]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/pbs.py
Imported Upstream version 2015.07.21
[youtubedl] / youtube_dl / extractor / pbs.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8 ExtractorError,
9 determine_ext,
10 int_or_none,
11 unified_strdate,
12 US_RATINGS,
13 )
14
15
16 class PBSIE(InfoExtractor):
17 _VALID_URL = r'''(?x)https?://
18 (?:
19 # Direct video URL
20 video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
21 # Article with embedded player (or direct video)
22 (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
23 # Player
24 video\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
25 )
26 '''
27
28 _TESTS = [
29 {
30 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/',
31 'md5': 'ce1888486f0908d555a8093cac9a7362',
32 'info_dict': {
33 'id': '2365006249',
34 'ext': 'mp4',
35 'title': 'A More Perfect Union',
36 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
37 'duration': 3190,
38 },
39 'params': {
40 'skip_download': True, # requires ffmpeg
41 },
42 },
43 {
44 'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
45 'md5': '143c98aa54a346738a3d78f54c925321',
46 'info_dict': {
47 'id': '2365297690',
48 'ext': 'mp4',
49 'title': 'Losing Iraq',
50 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
51 'duration': 5050,
52 },
53 'params': {
54 'skip_download': True, # requires ffmpeg
55 }
56 },
57 {
58 'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
59 'md5': 'b19856d7f5351b17a5ab1dc6a64be633',
60 'info_dict': {
61 'id': '2201174722',
62 'ext': 'mp4',
63 'title': 'Cyber Schools Gain Popularity, but Quality Questions Persist',
64 'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28',
65 'duration': 801,
66 },
67 },
68 {
69 'url': 'http://www.pbs.org/wnet/gperf/dudamel-conducts-verdi-requiem-hollywood-bowl-full-episode/3374/',
70 'md5': 'c62859342be2a0358d6c9eb306595978',
71 'info_dict': {
72 'id': '2365297708',
73 'ext': 'mp4',
74 'description': 'md5:68d87ef760660eb564455eb30ca464fe',
75 'title': 'Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full',
76 'duration': 6559,
77 'thumbnail': 're:^https?://.*\.jpg$',
78 },
79 'params': {
80 'skip_download': True, # requires ffmpeg
81 },
82 },
83 {
84 'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html',
85 'md5': '908f3e5473a693b266b84e25e1cf9703',
86 'info_dict': {
87 'id': '2365160389',
88 'display_id': 'killer-typhoon',
89 'ext': 'mp4',
90 'description': 'md5:c741d14e979fc53228c575894094f157',
91 'title': 'Killer Typhoon',
92 'duration': 3172,
93 'thumbnail': 're:^https?://.*\.jpg$',
94 'upload_date': '20140122',
95 },
96 'params': {
97 'skip_download': True, # requires ffmpeg
98 },
99 },
100 {
101 'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
102 'info_dict': {
103 'id': 'united-states-of-secrets',
104 },
105 'playlist_count': 2,
106 },
107 {
108 'url': 'http://www.pbs.org/wgbh/americanexperience/films/death/player/',
109 'info_dict': {
110 'id': '2280706814',
111 'display_id': 'player',
112 'ext': 'mp4',
113 'title': 'Death and the Civil War',
114 'description': 'American Experience, TV’s most-watched history series, brings to life the compelling stories from our past that inform our understanding of the world today.',
115 'duration': 6705,
116 'thumbnail': 're:^https?://.*\.jpg$',
117 },
118 'params': {
119 'skip_download': True, # requires ffmpeg
120 },
121 }
122 ]
123
124 def _extract_webpage(self, url):
125 mobj = re.match(self._VALID_URL, url)
126
127 presumptive_id = mobj.group('presumptive_id')
128 display_id = presumptive_id
129 if presumptive_id:
130 webpage = self._download_webpage(url, display_id)
131
132 upload_date = unified_strdate(self._search_regex(
133 r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"',
134 webpage, 'upload date', default=None))
135
136 # tabbed frontline videos
137 tabbed_videos = re.findall(
138 r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"', webpage)
139 if tabbed_videos:
140 return tabbed_videos, presumptive_id, upload_date
141
142 MEDIA_ID_REGEXES = [
143 r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed
144 r'class="coveplayerid">([^<]+)<', # coveplayer
145 r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>', # jwplayer
146 ]
147
148 media_id = self._search_regex(
149 MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None)
150 if media_id:
151 return media_id, presumptive_id, upload_date
152
153 url = self._search_regex(
154 r'<iframe\s+[^>]*\s+src=["\']([^\'"]+partnerplayer[^\'"]+)["\']',
155 webpage, 'player URL')
156 mobj = re.match(self._VALID_URL, url)
157
158 player_id = mobj.group('player_id')
159 if not display_id:
160 display_id = player_id
161 if player_id:
162 player_page = self._download_webpage(
163 url, display_id, note='Downloading player page',
164 errnote='Could not download player page')
165 video_id = self._search_regex(
166 r'<div\s+id="video_([0-9]+)"', player_page, 'video ID')
167 else:
168 video_id = mobj.group('id')
169 display_id = video_id
170
171 return video_id, display_id, None
172
173 def _real_extract(self, url):
174 video_id, display_id, upload_date = self._extract_webpage(url)
175
176 if isinstance(video_id, list):
177 entries = [self.url_result(
178 'http://video.pbs.org/video/%s' % vid_id, 'PBS', vid_id)
179 for vid_id in video_id]
180 return self.playlist_result(entries, display_id)
181
182 info = self._download_json(
183 'http://video.pbs.org/videoInfo/%s?format=json&type=partner' % video_id,
184 display_id)
185
186 formats = []
187 for encoding_name in ('recommended_encoding', 'alternate_encoding'):
188 redirect = info.get(encoding_name)
189 if not redirect:
190 continue
191 redirect_url = redirect.get('url')
192 if not redirect_url:
193 continue
194
195 redirect_info = self._download_json(
196 redirect_url + '?format=json', display_id,
197 'Downloading %s video url info' % encoding_name)
198
199 if redirect_info['status'] == 'error':
200 if redirect_info['http_code'] == 403:
201 message = (
202 'The video is not available in your region due to '
203 'right restrictions')
204 else:
205 message = redirect_info['message']
206 raise ExtractorError(message, expected=True)
207
208 format_url = redirect_info.get('url')
209 if not format_url:
210 continue
211
212 if determine_ext(format_url) == 'm3u8':
213 formats.extend(self._extract_m3u8_formats(
214 format_url, display_id, 'mp4', preference=1, m3u8_id='hls'))
215 else:
216 formats.append({
217 'url': format_url,
218 'format_id': redirect.get('eeid'),
219 })
220 self._sort_formats(formats)
221
222 rating_str = info.get('rating')
223 if rating_str is not None:
224 rating_str = rating_str.rpartition('-')[2]
225 age_limit = US_RATINGS.get(rating_str)
226
227 subtitles = {}
228 closed_captions_url = info.get('closed_captions_url')
229 if closed_captions_url:
230 subtitles['en'] = [{
231 'ext': 'ttml',
232 'url': closed_captions_url,
233 }]
234
235 return {
236 'id': video_id,
237 'display_id': display_id,
238 'title': info['title'],
239 'description': info['program'].get('description'),
240 'thumbnail': info.get('image_url'),
241 'duration': int_or_none(info.get('duration')),
242 'age_limit': age_limit,
243 'upload_date': upload_date,
244 'formats': formats,
245 'subtitles': subtitles,
246 }