aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/pbs.py
blob: 289f930e0819a0f5a68f634f84d9462fe0230146 (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
219
220
221
222
223
224
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    ExtractorError,
    determine_ext,
    int_or_none,
    unified_strdate,
    US_RATINGS,
)


class PBSIE(InfoExtractor):
    _VALID_URL = r'''(?x)https?://
        (?:
           # Direct video URL
           video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
           # Article with embedded player (or direct video)
           (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
           # Player
           video\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
        )
    '''

    _TESTS = [
        {
            'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/',
            'md5': 'ce1888486f0908d555a8093cac9a7362',
            'info_dict': {
                'id': '2365006249',
                'ext': 'mp4',
                'title': 'A More Perfect Union',
                'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
                'duration': 3190,
            },
        },
        {
            'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
            'md5': '143c98aa54a346738a3d78f54c925321',
            'info_dict': {
                'id': '2365297690',
                'ext': 'mp4',
                'title': 'Losing Iraq',
                'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
                'duration': 5050,
            },
        },
        {
            'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
            'md5': 'b19856d7f5351b17a5ab1dc6a64be633',
            'info_dict': {
                'id': '2201174722',
                'ext': 'mp4',
                'title': 'Cyber Schools Gain Popularity, but Quality Questions Persist',
                'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28',
                'duration': 801,
            },
        },
        {
            'url': 'http://www.pbs.org/wnet/gperf/dudamel-conducts-verdi-requiem-hollywood-bowl-full-episode/3374/',
            'md5': 'c62859342be2a0358d6c9eb306595978',
            'info_dict': {
                'id': '2365297708',
                'ext': 'mp4',
                'description': 'md5:68d87ef760660eb564455eb30ca464fe',
                'title': 'Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full',
                'duration': 6559,
                'thumbnail': 're:^https?://.*\.jpg$',
            }
        },
        {
            'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html',
            'md5': '908f3e5473a693b266b84e25e1cf9703',
            'info_dict': {
                'id': '2365160389',
                'display_id': 'killer-typhoon',
                'ext': 'mp4',
                'description': 'md5:c741d14e979fc53228c575894094f157',
                'title': 'Killer Typhoon',
                'duration': 3172,
                'thumbnail': 're:^https?://.*\.jpg$',
                'upload_date': '20140122',
            }
        },
        {
            'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
            'info_dict': {
                'id': 'united-states-of-secrets',
            },
            'playlist_count': 2,
        },
        {
            'url': 'http://www.pbs.org/wgbh/americanexperience/films/death/player/',
            'info_dict': {
                'id': '2280706814',
                'display_id': 'player',
                'ext': 'mp4',
                'title': 'Death and the Civil War',
                'description': 'American Experience, TV’s most-watched history series, brings to life the compelling stories from our past that inform our understanding of the world today.',
                'duration': 6705,
                'thumbnail': 're:^https?://.*\.jpg$',
            },
            'params': {
                'skip_download': True,  # requires ffmpeg
            }
        }
    ]

    def _extract_webpage(self, url):
        mobj = re.match(self._VALID_URL, url)

        presumptive_id = mobj.group('presumptive_id')
        display_id = presumptive_id
        if presumptive_id:
            webpage = self._download_webpage(url, display_id)

            upload_date = unified_strdate(self._search_regex(
                r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"',
                webpage, 'upload date', default=None))

            # tabbed frontline videos
            tabbed_videos = re.findall(
                r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"', webpage)
            if tabbed_videos:
                return tabbed_videos, presumptive_id, upload_date

            MEDIA_ID_REGEXES = [
                r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'",  # frontline video embed
                r'class="coveplayerid">([^<]+)<',                       # coveplayer
                r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>',  # jwplayer
            ]

            media_id = self._search_regex(
                MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None)
            if media_id:
                return media_id, presumptive_id, upload_date

            url = self._search_regex(
                r'<iframe\s+[^>]*\s+src=["\']([^\'"]+partnerplayer[^\'"]+)["\']',
                webpage, 'player URL')
            mobj = re.match(self._VALID_URL, url)

        player_id = mobj.group('player_id')
        if not display_id:
            display_id = player_id
        if player_id:
            player_page = self._download_webpage(
                url, display_id, note='Downloading player page',
                errnote='Could not download player page')
            video_id = self._search_regex(
                r'<div\s+id="video_([0-9]+)"', player_page, 'video ID')
        else:
            video_id = mobj.group('id')
            display_id = video_id

        return video_id, display_id, None

    def _real_extract(self, url):
        video_id, display_id, upload_date = self._extract_webpage(url)

        if isinstance(video_id, list):
            entries = [self.url_result(
                'http://video.pbs.org/video/%s' % vid_id, 'PBS', vid_id)
                for vid_id in video_id]
            return self.playlist_result(entries, display_id)

        info = self._download_json(
            'http://video.pbs.org/videoInfo/%s?format=json&type=partner' % video_id,
            display_id)

        formats = []
        for encoding_name in ('recommended_encoding', 'alternate_encoding'):
            redirect = info.get(encoding_name)
            if not redirect:
                continue
            redirect_url = redirect.get('url')
            if not redirect_url:
                continue

            redirect_info = self._download_json(
                redirect_url + '?format=json', display_id,
                'Downloading %s video url info' % encoding_name)

            if redirect_info['status'] == 'error':
                if redirect_info['http_code'] == 403:
                    message = (
                        'The video is not available in your region due to '
                        'right restrictions')
                else:
                    message = redirect_info['message']
                raise ExtractorError(message, expected=True)

            format_url = redirect_info.get('url')
            if not format_url:
                continue

            if determine_ext(format_url) == 'm3u8':
                formats.extend(self._extract_m3u8_formats(
                    format_url, display_id, 'mp4', preference=1, m3u8_id='hls'))
            else:
                formats.append({
                    'url': format_url,
                    'format_id': redirect.get('eeid'),
                })
        self._sort_formats(formats)

        rating_str = info.get('rating')
        if rating_str is not None:
            rating_str = rating_str.rpartition('-')[2]
        age_limit = US_RATINGS.get(rating_str)

        return {
            'id': video_id,
            'display_id': display_id,
            'title': info['title'],
            'description': info['program'].get('description'),
            'thumbnail': info.get('image_url'),
            'duration': int_or_none(info.get('duration')),
            'age_limit': age_limit,
            'upload_date': upload_date,
            'formats': formats,
        }