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