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