Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/pbs.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     unified_strdate,
   9     US_RATINGS,
  10 )
  11
  12
  13 class PBSIE(InfoExtractor):
  14     _VALID_URL = r'''(?x)https?://
  15         (?:
  16            # Direct video URL
  17            video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
  18            # Article with embedded player (or direct video)
  19            (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
  20            # Player
  21            video\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
  22         )
  23     '''
  24
  25     _TESTS = [
  26         {
  27             'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/',
  28             'md5': 'ce1888486f0908d555a8093cac9a7362',
  29             'info_dict': {
  30                 'id': '2365006249',
  31                 'ext': 'mp4',
  32                 'title': 'A More Perfect Union',
  33                 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
  34                 'duration': 3190,
  35             },
  36         },
  37         {
  38             'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
  39             'md5': '143c98aa54a346738a3d78f54c925321',
  40             'info_dict': {
  41                 'id': '2365297690',
  42                 'ext': 'mp4',
  43                 'title': 'Losing Iraq',
  44                 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
  45                 'duration': 5050,
  46             },
  47         },
  48         {
  49             'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
  50             'md5': 'b19856d7f5351b17a5ab1dc6a64be633',
  51             'info_dict': {
  52                 'id': '2201174722',
  53                 'ext': 'mp4',
  54                 'title': 'Cyber Schools Gain Popularity, but Quality Questions Persist',
  55                 'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28',
  56                 'duration': 801,
  57             },
  58         },
  59         {
  60             'url': 'http://www.pbs.org/wnet/gperf/dudamel-conducts-verdi-requiem-hollywood-bowl-full-episode/3374/',
  61             'md5': 'c62859342be2a0358d6c9eb306595978',
  62             'info_dict': {
  63                 'id': '2365297708',
  64                 'ext': 'mp4',
  65                 'description': 'md5:68d87ef760660eb564455eb30ca464fe',
  66                 'title': 'Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full',
  67                 'duration': 6559,
  68                 'thumbnail': 're:^https?://.*\.jpg$',
  69             }
  70         },
  71         {
  72             'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html',
  73             'md5': '908f3e5473a693b266b84e25e1cf9703',
  74             'info_dict': {
  75                 'id': '2365160389',
  76                 'display_id': 'killer-typhoon',
  77                 'ext': 'mp4',
  78                 'description': 'md5:c741d14e979fc53228c575894094f157',
  79                 'title': 'Killer Typhoon',
  80                 'duration': 3172,
  81                 'thumbnail': 're:^https?://.*\.jpg$',
  82                 'upload_date': '20140122',
  83             }
  84         },
  85         {
  86             'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
  87             'info_dict': {
  88                 'id': 'united-states-of-secrets',
  89             },
  90             'playlist_count': 2,
  91         }
  92     ]
  93
  94     def _extract_webpage(self, url):
  95         mobj = re.match(self._VALID_URL, url)
  96
  97         presumptive_id = mobj.group('presumptive_id')
  98         display_id = presumptive_id
  99         if presumptive_id:
 100             webpage = self._download_webpage(url, display_id)
 101
 102             upload_date = unified_strdate(self._search_regex(
 103                 r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"',
 104                 webpage, 'upload date', default=None))
 105
 106             # tabbed frontline videos
 107             tabbed_videos = re.findall(
 108                 r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"', webpage)
 109             if tabbed_videos:
 110                 return tabbed_videos, presumptive_id, upload_date
 111
 112             MEDIA_ID_REGEXES = [
 113                 r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'",  # frontline video embed
 114                 r'class="coveplayerid">([^<]+)<',                       # coveplayer
 115                 r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>',  # jwplayer
 116             ]
 117
 118             media_id = self._search_regex(
 119                 MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None)
 120             if media_id:
 121                 return media_id, presumptive_id, upload_date
 122
 123             url = self._search_regex(
 124                 r'<iframe\s+(?:class|id)=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>',
 125                 webpage, 'player URL')
 126             mobj = re.match(self._VALID_URL, url)
 127
 128         player_id = mobj.group('player_id')
 129         if not display_id:
 130             display_id = player_id
 131         if player_id:
 132             player_page = self._download_webpage(
 133                 url, display_id, note='Downloading player page',
 134                 errnote='Could not download player page')
 135             video_id = self._search_regex(
 136                 r'<div\s+id="video_([0-9]+)"', player_page, 'video ID')
 137         else:
 138             video_id = mobj.group('id')
 139             display_id = video_id
 140
 141         return video_id, display_id, None
 142
 143     def _real_extract(self, url):
 144         video_id, display_id, upload_date = self._extract_webpage(url)
 145
 146         if isinstance(video_id, list):
 147             entries = [self.url_result(
 148                 'http://video.pbs.org/video/%s' % vid_id, 'PBS', vid_id)
 149                 for vid_id in video_id]
 150             return self.playlist_result(entries, display_id)
 151
 152         info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
 153         info = self._download_json(info_url, display_id)
 154
 155         redirect_url = info['alternate_encoding']['url']
 156         redirect_info = self._download_json(
 157             redirect_url + '?format=json', display_id,
 158             'Downloading video url info')
 159         if redirect_info['status'] == 'error':
 160             if redirect_info['http_code'] == 403:
 161                 message = (
 162                     'The video is not available in your region due to '
 163                     'right restrictions')
 164             else:
 165                 message = redirect_info['message']
 166             raise ExtractorError(message, expected=True)
 167
 168         rating_str = info.get('rating')
 169         if rating_str is not None:
 170             rating_str = rating_str.rpartition('-')[2]
 171         age_limit = US_RATINGS.get(rating_str)
 172
 173         return {
 174             'id': video_id,
 175             'display_id': display_id,
 176             'title': info['title'],
 177             'url': redirect_info['url'],
 178             'ext': 'mp4',
 179             'description': info['program'].get('description'),
 180             'thumbnail': info.get('image_url'),
 181             'duration': info.get('duration'),
 182             'age_limit': age_limit,
 183             'upload_date': upload_date,
 184         }