')?>(.+?)</h1>", webpage, 'title')
        description = self._html_search_regex(
            r'(?s)<h4 class="[^"]+" id="h3--about-this-talk">.*?</h4>(.*?)</div>',
            webpage, 'description', fatal=False)

        return {
            'id': name,
            'url': video_url,
            'title': title,
            'thumbnail': thumbnail,
            'description': description,
        }